Electronic Health Record Based Algorithm to Identify Patients with Autism Spectrum Disorder

• Published in: PloS one Vol. 11; no. 7; p. e0159621
• Main Authors: Lingren, Todd, Chen, Pei, Bochenek, Joseph, Doshi-Velez, Finale, Manning-Courtney, Patty, Bickel, Julie, Wildenger Welchons, Leah, Reinhold, Judy, Bing, Nicole, Ni, Yizhao, Barbaresi, William, Mentch, Frank, Basford, Melissa, Denny, Joshua, Vazquez, Lyam, Perry, Cassandra, Namjou, Bahram, Qiu, Haijun, Connolly, John, Abrams, Debra, Holm, Ingrid A., Cobb, Beth A., Lingren, Nataline, Solti, Imre, Hakonarson, Hakon, Kohane, Isaac S., Harley, John, Savova, Guergana
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 29.07.2016; Public Library of Science (PLoS)
• Subjects: Algorithms; Archives & records; Artificial intelligence; Autism; Autism Spectrum Disorder - diagnosis; Biology; Biology and Life Sciences; Bipolar disorder; Child; Child, Preschool; Children; Children & youth; Clustering; Cohort Studies; Comorbidity; Computer and Information Sciences; Consortia; Diagnosis; Diagnostic systems; Electronic Health Records; Electronic medical records; Electronic records; Female; Genomes; Genomics; Health care facilities; Health informatics; Hospitals; Humans; Male; Medical diagnosis; Medical records; Medical schools; Medicine; Medicine and Health Sciences; Mental disorders; Patients; Pediatrics; People and Places; Pervasive developmental disorders; Physical Sciences; Physicians; Research and Analysis Methods; Rule based; Seizures; Social Sciences; Subgroups; United States; Ohio; United States > US; Massachusetts; Tennessee; Nashville Tennessee; Pennsylvania
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0159621

Cohort selection is challenging for large-scale electronic health record (EHR) analyses, as International Classification of Diseases 9th edition (ICD-9) diagnostic codes are notoriously unreliable disease predictors. Our objective was to develop, evaluate, and validate an automated algorithm for determining an Autism Spectrum Disorder (ASD) patient cohort from EHR. We demonstrate its utility via the largest investigation to date of the co-occurrence patterns of medical comorbidities in ASD. We extracted ICD-9 codes and concepts derived from the clinical notes. A gold standard patient set was labeled by clinicians at Boston Children's Hospital (BCH) (N = 150) and Cincinnati Children's Hospital and Medical Center (CCHMC) (N = 152). Two algorithms were created: (1) rule-based implementing the ASD criteria from Diagnostic and Statistical Manual of Mental Diseases 4th edition, (2) predictive classifier. The positive predictive values (PPV) achieved by these algorithms were compared to an ICD-9 code baseline. We clustered the patients based on grouped ICD-9 codes and evaluated subgroups. The rule-based algorithm produced the best PPV: (a) BCH: 0.885 vs. 0.273 (baseline); (b) CCHMC: 0.840 vs. 0.645 (baseline); (c) combined: 0.864 vs. 0.460 (baseline). A validation at Children's Hospital of Philadelphia yielded 0.848 (PPV). Clustering analyses of comorbidities on the three-site large cohort (N = 20,658 ASD patients) identified psychiatric, developmental, and seizure disorder clusters. In a large cross-institutional cohort, co-occurrence patterns of comorbidities in ASDs provide further hypothetical evidence for distinct courses in ASD. The proposed automated algorithms for cohort selection open avenues for other large-scale EHR studies and individualized treatment of ASD.