Background: Clinicians and researchers may rely on medical coding systems such as International Classification of Diseases (ICD) to identify patients with specific diseases from Electronic Health Records (EHRs). However, due to the lack of detail and specificity as well as a probability of miscoding, recent studies suggest the ICD codes often cannot characterise patients accurately for specific diseases in real clinical practice, and as a result, using them to find patients for studies or trials can result in high failure rates and missing out on uncoded patients. Manual inspection of all patients at scale is not feasible as it is highly costly and slow. Methodology: This paper proposes a scalable workflow which leverages both structured data and unstructured textual notes from EHRs with techniques including Natural Language Processing (for phenotyping), AutoML and Clinician-in-the-Loop mechanism to build machine learning classifiers to identify patients at scale with given diseases, especially those who might currently be miscoded or missed by ICD codes. Results: Case studies in the MIMIC-III dataset were conducted where the proposed workflow demonstrates a higher classification performance in terms of F1 scores compared to simply using ICD codes on gold testing subset to identify patients with Ovarian Cancer (0.901 vs 0.814), Lung Cancer (0.859 vs 0.828), Cancer Cachexia (0.862 vs 0.650), and Lupus Nephritis (0.959 vs 0.855). Also, the proposed workflow that leverages unstructured notes consistently outperforms the baseline that uses structured data only with an increase of F1 (Ovarian Cancer 0.901 vs 0.719, Lung Cancer 0.859 vs 0.787, Cancer Cachexia 0.862 vs 0.838 and Lupus Nephritis 0.959 vs 0.785). Experiments on the large testing set also demonstrate the proposed workflow can find more patients who are miscoded or missed by ICD codes. Moreover, interpretability studies are also conducted to clinically validate the top impact features behind the decision-making of the classifiers.
Conclusions:The proposed workflow can more accurately identify patients with specific diseases than simply using ICD codes. We also find the phenotypic features extracted from unstructured textual notes are beneficial for better accuracy and interpretability of classifiers. Moreover, the proposed workflow is scalable to other diseases and use cases as Clinician-in-the-Loop and AutoML enable rapid configuration of new machine learning classifiers.