Maintaining automated measurement of Choosing Wisely adherence across the ICD 9 to 10 transition.

BACKGROUND: It remains unclear how to incorporate terminology changes, such as the International Classification of Disease (ICD) transition from ICD-9 to ICD-10, into established automated healthcare quality metrics. OBJECTIVE: To evaluate whether general equivalence mapping (GEM) can apply ICD-9 based metrics to ICD-10 patient data. To develop and validate novel ICD-10 reference codesets. DESIGN: Retrospective analysis for eleven Choosing Wisely (CW) metrics was performed using three scripted algorithms on an institutional clinical data warehouse. ICD-10 data were compared against published ICD-9 based metric definitions using two equivalence mapping algorithms. A third algorithm implemented novel reference ICD-10 codes matching the original ICD-9 codes' intent for comparison with patient ICD-10 data. PARTICIPANTS: All adult patients seen at Vanderbilt University Medical Center, April - September 2016. MAIN MEASURES: The prevalence of eleven CW services during the six-month period. KEY RESULTS: The three algorithms found similar prevalence of avoidable CW services, with an unweighted-mean of 8.4% (range: 0.16-65%), or approximately 20,000 CW services out of 240,000 potential cases in 515,406 unique patients. The algorithms' median sensitivity was 0.80 (interquartile range: 0.75-0.95), median specificity was 0.88 (IQR: 0.77-0.94), and median Rand accuracy was 0.84 (IQR: 0.79-0.89). The attributed waste of these eleven services for the period ranged from $871,049 to $951,829 between methods. Accuracy assessment demonstrated that the GEM-based methods suffered recall losses for metrics requiring multistep mapping due to incompleteness, while novel ICD-10 metric definitions avoided these challenges. CONCLUSIONS: Comprehensive mapping enables use of legacy metrics across ICD generations, but requires computational complexity that can be avoided with novel ICD-10 based metric definitions. Variation in the dollars attributed to waste due to ICD mapping introduces ambiguity that may affect quality-based reimbursement.

Mining 100 million notes to find homelessness and adverse childhood experiences: 2 case studies of rare and severe social determinants of health in electronic health records.

Objective: Understanding how to identify the social determinants of health from electronic health records (EHRs) could provide important insights to understand health or disease outcomes. We developed a methodology to capture 2 rare and severe social determinants of health, homelessness and adverse childhood experiences (ACEs), from a large EHR repository. Materials and Methods: We first constructed lexicons to capture homelessness and ACE phenotypic profiles. We employed word2vec and lexical associations to mine homelessness-related words. Next, using relevance feedback, we refined the 2 profiles with iterative searches over 100 million notes from the Vanderbilt EHR. Seven assessors manually reviewed the top-ranked results of 2544 patient visits relevant for homelessness and 1000 patients relevant for ACE. Results: word2vec yielded better performance (area under the precision-recall curve [AUPRC] of 0.94) than lexical associations (AUPRC = 0.83) for extracting homelessness-related words. A comparative study of searches for the 2 phenotypes revealed a higher performance achieved for homelessness (AUPRC = 0.95) than ACE (AUPRC = 0.79). A temporal analysis of the homeless population showed that the majority experienced chronic homelessness. Most ACE patients suffered sexual (70%) and/or physical (50.6%) abuse, with the top-ranked abuser keywords being "father" (21.8%) and "mother" (15.4%). Top prevalent associated conditions for homeless patients were lack of housing (62.8%) and tobacco use disorder (61.5%), while for ACE patients it was mental disorders (36.6%-47.6%). Conclusion: We provide an efficient solution for mining homelessness and ACE information from EHRs, which can facilitate large clinical and genetic studies of these social determinants of health.

Learning probabilistic phenotypes from heterogeneous EHR data.

We present the Unsupervised Phenome Model (UPhenome), a probabilistic graphical model for large-scale discovery of computational models of disease, or phenotypes. We tackle this challenge through the joint modeling of a large set of diseases and a large set of clinical observations. The observations are drawn directly from heterogeneous patient record data (notes, laboratory tests, medications, and diagnosis codes), and the diseases are modeled in an unsupervised fashion. We apply UPhenome to two qualitatively different mixtures of patients and diseases: records of extremely sick patients in the intensive care unit with constant monitoring, and records of outpatients regularly followed by care providers over multiple years. We demonstrate that the UPhenome model can learn from these different care settings, without any additional adaptation. Our experiments show that (i) the learned phenotypes combine the heterogeneous data types more coherently than baseline LDA-based phenotypes; (ii) they each represent single diseases rather than a mix of diseases more often than the baseline ones; and (iii) when applied to unseen patient records, they are correlated with the patients' ground-truth disorders. Code for training, inference, and quantitative evaluation is made available to the research community.