Artificial Intelligence for healthcare applications and management:
Artificial Intelligence for Healthcare Applications and Management introduces application domains of various AI algorithms across healthcare management. Instead of discussing AI first and then exploring its applications in healthcare afterward, the authors attack the problems in context directly, in...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
London, United Kingdom
Academic Press, Elsevier
[2022]
|
| Ausgabe: | Boris Galitsky, Saveli Goldberg |
| Schlagworte: | |
| Online-Zugang: | Inhaltsverzeichnis |
| Zusammenfassung: | Artificial Intelligence for Healthcare Applications and Management introduces application domains of various AI algorithms across healthcare management. Instead of discussing AI first and then exploring its applications in healthcare afterward, the authors attack the problems in context directly, in order to accelerate the path of an interested reader toward building industrial-strength healthcare applications. Readers will be introduced to a wide spectrum of AI applications supporting all stages of patient flow in a healthcare facility. The authors explain how AI supports patients throughout a healthcare facility, including diagnosis and treatment recommendations needed to get patients from the point of admission to the point of discharge while maintaining quality, patient safety, and patient/provider satisfaction.AI methods are expected to decrease the burden on physicians, improve the quality of patient care, and decrease overall treatment costs. Current conditions affected by COVID-19 pose new challenges for healthcare management and learning how to apply AI will be important for a broad spectrum of students and mature professionals working in medical informatics. This book focuses on predictive analytics, health text processing, data aggregation, management of patients, and other fields which have all turned out to be bottlenecks for the efficient management of coronavirus patients.- Presents an in-depth exploration of how AI algorithms embedded in scheduling, prediction, automated support, personalization, and diagnostics can improve the efficiency of patient treatment- Investigates explainable AI, including explainable decision support and machine learning, from limited data to back-up clinical decisions, and data analysis- Offers hands-on skills to computer science and medical informatics students to aid them in designing intelligent systems for healthcare- Informs a broad, multidisciplinary audience about a multitude of applications of machine learning and linguistics across various healthcare fields- Introduces medical discourse analysis for a high-level representation of health texts |
| Beschreibung: | xv, 532 Seiten Illustrationen, Diagramme |
| ISBN: | 9780128245217 |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV048203262 | ||
| 003 | DE-604 | ||
| 005 | 20230306 | ||
| 007 | t | ||
| 008 | 220506s2022 a||| |||| 00||| eng d | ||
| 020 | |a 9780128245217 |c pbk |9 978-0-12-824521-7 | ||
| 024 | 3 | |a 9780128245217 | |
| 035 | |a (OCoLC)1334032067 | ||
| 035 | |a (DE-599)BVBBV048203262 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-29T |a DE-739 |a DE-1043 |a DE-898 | ||
| 084 | |a ST 640 |0 (DE-625)143686: |2 rvk | ||
| 100 | 1 | |a Galitsky, Boris |e Verfasser |0 (DE-588)122085025X |4 aut | |
| 245 | 1 | 0 | |a Artificial Intelligence for healthcare applications and management |
| 250 | |a Boris Galitsky, Saveli Goldberg | ||
| 264 | 1 | |a London, United Kingdom |b Academic Press, Elsevier |c [2022] | |
| 300 | |a xv, 532 Seiten |b Illustrationen, Diagramme | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 520 | |a Artificial Intelligence for Healthcare Applications and Management introduces application domains of various AI algorithms across healthcare management. Instead of discussing AI first and then exploring its applications in healthcare afterward, the authors attack the problems in context directly, in order to accelerate the path of an interested reader toward building industrial-strength healthcare applications. Readers will be introduced to a wide spectrum of AI applications supporting all stages of patient flow in a healthcare facility. The authors explain how AI supports patients throughout a healthcare facility, including diagnosis and treatment recommendations needed to get patients from the point of admission to the point of discharge while maintaining quality, patient safety, and patient/provider satisfaction.AI methods are expected to decrease the burden on physicians, improve the quality of patient care, and decrease overall treatment costs. | ||
| 520 | |a Current conditions affected by COVID-19 pose new challenges for healthcare management and learning how to apply AI will be important for a broad spectrum of students and mature professionals working in medical informatics. | ||
| 520 | |a This book focuses on predictive analytics, health text processing, data aggregation, management of patients, and other fields which have all turned out to be bottlenecks for the efficient management of coronavirus patients.- Presents an in-depth exploration of how AI algorithms embedded in scheduling, prediction, automated support, personalization, and diagnostics can improve the efficiency of patient treatment- Investigates explainable AI, including explainable decision support and machine learning, from limited data to back-up clinical decisions, and data analysis- Offers hands-on skills to computer science and medical informatics students to aid them in designing intelligent systems for healthcare- Informs a broad, multidisciplinary audience about a multitude of applications of machine learning and linguistics across various healthcare fields- Introduces medical discourse analysis for a high-level representation of health texts | ||
| 650 | 0 | 7 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Medizin |0 (DE-588)4038243-6 |2 gnd |9 rswk-swf |
| 689 | 0 | 0 | |a Medizin |0 (DE-588)4038243-6 |D s |
| 689 | 0 | 1 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |D s |
| 689 | 0 | |5 DE-604 | |
| 700 | 1 | |a Goldberg, Saveli |e Verfasser |4 aut | |
| 856 | 4 | 2 | |m Digitalisierung UB Passau - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=033584217&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-033584217 | ||
Datensatz im Suchindex
| _version_ | 1804183969985462272 |
|---|---|
| adam_text | Contents Contributors........................................................................................................................................ xv Introduction.................................................................................. 1 CHAPTER 1 Boris Galitsky 1. The issues of ML in medicine this book is solving................................................ 4 2. AI for diagnosis and treatment..................................................................................7 3. Health discourse........................................................................................................ 9 References................................................................................................................И CHAPTER 2 Multi-case-based reasoning by syntactic-semantic alignment and discourse analysis........................................... із Boris Galitsky 1. Introduction.............................................................................................................. 13 2. Multi-case-based reasoning in the medicalfield...................................................... 15 3. 4. 5. 6. 7. 8. 9. 2.1 Mixed illness description................................................................................... 19 2.2 Probabilistic ontology........................................................................................ 21 2.3 Mapping a patient record to identified cases......................................................24 2.4 Learning semantic
similarity............................................................................. 28 2.5 Discourse analysis and discourse trees..............................................................30 Alignment of linguistic graphs.................................................................................32 3.1 Abstract meaning representation........................................................................32 3.2 Aligning AMR................................................................................................... 37 3.3 Alignment algorithm......................................................................................... 38 Case-based reasoning in health................................................................................39 4.1 Mining cases from health forum threads.......................................................... 43 4.2 Discourse disentanglement................................................................................ 45 Building a repository of labeled cases anddiagnoses.............................................. 45 5.1 An example of navigating an extended discourse tree for three documents....45 5.2 Constructing extended DTs........................................................................ 48 System architecture..................................................................................................52 Evaluation................................................................................................................ 54 7.1
Datasets.............................................................................................................. 54 7.2 Evaluation of text matching.............................................................................. 54 7.3 Overall assessment of the Symptom Checker engine....................................... 57 7.4 Diagnosing forum data...................................................................................... 58 Related work............................................................................................................ 60 Conclusions.............................................................................................................. 64 References............................................................................................................... 66 V
vi Contents CHAPTER 3 Obtaining supported decision trees from text for health system applications........................................................... 71 Boris Galitsky 1. Introduction................................................................................................................... 71 1.1 Supported decision trees for anexpertsystem........................................................ 72 2. Obtaining supported decision treesfromtext............................................................... 73 2.1 From a discourse tree to its supported decision tree.......................................... 73 2.2 System architecture of construction of a supported decision tree.................... 79 3. Evaluation...................................................................................................................... 80 4. Decision trees in health................................................................................................ 84 4.1 Defining decision tree as a supervised learning task...........................................84 4.2 Decision trees and COVID-19........................................................................ 88 5. Expert system for health management........................................................................ 91 5.1 Basic expert systems and their values in health domain..................................... 91 5.2 Backward chaining inference................................................................................. 95 5.3 Expert system and health
management..................................................................96 5.4 Clinical use of expert systems............................................................................. 101 5.5 Expert system lifecycle......................................................................................... 102 5.6 Learning ES rules...................................................................................................104 5.7 Dynamics of ES usage.......................................................................................... 107 6. Conclusions.................................................................................................................... 109 References.....................................................................................................................109 CHAPTER 4 Search and prevention of errors in medical databases............... 113 Saveli Goldberg 1. Introduction ................................................................................................................. 113 2. Data entry errors when transferring information from the initial medical documentation to the studied database................................................................. 113 2.1 Analyzed databases................................................................................................113 2.2 Impossible/internally inconsistent data................................................................ 114 2.3 Externally inconsistent data................................................................................ 115 2.4
Impossible/internally inconsistent data entry in В and S databases............... 116 2.5 Specific type of the errors “omitted data”......................................................... 116 3. Errors in initial medical information........................................................................ 119 3.1 Measurement errors “bodyweight” as an indicator of the quality of the initial information............................................................................................ 119 3.2 Algorithm.................................................................................................................119 3.3 Errors in EMR data................................................................................................ 120 3.4 User history of previous errors............................................................................. 121 3.5 Physicians vs non-physicians................................................................................ 121 3.6 Effect of practice location on weight error rates................................................ 122 3.7 Error rates over time.............................................................................................. 122
Contents vii 3.8 Error rates and user experience........................................................................ 123 4. Error reduction....................................................................................................... 123 4.1 Detection errors in datasets.............................................................................. 123 4.2 Alarm system in data entry process................................................................. 124 4.3 “Follow-up summary” as a method of error prevention................................. 126 5. Conclusions............................................................................................................. 131 References.............................................................................................................. 132 CHAPTER 5 Overcoming Al applications challenges in health: Decision system DINAR2...................................................... 135 Saveli Goldberg and Mark Prutkin 1. Introduction............................................................................................................ 135 2. Problems of introducing medical AI applications................................................. 135 2.1 Domain overfitting...........................................................................................135 2.2 Terminology problems................................................................................... 136 2.3 Cognitive bias................................................................................................... 137 2.4 Integration of AI
into clinical practice............................................................ 139 3. Integrated decision support system at the regional consultative Center for Intensive Pediatrics (DINAR2)................................................................... 140 3.1 Idea and problems of the regional consultative Center for Intensive Pediatrics................................................................................................... 140 3.2 History of DINAR2 development.................................................................... 141 3.3 Methods............................................................................................................144 3.4 DINAR2 efficiency.......................................................................................... 152 4. Conclusions............................................................................................................. 157 References.............................................................................................................. 158 CHAPTER 6 Formulating critical questions tothe user in the course of decision-making.................................................................... 161 Boris Galitsky 1. Introduction............................................................................................................ 161 2. Reasoning patterns and formulating critical questions.......................................... 165 3. Automated building of reasoning chains............................................................... 168 3.1 Questions as relative complement
of linguistic representations............................................................................................ 170 3.2 Generating text from AMR graph fragment.................................................... 173 3.3 Deriving critical questions via anti-unification............................................... 175 4. Question-generation system architecture............................................................... 178 4.1 Chatbot implementation................................................................................... 180 4.2 Data collection..................................................................................................181 5. Evaluation...............................................................................................................183
viii Contents 6. Syntactic and semantic generalizations.................................................................... 186 6.1 Semantic generalization........................................................................................ 189 6.2 Attribute-based generalization.............................................................................. 192 7. Building questions via generalization of instances................................................. 193 8. Discussion and conclusions........................................................................................ 196 References..................................................................................................................... 197 CHAPTER 7 1. 2. 3. 4. 5. 6. 7. 8. 9. 10. 11. 12. 13. CHAPTER 8 Relying on discourse analysis to answer complex questions by neural machine reading comprehension................................ 201 Boris Galitsky Introduction................................................................................................................. 201 Examples where discourse analysis is essentialfor MRC...................................... 203 Discourse dataset.........................................................................................................204 Discourse parsing....................................................................................................... 206 Incorporating syntax into model............................................................................... 209 Attention mechanism for the sequence of
tokens.................................................... 210 Enabling attention mechanism with syntacticfeatures............................................212 Including discourse structure into the model........................................................... 216 Pre-trained language models and their semantic extensions..................................217 9.1 Encoding and alignment with BERT................................................................... 218 Direct similarity-based question answering............................................................. 219 10.1 Correcting an MRC answer................................................................................ 224 System architecture.................................................................................................... 225 Evaluation.................................................................................................................... 226 Discussion and conclusions........................................................................................229 References.................................................................................................................... 231 Machine reading between the lines (RBL) of medical complaints................................................................................ 235 Boris Galitsky 1. Introduction................................................................................................................. 235 1.1 RBL, machine reading comprehension, and inference...................................... 237 1.2 RBL and
common sense..................................................................................... 238 2. RBL as generalization and web mining..................................................................... 239 2.1 Patient repeats what he wants to say................................................................... 239 2.2 Reading deep between the lines........................................................................... 242 2.3 RBL in storytelling................................................................................................ 247 2.4 Extracting RBL results from text......................................................................... 249 2.5 Difficult RBL cases................................................................................................249 2.6 RBL in a dialogue..................................................................................................251 2.7 Question formation and diversification............................................................... 253
Contents ix 3. System architecture................................................................................................254 4. Statistical model of RBL........................................................................................255 5. RBL and NLI..........................................................................................................259 5.1 NLI and semantic fragments........................................................................... 260 5.2 Reinforcement learning approach................................................................... 263 5.3 Language models............................................................................................. 265 5.4 Storytelling discourse approach.......................................................................266 6. Evaluation.............................................................................................................. 267 6.1 Meaningfulness of generated RBLs................................................................ 268 6.2 Search recall improvement.............................................................................. 268 7. Discussions............................................................................................................ 269 8. Conclusions............................................................................................................ 272 References............................................................................................................. 274 CHAPTER 9 1. 2. 3. 4. 5. 6. 7. 8. 9. 10. Discourse means
for maintaining a proper rhetorical flow........... 279 Boris Galitsky Introduction............................................................................................................279 1.1 Medical dialogue systems............................................................................... 281 Discourse tree of a dialogue.................................................................................. 282 2.1 Response selection.......................................................................................... 283 2.2 Speech acts and communicative actions..........................................................285 2.3 A dialogue with doubt..................................................................................... 286 2,4 Further extending the set of rhetorical relations toward dialogue.................. 287 Computing rhetorical relation of entailment......................................................... 288 Dialogue generation as language modeling........................................................... 292 4.1 Strategies for informative conversations......................................................... 294 Rhetorical agreement between questions and answers.......................................... 296 Discourse parsing of a dialogue.............................................................................297 Constructing a dialogue from text......................................................................... 304 7.1 Building a dialogue based on a DT.................................................................305 7.2
Constructing questions.................................................................................... 306 System architecture................................................................................................308 Evaluation.............................................................................................................. 310 Discussions and conclusions................................................................................. 313 References............................................................................................................. 317 CHAPTER 10 Dialogue management based on forcing a user through a discourse tree of a text..............................................323 Boris Galitsky 1. Introduction............................................................................................................323 2. Keeping a learner focused on a text...................................................................... 325
x Contents 3. Navigating discourse tree in conversation............................................................... 330 4. The dialogue flow....................................................................................................... 332 4.1 Managing user intents........................................................................................... 334 4.2 Handling epistemic states...................................................................................... 337 5. User intent recognizer................................................................................................ 340 5.1 Nearest neighbor-based learning for user intentrecognition............................. 343 6. System architecture..................................................................................................... 344 7. Evaluation.................................................................................................................... 345 7.1 Evaluation setting.................................................................................................. 345 7.2 Assessment of navigation algorithm.................................................................... 347 8. Related work................................................................................................................ 350 8.1 Personalization in health chatbots........................................................................ 354 8.2 Interaction in the mental space.............................................................................354 8.3 Persuasive
dialogue............................................................................................... 357 9. Conclusions.................................................................................................................. 359 References.....................................................................................................................359 CHAPTER 11 Building medical ontologies relying on communicative discourse trees............................................................................................. 365 Boris Galitsky and Dmitry llvovsky 1. Introduction................................................................................................................. 365 1.1 Ontology extraction from text.............................................................................. 366 1.2 Text mining............................................................................................................ 366 2. Introducing discourse features................................................................................... 367 2.1 Discourse-level support for ontology construction............................................. 368 2.2 Issues associated with not using discourse information for ontology entry extraction................................................................................................................ 370 2.3 Annotating events...................................................................................................372 3. Informative and uninformative parts of
text.............................................................374 3.1 Informative and uninformative parts of an answer............................................374 3.2 How a discourse tree indicates what to index andwhat not to index.............. 377 3.3 How rhetorical relations determine indexing rules............................................379 4. Designing ontologies................................................................................................... 380 4.1 Systematized nomenclature of medicine—Clinical terms................................ 380 4.2 Relation extractor based on syntactic parsing.................................................... 381 4.3 Conceptualization process..................................................................................... 383 5. Neural dictionary manager......................................................................................... 386 6. Phrase aggregator........................................................................................................ 388 7. Ontologies supporting reasoning................................................................................ 390
Contents 8. 9. 10. 11. 12. xi 7.1 Entity grid helps to extract relationships.........................................................394 7.2 Validating ontology..........................................................................................395 Specific ontology types in bioinformatics............................................................. 397 8.1 Spatial taxonomy............................................................................................. 397 Supporting search...................................................................................................398 System architecture............................................................................................... 403 Evaluation.............................................................................................................. 406 11.1 Datasets.......................................................................................................... 406 11.2 Assessment of ontology consistency..............................................................406 11.3 An assessment of search improvement due to ontology....... ....................... 408 Conclusions............................................................................................................ 409 References............................................................................................................. 411 CHAPTER 12 Explanation in medical decision support systems....................... 415 1. 2. 3. 4. 5. 6. Saveli Goldberg
Introduction........................................................................................................... 415 Models of machine learning explanation............................................................... 415 2.1 Interpretable models........................................................................................ 415 2.2 Black-box models............................................................................................ 416 Explanation based on comparison of the local case with the closest case with an alternative ML solution....................................................................... 418 3.1 Finding the closest point to a local case......................................................... 422 A bi-directional adversarial meta-agent between user and ML system................ 422 4.1 Meta-agent behavior........................................................................................ 422 4.2 Steps of the meta-agent................................................................................... 424 Discussion.............................................................................................................. 427 Conclusions............................................................................................................ 428 References............................................................................................................. 428 CHAPTER 13 Passive decision support for patient management...................... 431 Saveli Goldberg and Stanislav Belyaev 1.
Introduction........................................................................................................... 431 2. Dr. Watson-type systems....................................................................................... 432 2.1 Principles of Dr. Watson-type systems............................................................432 2.2 Dr. Watson-type system formalization............................................................434 3. Patient management system (SAGe).....................................................................435 3.1 Requirements and subsystems......................................................................... 435 3.2 Information import.......................................................................................... 436
xii Contents 3.3 Diagnostics............................................................................................................. 436 3.4 Treatment effectiveness......................................................................................... 440 3.5 Treatment adequacy.............................................................................................. 442 3.6 Discontinuation of observation............................................................................ 442 3.7 Integral assessment of patients in the department............................................ 444 3.8 Features of Dr. Watson-type system presented in SAGe.................................. 445 4. Conclusions................................................................................................................... 446 References.................................................................................................................... 446 CHAPTER 14 Multimodal discourse trees for health management and security..................................................................... 449 Boris Galitsky 1. Introduction.................................................................................................................. 449 1.1 Forensic linguistics................................................................................................ 450 1.2 Extended discourse trees....................................................................................... 451 1.3 Victims’ right and state responsibility to investigate........................................
452 2. Discourse analysis of health and security-related scenarios................................... 452 2.1 Discourse of a reasonable doubt.......................................................................... 452 2.2 Discourse analysis of a scenario.......................................................................... 453 3. Multimodal discourse representation......................................................................... 454 3.1 Multimodal discourse tree for a crime report..................................................... 457 3.2 Multimodal data sources and references between them.................................... 457 3.3 Manipulation with discourse trees...................................................................... 462 3.4 Extended discourse tree........................................................................................ 464 4. Mobile location data and COVID-19......................................................................... 464 4.1 Call detail records and COVID-19...................................................................... 467 4.2 Automatic number plate recognition................................................................... 472 5. Reasoning about a cause and effect of data records...............................................473 5.1 Representing causal links by R-Cframework..................................................... 474 5.2 Reasoning with arguments extracted from text................................................... 475 6. System
architecture..................................................................................................... 478 7. Evaluation.................................................................................................................... 480 8. Discussions and conclusions...................................................................................... 481 References.................................................................................................................... 485 CHAPTER 15 Improving open domain content generation by text mining and alignment................................................................. 489 Boris Galitsky 1. Introduction................................................................................................................. 489 1.1 Content generation in health care........................................................................ 490
Contents 2. 3. 4. 5. 6. 7. 8. 9. 10. xiii 1.2 Content generation for personalization ............................................................491 1.3 Natural language generation in intensive care................................................492 Processing raw natural language generation results............................................. 494 2.1 Alignment of raw and true content................................................................. 495 Fact-checking of deep learning generation........................................................... 498 3.1 Personalized drug recommendation................................................................ 499 3.2 Discourse structure deviation of the corrected content................................... 500 System architecture............................................................................................... 501 4.1 Deep learning subsystem................................................................................. 503 4.2 Raw content correction....................................................................................504 Probabilistic text merging.....................................................................................504 Graph-based fact-checking....................................................................................507 Entity substitution..................................................................................................511 Evaluation............................................................................................................. 513
Discussions........................................................................................................... 515 Conclusions............................................................................................................518 References............................................................................................................. 519 Index................................................................................................................................................. 523
|
| adam_txt |
Contents Contributors. xv Introduction. 1 CHAPTER 1 Boris Galitsky 1. The issues of ML in medicine this book is solving. 4 2. AI for diagnosis and treatment.7 3. Health discourse. 9 References.И CHAPTER 2 Multi-case-based reasoning by syntactic-semantic alignment and discourse analysis. із Boris Galitsky 1. Introduction. 13 2. Multi-case-based reasoning in the medicalfield. 15 3. 4. 5. 6. 7. 8. 9. 2.1 Mixed illness description. 19 2.2 Probabilistic ontology. 21 2.3 Mapping a patient record to identified cases.24 2.4 Learning semantic
similarity. 28 2.5 Discourse analysis and discourse trees.30 Alignment of linguistic graphs.32 3.1 Abstract meaning representation.32 3.2 Aligning AMR. 37 3.3 Alignment algorithm. 38 Case-based reasoning in health.39 4.1 Mining cases from health forum threads. 43 4.2 Discourse disentanglement. 45 Building a repository of labeled cases anddiagnoses. 45 5.1 An example of navigating an extended discourse tree for three documents.45 5.2 Constructing extended DTs. 48 System architecture.52 Evaluation. 54 7.1
Datasets. 54 7.2 Evaluation of text matching. 54 7.3 Overall assessment of the Symptom Checker engine. 57 7.4 Diagnosing forum data. 58 Related work. 60 Conclusions. 64 References. 66 V
vi Contents CHAPTER 3 Obtaining supported decision trees from text for health system applications. 71 Boris Galitsky 1. Introduction. 71 1.1 Supported decision trees for anexpertsystem. 72 2. Obtaining supported decision treesfromtext. 73 2.1 From a discourse tree to its supported decision tree. 73 2.2 System architecture of construction of a supported decision tree. 79 3. Evaluation. 80 4. Decision trees in health. 84 4.1 Defining decision tree as a supervised learning task.84 4.2 Decision trees and COVID-19. 88 5. Expert system for health management. 91 5.1 Basic expert systems and their values in health domain. 91 5.2 Backward chaining inference. 95 5.3 Expert system and health
management.96 5.4 Clinical use of expert systems. 101 5.5 Expert system lifecycle. 102 5.6 Learning ES rules.104 5.7 Dynamics of ES usage. 107 6. Conclusions. 109 References.109 CHAPTER 4 Search and prevention of errors in medical databases. 113 Saveli Goldberg 1. Introduction . 113 2. Data entry errors when transferring information from the initial medical documentation to the studied database. 113 2.1 Analyzed databases.113 2.2 Impossible/internally inconsistent data. 114 2.3 Externally inconsistent data. 115 2.4
Impossible/internally inconsistent data entry in В and S databases. 116 2.5 Specific type of the errors “omitted data”. 116 3. Errors in initial medical information. 119 3.1 Measurement errors “bodyweight” as an indicator of the quality of the initial information. 119 3.2 Algorithm.119 3.3 Errors in EMR data. 120 3.4 User history of previous errors. 121 3.5 Physicians vs non-physicians. 121 3.6 Effect of practice location on weight error rates. 122 3.7 Error rates over time. 122
Contents vii 3.8 Error rates and user experience. 123 4. Error reduction. 123 4.1 Detection errors in datasets. 123 4.2 Alarm system in data entry process. 124 4.3 “Follow-up summary” as a method of error prevention. 126 5. Conclusions. 131 References. 132 CHAPTER 5 Overcoming Al applications challenges in health: Decision system DINAR2. 135 Saveli Goldberg and Mark Prutkin 1. Introduction. 135 2. Problems of introducing medical AI applications. 135 2.1 Domain overfitting.135 2.2 Terminology problems. 136 2.3 Cognitive bias. 137 2.4 Integration of AI
into clinical practice. 139 3. Integrated decision support system at the regional consultative Center for Intensive Pediatrics (DINAR2). 140 3.1 Idea and problems of the regional consultative Center for Intensive Pediatrics. 140 3.2 History of DINAR2 development. 141 3.3 Methods.144 3.4 DINAR2 efficiency. 152 4. Conclusions. 157 References. 158 CHAPTER 6 Formulating critical questions tothe user in the course of decision-making. 161 Boris Galitsky 1. Introduction. 161 2. Reasoning patterns and formulating critical questions. 165 3. Automated building of reasoning chains. 168 3.1 Questions as relative complement
of linguistic representations. 170 3.2 Generating text from AMR graph fragment. 173 3.3 Deriving critical questions via anti-unification. 175 4. Question-generation system architecture. 178 4.1 Chatbot implementation. 180 4.2 Data collection.181 5. Evaluation.183
viii Contents 6. Syntactic and semantic generalizations. 186 6.1 Semantic generalization. 189 6.2 Attribute-based generalization. 192 7. Building questions via generalization of instances. 193 8. Discussion and conclusions. 196 References. 197 CHAPTER 7 1. 2. 3. 4. 5. 6. 7. 8. 9. 10. 11. 12. 13. CHAPTER 8 Relying on discourse analysis to answer complex questions by neural machine reading comprehension. 201 Boris Galitsky Introduction. 201 Examples where discourse analysis is essentialfor MRC. 203 Discourse dataset.204 Discourse parsing. 206 Incorporating syntax into model. 209 Attention mechanism for the sequence of
tokens. 210 Enabling attention mechanism with syntacticfeatures.212 Including discourse structure into the model. 216 Pre-trained language models and their semantic extensions.217 9.1 Encoding and alignment with BERT. 218 Direct similarity-based question answering. 219 10.1 Correcting an MRC answer. 224 System architecture. 225 Evaluation. 226 Discussion and conclusions.229 References. 231 Machine reading between the lines (RBL) of medical complaints. 235 Boris Galitsky 1. Introduction. 235 1.1 RBL, machine reading comprehension, and inference. 237 1.2 RBL and
common sense. 238 2. RBL as generalization and web mining. 239 2.1 Patient repeats what he wants to say. 239 2.2 Reading deep between the lines. 242 2.3 RBL in storytelling. 247 2.4 Extracting RBL results from text. 249 2.5 Difficult RBL cases.249 2.6 RBL in a dialogue.251 2.7 Question formation and diversification. 253
Contents ix 3. System architecture.254 4. Statistical model of RBL.255 5. RBL and NLI.259 5.1 NLI and semantic fragments. 260 5.2 Reinforcement learning approach. 263 5.3 Language models. 265 5.4 Storytelling discourse approach.266 6. Evaluation. 267 6.1 Meaningfulness of generated RBLs. 268 6.2 Search recall improvement. 268 7. Discussions. 269 8. Conclusions. 272 References. 274 CHAPTER 9 1. 2. 3. 4. 5. 6. 7. 8. 9. 10. Discourse means
for maintaining a proper rhetorical flow. 279 Boris Galitsky Introduction.279 1.1 Medical dialogue systems. 281 Discourse tree of a dialogue. 282 2.1 Response selection. 283 2.2 Speech acts and communicative actions.285 2.3 A dialogue with doubt. 286 2,4 Further extending the set of rhetorical relations toward dialogue. 287 Computing rhetorical relation of entailment. 288 Dialogue generation as language modeling. 292 4.1 Strategies for informative conversations. 294 Rhetorical agreement between questions and answers. 296 Discourse parsing of a dialogue.297 Constructing a dialogue from text. 304 7.1 Building a dialogue based on a DT.305 7.2
Constructing questions. 306 System architecture.308 Evaluation. 310 Discussions and conclusions. 313 References. 317 CHAPTER 10 Dialogue management based on forcing a user through a discourse tree of a text.323 Boris Galitsky 1. Introduction.323 2. Keeping a learner focused on a text. 325
x Contents 3. Navigating discourse tree in conversation. 330 4. The dialogue flow. 332 4.1 Managing user intents. 334 4.2 Handling epistemic states. 337 5. User intent recognizer. 340 5.1 Nearest neighbor-based learning for user intentrecognition. 343 6. System architecture. 344 7. Evaluation. 345 7.1 Evaluation setting. 345 7.2 Assessment of navigation algorithm. 347 8. Related work. 350 8.1 Personalization in health chatbots. 354 8.2 Interaction in the mental space.354 8.3 Persuasive
dialogue. 357 9. Conclusions. 359 References.359 CHAPTER 11 Building medical ontologies relying on communicative discourse trees. 365 Boris Galitsky and Dmitry llvovsky 1. Introduction. 365 1.1 Ontology extraction from text. 366 1.2 Text mining. 366 2. Introducing discourse features. 367 2.1 Discourse-level support for ontology construction. 368 2.2 Issues associated with not using discourse information for ontology entry extraction. 370 2.3 Annotating events.372 3. Informative and uninformative parts of
text.374 3.1 Informative and uninformative parts of an answer.374 3.2 How a discourse tree indicates what to index andwhat not to index. 377 3.3 How rhetorical relations determine indexing rules.379 4. Designing ontologies. 380 4.1 Systematized nomenclature of medicine—Clinical terms. 380 4.2 Relation extractor based on syntactic parsing. 381 4.3 Conceptualization process. 383 5. Neural dictionary manager. 386 6. Phrase aggregator. 388 7. Ontologies supporting reasoning. 390
Contents 8. 9. 10. 11. 12. xi 7.1 Entity grid helps to extract relationships.394 7.2 Validating ontology.395 Specific ontology types in bioinformatics. 397 8.1 Spatial taxonomy. 397 Supporting search.398 System architecture. 403 Evaluation. 406 11.1 Datasets. 406 11.2 Assessment of ontology consistency.406 11.3 An assessment of search improvement due to ontology. . 408 Conclusions. 409 References. 411 CHAPTER 12 Explanation in medical decision support systems. 415 1. 2. 3. 4. 5. 6. Saveli Goldberg
Introduction. 415 Models of machine learning explanation. 415 2.1 Interpretable models. 415 2.2 Black-box models. 416 Explanation based on comparison of the local case with the closest case with an alternative ML solution. 418 3.1 Finding the closest point to a local case. 422 A bi-directional adversarial meta-agent between user and ML system. 422 4.1 Meta-agent behavior. 422 4.2 Steps of the meta-agent. 424 Discussion. 427 Conclusions. 428 References. 428 CHAPTER 13 Passive decision support for patient management. 431 Saveli Goldberg and Stanislav Belyaev 1.
Introduction. 431 2. Dr. Watson-type systems. 432 2.1 Principles of Dr. Watson-type systems.432 2.2 Dr. Watson-type system formalization.434 3. Patient management system (SAGe).435 3.1 Requirements and subsystems. 435 3.2 Information import. 436
xii Contents 3.3 Diagnostics. 436 3.4 Treatment effectiveness. 440 3.5 Treatment adequacy. 442 3.6 Discontinuation of observation. 442 3.7 Integral assessment of patients in the department. 444 3.8 Features of Dr. Watson-type system presented in SAGe. 445 4. Conclusions. 446 References. 446 CHAPTER 14 Multimodal discourse trees for health management and security. 449 Boris Galitsky 1. Introduction. 449 1.1 Forensic linguistics. 450 1.2 Extended discourse trees. 451 1.3 Victims’ right and state responsibility to investigate.
452 2. Discourse analysis of health and security-related scenarios. 452 2.1 Discourse of a reasonable doubt. 452 2.2 Discourse analysis of a scenario. 453 3. Multimodal discourse representation. 454 3.1 Multimodal discourse tree for a crime report. 457 3.2 Multimodal data sources and references between them. 457 3.3 Manipulation with discourse trees. 462 3.4 Extended discourse tree. 464 4. Mobile location data and COVID-19. 464 4.1 Call detail records and COVID-19. 467 4.2 Automatic number plate recognition. 472 5. Reasoning about a cause and effect of data records.473 5.1 Representing causal links by R-Cframework. 474 5.2 Reasoning with arguments extracted from text. 475 6. System
architecture. 478 7. Evaluation. 480 8. Discussions and conclusions. 481 References. 485 CHAPTER 15 Improving open domain content generation by text mining and alignment. 489 Boris Galitsky 1. Introduction. 489 1.1 Content generation in health care. 490
Contents 2. 3. 4. 5. 6. 7. 8. 9. 10. xiii 1.2 Content generation for personalization .491 1.3 Natural language generation in intensive care.492 Processing raw natural language generation results. 494 2.1 Alignment of raw and true content. 495 Fact-checking of deep learning generation. 498 3.1 Personalized drug recommendation. 499 3.2 Discourse structure deviation of the corrected content. 500 System architecture. 501 4.1 Deep learning subsystem. 503 4.2 Raw content correction.504 Probabilistic text merging.504 Graph-based fact-checking.507 Entity substitution.511 Evaluation. 513
Discussions. 515 Conclusions.518 References. 519 Index. 523 |
| any_adam_object | 1 |
| any_adam_object_boolean | 1 |
| author | Galitsky, Boris Goldberg, Saveli |
| author_GND | (DE-588)122085025X |
| author_facet | Galitsky, Boris Goldberg, Saveli |
| author_role | aut aut |
| author_sort | Galitsky, Boris |
| author_variant | b g bg s g sg |
| building | Verbundindex |
| bvnumber | BV048203262 |
| classification_rvk | ST 640 |
| ctrlnum | (OCoLC)1334032067 (DE-599)BVBBV048203262 |
| discipline | Informatik |
| discipline_str_mv | Informatik |
| edition | Boris Galitsky, Saveli Goldberg |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>03716nam a2200409 c 4500</leader><controlfield tag="001">BV048203262</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20230306 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">220506s2022 a||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9780128245217</subfield><subfield code="c">pbk</subfield><subfield code="9">978-0-12-824521-7</subfield></datafield><datafield tag="024" ind1="3" ind2=" "><subfield code="a">9780128245217</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1334032067</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV048203262</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-29T</subfield><subfield code="a">DE-739</subfield><subfield code="a">DE-1043</subfield><subfield code="a">DE-898</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 640</subfield><subfield code="0">(DE-625)143686:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Galitsky, Boris</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)122085025X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Artificial Intelligence for healthcare applications and management</subfield></datafield><datafield tag="250" ind1=" " ind2=" "><subfield code="a">Boris Galitsky, Saveli Goldberg</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">London, United Kingdom</subfield><subfield code="b">Academic Press, Elsevier</subfield><subfield code="c">[2022]</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xv, 532 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Artificial Intelligence for Healthcare Applications and Management introduces application domains of various AI algorithms across healthcare management. Instead of discussing AI first and then exploring its applications in healthcare afterward, the authors attack the problems in context directly, in order to accelerate the path of an interested reader toward building industrial-strength healthcare applications. Readers will be introduced to a wide spectrum of AI applications supporting all stages of patient flow in a healthcare facility. The authors explain how AI supports patients throughout a healthcare facility, including diagnosis and treatment recommendations needed to get patients from the point of admission to the point of discharge while maintaining quality, patient safety, and patient/provider satisfaction.AI methods are expected to decrease the burden on physicians, improve the quality of patient care, and decrease overall treatment costs. </subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Current conditions affected by COVID-19 pose new challenges for healthcare management and learning how to apply AI will be important for a broad spectrum of students and mature professionals working in medical informatics. </subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This book focuses on predictive analytics, health text processing, data aggregation, management of patients, and other fields which have all turned out to be bottlenecks for the efficient management of coronavirus patients.- Presents an in-depth exploration of how AI algorithms embedded in scheduling, prediction, automated support, personalization, and diagnostics can improve the efficiency of patient treatment- Investigates explainable AI, including explainable decision support and machine learning, from limited data to back-up clinical decisions, and data analysis- Offers hands-on skills to computer science and medical informatics students to aid them in designing intelligent systems for healthcare- Informs a broad, multidisciplinary audience about a multitude of applications of machine learning and linguistics across various healthcare fields- Introduces medical discourse analysis for a high-level representation of health texts</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Medizin</subfield><subfield code="0">(DE-588)4038243-6</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Medizin</subfield><subfield code="0">(DE-588)4038243-6</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Goldberg, Saveli</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Passau - ADAM Catalogue Enrichment</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=033584217&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-033584217</subfield></datafield></record></collection> |
| id | DE-604.BV048203262 |
| illustrated | Illustrated |
| index_date | 2024-07-03T19:47:14Z |
| indexdate | 2024-07-10T09:31:54Z |
| institution | BVB |
| isbn | 9780128245217 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-033584217 |
| oclc_num | 1334032067 |
| open_access_boolean | |
| owner | DE-29T DE-739 DE-1043 DE-898 DE-BY-UBR |
| owner_facet | DE-29T DE-739 DE-1043 DE-898 DE-BY-UBR |
| physical | xv, 532 Seiten Illustrationen, Diagramme |
| publishDate | 2022 |
| publishDateSearch | 2022 |
| publishDateSort | 2022 |
| publisher | Academic Press, Elsevier |
| record_format | marc |
| spelling | Galitsky, Boris Verfasser (DE-588)122085025X aut Artificial Intelligence for healthcare applications and management Boris Galitsky, Saveli Goldberg London, United Kingdom Academic Press, Elsevier [2022] xv, 532 Seiten Illustrationen, Diagramme txt rdacontent n rdamedia nc rdacarrier Artificial Intelligence for Healthcare Applications and Management introduces application domains of various AI algorithms across healthcare management. Instead of discussing AI first and then exploring its applications in healthcare afterward, the authors attack the problems in context directly, in order to accelerate the path of an interested reader toward building industrial-strength healthcare applications. Readers will be introduced to a wide spectrum of AI applications supporting all stages of patient flow in a healthcare facility. The authors explain how AI supports patients throughout a healthcare facility, including diagnosis and treatment recommendations needed to get patients from the point of admission to the point of discharge while maintaining quality, patient safety, and patient/provider satisfaction.AI methods are expected to decrease the burden on physicians, improve the quality of patient care, and decrease overall treatment costs. Current conditions affected by COVID-19 pose new challenges for healthcare management and learning how to apply AI will be important for a broad spectrum of students and mature professionals working in medical informatics. This book focuses on predictive analytics, health text processing, data aggregation, management of patients, and other fields which have all turned out to be bottlenecks for the efficient management of coronavirus patients.- Presents an in-depth exploration of how AI algorithms embedded in scheduling, prediction, automated support, personalization, and diagnostics can improve the efficiency of patient treatment- Investigates explainable AI, including explainable decision support and machine learning, from limited data to back-up clinical decisions, and data analysis- Offers hands-on skills to computer science and medical informatics students to aid them in designing intelligent systems for healthcare- Informs a broad, multidisciplinary audience about a multitude of applications of machine learning and linguistics across various healthcare fields- Introduces medical discourse analysis for a high-level representation of health texts Künstliche Intelligenz (DE-588)4033447-8 gnd rswk-swf Medizin (DE-588)4038243-6 gnd rswk-swf Medizin (DE-588)4038243-6 s Künstliche Intelligenz (DE-588)4033447-8 s DE-604 Goldberg, Saveli Verfasser aut Digitalisierung UB Passau - ADAM Catalogue Enrichment application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=033584217&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Galitsky, Boris Goldberg, Saveli Artificial Intelligence for healthcare applications and management Künstliche Intelligenz (DE-588)4033447-8 gnd Medizin (DE-588)4038243-6 gnd |
| subject_GND | (DE-588)4033447-8 (DE-588)4038243-6 |
| title | Artificial Intelligence for healthcare applications and management |
| title_auth | Artificial Intelligence for healthcare applications and management |
| title_exact_search | Artificial Intelligence for healthcare applications and management |
| title_exact_search_txtP | Artificial Intelligence for healthcare applications and management |
| title_full | Artificial Intelligence for healthcare applications and management |
| title_fullStr | Artificial Intelligence for healthcare applications and management |
| title_full_unstemmed | Artificial Intelligence for healthcare applications and management |
| title_short | Artificial Intelligence for healthcare applications and management |
| title_sort | artificial intelligence for healthcare applications and management |
| topic | Künstliche Intelligenz (DE-588)4033447-8 gnd Medizin (DE-588)4038243-6 gnd |
| topic_facet | Künstliche Intelligenz Medizin |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=033584217&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT galitskyboris artificialintelligenceforhealthcareapplicationsandmanagement AT goldbergsaveli artificialintelligenceforhealthcareapplicationsandmanagement |