Basic Science in Medical Reasoning: An Artificial Intelligence Approach

A new generation of intelligent systems is growing up in the community of Artificial Intelligence in Medicine. The main goal of these systems is the representation and use of real theory of diseases, as they are represented in medical textbooks or in scientific articles, rather than the heuristic shortcuts of human experts. In this paper, we will argue that the difficulties in the integration of basic science and clinical knowledge in intelligent systems arise from ontological differences between these kinds of knowledge and that the solution can be found in their dynamic integration during the reasoning process. In order to illustrate this point, we will first describe an epistemological analysis of the interplay between basic science knowledge and clinical knowledge, and then we will provide the example of a computational architecture implementing this view. This revised version was published online in June 2006 with corrections to the Cover Date.     

Sentiments analysis at conceptual level making use of the Narrative Knowledge Representation Language

This paper illustrates some of the knowledge representation structures and inference procedures proper to a high-level, fully implemented conceptual language, NKRL (Narrative Knowledge Representation Language). The aim is to show how these tools can be used to deal, in a sentiment analysis/opinion mining context, with some common types of human (and non-human) “behaviors”. These behaviors correspond, in particular, to the concrete, mutual relationships among human and non-human characters that can be expressed under the form of non-fictional and real-time “narratives” (i.e., as logically and temporally structured sequences of “elementary events”).     

Executing medical logic modules expressed in ArdenML using Drools

The Arden Syntax is an HL7 standard language for representing medical knowledge as logic statements. Despite nearly 2 decades of availability, Arden Syntax has not been widely used. This has been attributed to the lack of a generally available compiler to implement the logic, to Arden's complex syntax, to the challenges of mapping local data to data references in the Medical Logic Modules (MLMs), or, more globally, to the general absence of decision support in healthcare computing. An XML representation (ArdenML) may partially address the technical challenges. MLMs created in ArdenML can be converted into executable files using standard transforms written in the Extensible Stylesheet Language Transformation (XSLT) language. As an example, we have demonstrated an approach to executing MLMs written in ArdenML using the Drools business rule management system. Extensions to ArdenML make it possible to generate a user interface through which an MLM developer can test for logical errors.     

Clinical decision support with automated text processing for cervical cancer screening

Objective

To develop a computerized clinical decision support system (CDSS) for cervical cancer screening that can interpret free-text Papanicolaou (Pap) reports.

Materials and Methods

The CDSS was constituted by two rulebases: the free-text rulebase for interpreting Pap reports and a guideline rulebase. The free-text rulebase was developed by analyzing a corpus of 49 293 Pap reports. The guideline rulebase was constructed using national cervical cancer screening guidelines. The CDSS accesses the electronic medical record (EMR) system to generate patient-specific recommendations. For evaluation, the screening recommendations made by the CDSS for 74 patients were reviewed by a physician.

Results and Discussion

Evaluation revealed that the CDSS outputs the optimal screening recommendations for 73 out of 74 test patients and it identified two cases for gynecology referral that were missed by the physician. The CDSS aided the physician to amend recommendations in six cases. The failure case was because human papillomavirus (HPV) testing was sometimes performed separately from the Pap test and these results were reported by a laboratory system that was not queried by the CDSS. Subsequently, the CDSS was upgraded to look up the HPV results missed earlier and it generated the optimal recommendations for all 74 test cases.

Limitations

Single institution and single expert study.

Conclusion

An accurate CDSS system could be constructed for cervical cancer screening given the standardized reporting of Pap tests and the availability of explicit guidelines. Overall, the study demonstrates that free text in the EMR can be effectively utilized through natural language processing to develop clinical decision support tools.     

A knowledge discovery and reuse pipeline for information extraction in clinical notes

Objective

Information extraction and classification of clinical data are current challenges in natural language processing. This paper presents a cascaded method to deal with three different extractions and classifications in clinical data: concept annotation, assertion classification and relation classification.

Materials and Methods

A pipeline system was developed for clinical natural language processing that includes a proofreading process, with gold-standard reflexive validation and correction. The information extraction system is a combination of a machine learning approach and a rule-based approach. The outputs of this system are used for evaluation in all three tiers of the fourth i2b2/VA shared-task and workshop challenge.

Results

Overall concept classification attained an F-score of 83.3% against a baseline of 77.0%, the optimal F-score for assertions about the concepts was 92.4% and relation classifier attained 72.6% for relationships between clinical concepts against a baseline of 71.0%. Micro-average results for the challenge test set were 81.79%, 91.90% and 70.18%, respectively.

Discussion

The challenge in the multi-task test requires a distribution of time and work load for each individual task so that the overall performance evaluation on all three tasks would be more informative rather than treating each task assessment as independent. The simplicity of the model developed in this work should be contrasted with the very large feature space of other participants in the challenge who only achieved slightly better performance. There is a need to charge a penalty against the complexity of a model as defined in message minimalisation theory when comparing results.

Conclusion

A complete pipeline system for constructing language processing models that can be used to process multiple practical detection tasks of language structures of clinical records is presented.     

Getting the foot out of the pelvis: modeling problems affecting use of SNOMED CT hierarchies in practical applications

Objectives

(a) To determine the extent and range of errors and issues in the Systematised Nomenclature of Medicine – Clinical Terms (SNOMED CT) hierarchies as they affect two practical projects. (b) To determine the origin of issues raised and propose methods to address them.

Methods

The hierarchies for concepts in the Core Problem List Subset published by the Unified Medical Language System were examined for their appropriateness in two applications. Anomalies were traced to their source to determine whether they were simple local errors, systematic inferences propagated by SNOMED''s classification process, or the result of problems with SNOMED''s schemas. Conclusions were confirmed by showing that altering the root cause and reclassifying had the intended effects, and not others.

Main results

Major problems were encountered, involving concepts central to medicine including myocardial infarction, diabetes, and hypertension. Most of the issues raised were systematic. Some exposed fundamental errors in SNOMED''s schemas, particularly with regards to anatomy. In many cases, the root cause could only be identified and corrected with the aid of a classifier.

Limitations

This is a preliminary ‘experiment of opportunity.’ The results are not exhaustive; nor is consensus on all points definitive.

Conclusions

The SNOMED CT hierarchies cannot be relied upon in their present state in our applications. However, systematic quality assurance and correction are possible and practical but require sound techniques analogous to software engineering and combined lexical and semantic techniques. Until this is done, anyone using SNOMED codes should exercise caution. Errors in the hierarchies, or attempts to compensate for them, are likely to compromise interoperability and meaningful use.     

Evaluating semantic similarity between Chinese biomedical terms through multiple ontologies with score normalization: An initial study

BackgroundSemantic similarity estimation significantly promotes the understanding of natural language resources and supports medical decision making. Previous studies have investigated semantic similarity and relatedness estimation between biomedical terms through resources in English, such as SNOMED-CT or UMLS. However, very limited studies focused on the Chinese language, and technology on natural language processing and text mining of medical documents in China is urgently needed. Due to the lack of a complete and publicly available biomedical ontology in China, we only have access to several modest-sized ontologies with no overlaps. Although all these ontologies do not constitute a complete coverage of biomedicine, their coverage of their respective domains is acceptable. In this paper, semantic similarity estimations between Chinese biomedical terms using these multiple non-overlapping ontologies were explored as an initial study.MethodsTypical path-based and information content (IC)-based similarity measures were applied on these ontologies. From the analysis of the computed similarity scores, heterogeneity in the statistical distributions of scores derived from multiple ontologies was discovered. This heterogeneity hampers the comparability of scores and the overall accuracy of similarity estimation. This problem was addressed through a novel language-independent method by combining semantic similarity estimation and score normalization. A reference standard was also created in this study.ResultsCompared with the existing task-independent normalization methods, the newly developed method exhibited superior performance on most IC-based similarity measures. The accuracy of semantic similarity estimation was enhanced through score normalization. This enhancement resulted from the mitigation of heterogeneity in the similarity scores derived from multiple ontologies.ConclusionWe demonstrated the potential necessity of score normalization when estimating semantic similarity using ontology-based measures. The results of this study can also be extended to other language systems to implement semantic similarity estimation in biomedicine.