Temporal Reasoning and Planning in Medicine Knowledge-Based Abstraction

Temporal Reasoning and Planning in Medicine Knowledge-Based Abstraction of Time-Oriented Clinical Data Yuval Shahar, M. D. , Ph. D

The Temporal-Abstraction Task • Input: time-stamped data and relevant events • Output: interval-based abstractions • Identifies past and present trends and states • Supports decisions based on temporal patterns “modify therapy if the patient has a second episode of Grade II bone-marrow toxicity lasting more than 3 weeks” • Focuses on interpretation, rather than on forecasting

Temporal Abstraction: The Bone-Marrow Transplantation Domain

Uses of Temporal Abstractions • Planning therapy and monitoring patients over time • Creating high-level summaries of time-oriented patient records • Supporting an explanation module for medical DSSs • Representing goals and policies of therapy plans and guidelines • Visualization and exploration of time-oriented medical data

Generation of Abstractions: The Knowledge-Based Temporal-Abstraction Method • Knowledge-based temporal abstraction (KBTA): A computational framework for interpretation of time-oriented data • Decomposes the TA task into five TA sub-tasks, each solved using one of five TA computational mechanisms, all mechanisms operating in parallel • Includes an explicit temporal-abstraction (TA) ontology (events, parameters, patterns, abstraction goals, contexts) and four TA knowledge types (structural, functional, logical, probabilistic) • Underlies tools for semi-automated acquisition of temporalabstraction knowledge from domain experts

Knowledge-Based Temporal Abstraction

The Temporal-Abstraction Ontology (Shahar, AIJ, 1997) • Events (interventions) (e. g. , insulin therapy; bombardment) - part-of, is-a relations • Parameters (measured raw data and derived [abstract] concepts) (e. g. , hemoglobin values; anemia levels; number of open sockets) - abstracted-into, is-a relations • Patterns (e. g. , crescendo angina; paradoxical hyperglycemia) - component-of, is-a relations • Abstraction goals (user views)(e. g. , diabetes therapy; terror threats) - is-a relations • Interpretation contexts (effect of regular insulin; political tension) - subcontext, is-a relations • Interpretation contexts are induced by all other entities

Temporal-Abstraction Output Types • • State abstractions (LOW, HIGH) Gradient abstractions (INC, DEC) Rate Abstractions (SLOW, FAST) Pattern Abstractions (CRESCENDO) - Linear patterns - Periodic patterns - Fuzzy patterns (partial match)

Temporal-Abstraction Knowledge Types • Structural (e. g. , part-of, is-a relations) - mainly declarative/relational • Classification (e. g. , value ranges; patterns) - mainly functional • Temporal-semantic (e. g. , “concatenable” property) - mainly logical • Temporal-dynamic (e. g. , interpolation functions) - mainly probabilistic

Dynamic Induction of Contexts: Temporal Constraints Between Inducing Proposition and Induced Context (Shahar, AMAI 1998) ee ss es se

Induction of Interpretation Contexts

The Meaning of Interpretation Contexts • Context intervals serve as a frame of reference for interpretation: Abstractions are meaningful only in a context (e. g. , “Significant communication activity in the context of no mouse commands” ) • Context intervals focus and limit the computations to only those relevant to a particular context (thus, knowledge is brought to bear only when relevant) • Contexts enable the use of context-specific knowledge, thus increasing accuracy of resultant abstractions

Advantages of Explicit Contexts • Any temporal relation (e. g. , overlaps) can hold between a context and its inducing proposition; contexts can be induced before and after the inducing proposition (thus enabling a certain type of hindsight and foresight) + Claim: Forming contexts is a finite process • The same context-forming proposition can induce multiple context intervals • The same interpretation context might be induced by different propositions • Explicit contexts support maintenance of several concurrent views (or interpretations) of the data, in which the same parameter has different values at the same time, each within a different context + Note: There is no contradiction-values are in different contexts

Local and Global Persistence Functions: Exponential-Decay Local Belief Functions (Shahar, JETAI 1999) t j 1 j 2 I 1 Bel(j) I 2 1 e –λ 1 t e –λ 2 t jth 0 Time

Local and Global Persistence Functions and their Typology • • Local (ρ) persistence functions represent the local persistence of the truth of a parameter proposition (a decay of the degree of belief forwards to the future, or backwards to the past), given a single parameter point or interval Global (D) maximal-gap persistence functions return the maximal time gap that still allows us to join two propositions into an abstraction that is believed to be true, with a sufficient, task-specific, predefined degree of belief in the proposition, during the gap (a function of the parameter, its value, context, and the two interval durations) – – • • An extension of local persistence functions that often can be constructed from them Usually easier to acquire from domain experts since they can be linear functions of the durations Global persistence functions can have four qualitative types: PP, NN, PN, and NP, depending on whether the function is either (1) positive monotonic or (2) negative monotonic, with respect to (a) the length of the first parameter interval L(I 1) or (b) the length of the second parameter interval L(I 2) Claim 1: PP functions are associative (the order of joining intervals and points cannot change the resulting set of abstractions) Claim 2: NN functions are not associative Can PN and NP functions exist?

Irregular-Time Markov Models (Ramati & Shahar, UAI 2010) • Discrete-time Markov models do not handle time irregularity very well: Kalman Filters, Hidden Markov Models, and Dynamic Bayesian Networks in general require the specification of a constant time difference between each two consecutive observations – leads to inefficient computation or to information loss, and limits the inference to multiples of the modeled time granularity • Markov models that represent time continuously handle well time irregularity, but suffer from other limitations – they assume either a discrete state space (as Continuous-Time Bayesian Networks), or a at continuous state space (as stochastic differential equations) • Irregular-Time Bayesian Networks (ITBNs) generalize Dynamic Bayesian Networks such that each time slice may span over a time interval rather than a single time point, and the time difference between consecutive slices may vary according to the available data and inference needs – Leading to increased computational efficiency and increased expressivity

A Constraint-Based Specification of Linear and Periodic Patterns (Chakravarty & Shahar, AMAI, 2000; MIM, 2001) Periodic Pattern: Periodic Constraints Linear Patterns: <start> <duration> <end> Global Constraints Abstractions: Local Constraints <before> Raw Data: Time

Linear and Periodic Clinical Patterns Periodic Pattern Linear Component Fever Anemia Week 1 = Temperature Linear Component Fever Anemia Week 2 = Hemoglobin Level Linear Component Fever Anemia Week 3

An Overall View of the Temporal Abstraction Task The temporal-abstraction task can be defined as follows: Given at least one abstraction-goal interval, a set of event intervals , a set of parameter intervals, and the domain’s temporal-abstraction ontology, produce an interpretation - that is, a set of context intervals and a set of (new) abstractions such that the interpretation can answer any temporal query about all of the abstractions derivable from the transitive closure of the input data and the domain knowledge. This is, in fact, a knowledge-based data-integration task.

Application Domains for the KBTA Method [Shahar & Musen, Comp Biomed Res 1993, AI in Med 1996; Kuilboer et al. , SCAMC 1993; Shahar & Molina, Boaz & Shahar, AI in Med 2005; Shabtai et al. , J. Computer Virology, 2009; JIIS, 2012] Patt Anal & App 1999; • Medical domains: – Guideline-based care • AIDS therapy • Oncology [Shahar & Musen, CBR 1993, AIM 1996] – Monitoring of children’s growth [Kuilboer et al. , SCAMC 1993] – Therapy of insulin-dependent diabetes [Shahar and Musen, AIM 1996] • Non-medical domains: – – Evaluation of traffic-controllers actions [Shahar & Molina, PAA 1999] summarization of meteorological data Integration of intelligence data over time Monitoring electronic security threats in computers and communication networks [Shabtai et al. , JCV 2009; JIIS, 2012]

The RÉSUMÉ System Architecture

Monitoring of Children’s growth: The Parameter Ontology

Monitoring of Children’s growth: Temporal Abstraction of the Height Standard Deviation Score (HTSDS)

The Diabetes Parameter Ontology = PROPERTY-OF relation; = IS-A relation; = ABSTRACTED_INTO relation

The Diabetes Event Ontology = PART-OF relation; = IS-A relation

The Diabetes Context Ontology = SUB-CONTEXT relation; = IS-A relation

Forming Contexts in Diabetes

Temporal Abstractions in Diabetes (I) | D M _planning_event DM H Blood glucose values H | St a t e ( s t a t e ( p r e s u p p e r - g lu c o s e ) ) 20 0 100 H • | | • • 7 /23 H ² | 7/22 H 7 /24 7 /25 7/26 T im e (date in 1 9 9 0 ) = pre-breakfast glucose; • = pre-lunch glucose; = pre-supper glucose

Temporal Abstractions in Diabetes (II) D M _ p lan n in g _ ev en t | . DM Blood glucose values NLH NNH St a t e ( s t a t e ( p r e p r a n d i a l- g lu c o s e ) ) 200 100 • 7/22 7 /2 3 7 /2 4 T im e ( d a te in 1 9 9 0 ) 7 /2 5 7 /2 6 = pre-breakfast glucose; • = pre-lunch glucose; = pre-supper glucose

Acquisition of Temporal-Abstraction Knowledge Using the Protégé System

Evaluation of Automated Knowledge Entry Using the Protégé System • Formal evaluation performed, using 3 experts, 3 knowledge engineers, 3 clinical domains, a gold standard of data, knowledge and output abstractions • Domains: monitoring of children’s growth, care of diabetes patients, and protocol-based care in oncology and AIDS. • The study evaluated the usability of the KA tool solely for entry of previously elicited knowledge.

KA Tool Evaluation: Results • Understanding RÉSUMÉ required 6 to 20 hours (median: 15 to 20 hours); • Learning to use the KA tool required 2 to 6 hours (median: 3 to 4 hours). • Acquisition times for physicians varied by domain: 2 to 20 hours for growth monitoring (median: 3 hours), 6 and 12 hours for diabetes care, and 5 to 60 hours for protocol-based care (median: 10 hours). • A speedup of up to 25 times (median: 3 times) was demonstrated for all participants when the KA process was repeated. • On their first attempt at using the tool to enter the knowledge, the knowledge engineers recorded entry times similar to those of the expert physicians’ second attempt at entering the same knowledge. • In all cases, RÉSUMÉ, using knowledge entered via the KA tool, generated abstractions that were almost identical to those generated using the same knowledge, when entered manually.

The GESHER Knowledge Structuring and Maintenance Tool: Creating a Declarative Knowledge Map from Medical Concepts [Hatsek et al. , OMIJ 2010] A knowledge map Constraints on concept values Structured text description

Detection of Infections in the ICU: The Knowledge Centers for Disease Control (CDC) and Prevention. National Healthcare Safety Network. Guidelines and procedures for monitoring VAP. March 2009. http: //www. cdc. gov/nhsn/PDFs/psc. Manual/6 psc. VAPcurrent. pdf

The ICU Infection-Monitoring System Red: Has an infection Infection type Patient ID Blue: Additional data needed Green: Normal • Displays the infections’ status of all the patients in the department in real-time • Can be queried and can provide explanations for all alerts

Evaluation of the GESHER Module [Hatsek et al. , OMIJ 2010] • 3 knowledge engineers, 3 physicians, 3 combined teams of KE+MD • All received a short training course in the Knowledge Map tool • All created the declarative knowledge specification of the Pre-eclampsia-Toxemia (PET) guideline (20 concepts) • Correctness and Completeness measures computed in comparison to a predefined expert+KE gold standard knowledge map

Results of the GESHER Evaluation Group 1 vs. Group 2 Physicians vs. Engineers Completeness Physicians vs. Teams Engineers vs. Teams Group 1 performance 151/171 (88. 3%) 162/171 (94. 74%) Group 2 P value performance 162/171 (94. 74%) 0. 033 * 165/171 (96. 49%) 0. 004 * 165/171 (96. 49%) 0. 428 Group 1 performance P value Physicians vs. Engineers 603/663 (90. 95%) 620/663 (93. 51%) 0. 081 Physicians vs. Teams Correctness Group 2 performance 603/663 (90. 95%) 649/663 (97. 89%) <0. 001 * Engineers vs. Teams 620/663 (93. 51%) 649/663 (97. 89%) <0. 001* Training Time (minutes) * significant Knowledge Engineers Expert Physicians Teams Mean Specification Overall 100 140 93 111 188 313 193 231 288 453 287 342

Conclusions • Temporal abstraction is an important task in medical decisionsupport systems, which can be solved using a knowledge-based methodology • The knowledge-based temporal-abstraction method employs reusable domain-independent temporal-abstraction mechanisms • The temporal-abstraction mechanisms rely on access to a domainspecific temporal-abstraction ontology of parameters, events, patterns, context, and abstraction goals • Temporal-abstraction knowledge can be specified either by knowledge engineers or by medical experts (best is by multidisciplinary teams) and is usable, reusable, and sharable