BackgroundElectronic health records (EHRs) bring many opportunities for information utilization. One such use is the surveillance conducted by the Centers for Disease Control and Prevention to track cases of autism spectrum disorder (ASD). This process currently comprises manual collection and review of EHRs of 4- and 8-year old children in 11 US states for the presence of ASD criteria. The work is time-consuming and expensive.ObjectiveOur objective was to automatically extract from EHRs the description of behaviors noted by the clinicians in evidence of the diagnostic criteria in the Diagnostic and Statistical Manual of Mental Disorders (DSM). Previously, we reported on the classification of entire EHRs as ASD or not. In this work, we focus on the extraction of individual expressions of the different ASD criteria in the text. We intend to facilitate large-scale surveillance efforts for ASD and support analysis of changes over time as well as enable integration with other relevant data.MethodsWe developed a natural language processing (NLP) parser to extract expressions of 12 DSM criteria using 104 patterns and 92 lexicons (1787 terms). The parser is rule-based to enable precise extraction of the entities from the text. The entities themselves are encompassed in the EHRs as very diverse expressions of the diagnostic criteria written by different people at different times (clinicians, speech pathologists, among others). Due to the sparsity of the data, a rule-based approach is best suited until larger datasets can be generated for machine learning algorithms.ResultsWe evaluated our rule-based parser and compared it with a machine learning baseline (decision tree). Using a test set of 6636 sentences (50 EHRs), we found that our parser achieved 76% precision, 43% recall (ie, sensitivity), and >99% specificity for criterion extraction. The performance was better for the rule-based approach than for the machine learning baseline (60% precision and 30% recall). For some individual criteria, precision was as high as 97% and recall 57%. Since precision was very high, we were assured that criteria were rarely assigned incorrectly, and our numbers presented a lower bound of their presence in EHRs. We then conducted a case study and parsed 4480 new EHRs covering 10 years of surveillance records from the Arizona Developmental Disabilities Surveillance Program. The social criteria (A1 criteria) showed the biggest change over the years. The communication criteria (A2 criteria) did not distinguish the ASD from the non-ASD records. Among behaviors and interests criteria (A3 criteria), 1 (A3b) was present with much greater frequency in the ASD than in the non-ASD EHRs.ConclusionsOur results demonstrate that NLP can support large-scale analysis useful for ASD surveillance and research. In the future, we intend to facilitate detailed analysis and integration of national datasets.

BackgroundWhile health literacy is important for people to maintain good health and manage diseases, medical educational texts are often written beyond the reading level of the average individual. To mitigate this disconnect, text simplification research provides methods to increase readability and, therefore, comprehension. One method of text simplification is to isolate particularly difficult terms within a document and replace them with easier synonyms (lexical simplification) or an explanation in plain language (semantic simplification). Unfortunately, existing dictionaries are seldom complete, and consequently, resources for many difficult terms are unavailable. This is the case for English and Spanish resources.ObjectiveOur objective was to automatically generate explanations for difficult terms in both English and Spanish when they are not covered by existing resources. The system we present combines existing resources for explanation generation using a novel algorithm (SubSimplify) to create additional explanations.MethodsSubSimplify uses word-level parsing techniques and specialized medical affix dictionaries to identify the morphological units of a term and then source their definitions. While the underlying resources are different, SubSimplify applies the same principles in both languages. To evaluate our approach, we used term familiarity to identify difficult terms in English and Spanish and then generated explanations for them. For each language, we extracted 400 difficult terms from two different article types (General and Medical topics) balanced for frequency. For English terms, we compared SubSimplify’s explanation with the explanations from the Consumer Health Vocabulary, WordNet Synonyms and Summaries, as well as Word Embedding Vector (WEV) synonyms. For Spanish terms, we compared the explanation to WordNet Summaries and WEV Embedding synonyms. We evaluated quality, coverage, and usefulness for the simplification provided for each term. Quality is the average score from two subject experts on a 1-4 Likert scale (two per language) for the synonyms or explanations provided by the source. Coverage is the number of terms for which a source could provide an explanation. Usefulness is the same expert score, however, with a 0 assigned when no explanations or synonyms were available for a term.ResultsSubSimplify resulted in quality scores of 1.64 for English (P<.001) and 1.49 for Spanish (P<.001), which were lower than those of existing resources (Consumer Health Vocabulary [CHV]=2.81). However, in coverage, SubSimplify outperforms all existing written resources, increasing the coverage from 53.0% to 80.5% in English and from 20.8% to 90.8% in Spanish (P<.001). This result means that the usefulness score of SubSimplify (1.32; P<.001) is greater than that of most existing resources (eg, CHV=0.169).ConclusionsOur approach is intended as an additional resource to existing, manually created resources. It greatly increases the number of difficult terms for which an easier alternative can be made available,...

No abstract

Deep learning delivers good performance in classification tasks, but is suboptimal with small and unbalanced datasets, which are common in many domains. To address this limitation, we use conventional machine learning, i.e., support vector machines (SVM) to tune deep learning hyperparameters. We evaluated our approach using mental health electronic health records in which diagnostic criteria needed to be extracted. A bidirectional Long Short-Term Memory network (BI-LSTM) could not learn the labels for the seven scarcest classes, but saw an increase in performance after training with optimal weights learned from tuning SVMs. With these customized class weights, the F1 scores for rare classes rose from 0 to values ranging from 18% to 57%. Overall, the BI-LSTM with SVM-customized class weights achieved a micro-average of 47.1% for F1 across all classes, an improvement over the regular BI-LSTM's 45.9%. The main contribution lies in avoiding null performance for rare classes.

No abstract