5 June 2023 in npj Digital Medicine
Machine learning (ML) models trained for triggering clinical decision support (CDS) are typically either accurate or interpretable but not both. Scaling CDS to the panoply of clinical use cases while mitigating risks to patients will require many ML models be intuitively interpretable for clinicians. To this end, we adapted a symbolic regression method, coined the feature engineering automation tool (FEAT), to train concise and accurate models from high-dimensional electronic health record (EHR) data. We first present an in-depth application of FEAT to classify hypertension, hypertension with unexplained hypokalemia, and apparent treatment-resistant hypertension (aTRH) using EHR data for 1200 subjects receiving longitudinal care in a large healthcare system. FEAT models trained to predict phenotypes adjudicated by chart review had equivalent or higher discriminative performance (p < 0.001) and were at least three times smaller (p < 1 × 10−6) than other potentially interpretable models. For aTRH, FEAT generated a six-feature, highly discriminative (positive predictive value = 0.70, sensitivity = 0.62), and clinically intuitive model. To assess the generalizability of the approach, we tested FEAT on 25 benchmark clinical phenotyping tasks using the MIMIC-III critical care database. Under comparable dimensionality constraints, FEAT’s models exhibited higher area under the receiver-operating curve scores than penalized linear models across tasks (p < 6 × 10−6). In summary, FEAT can train EHR prediction models that are both intuitively interpretable and accurate, which should facilitate safe and effective scaling of ML-triggered CDS to the panoply of potential clinical use cases and healthcare practices.
22 March 2022 in Journal of Bone and Mineral Research
Enchondromas and chondrosarcomas are common cartilage neoplasms that are either benign or malignant, respectively. The majority of these tumors harbor mutations in either IDH1 or IDH2. Glutamine metabolism has been implicated as a critical regulator of tumors with IDH mutations. Using genetic and pharmacological approaches, we demonstrated that glutaminase-mediated glutamine metabolism played distinct roles in enchondromas and chondrosarcomas with IDH1 or IDH2 mutations. Glutamine affected cell differentiation and viability in these tumors differently through different downstream metabolites. During murine enchondroma-like lesion development, glutamine-derived α-ketoglutarate promoted hypertrophic chondrocyte differentiation and regulated chondrocyte proliferation. Deletion of glutaminase in chondrocytes with Idh1 mutation increased the number and size of enchondroma-like lesions. In contrast, pharmacological inhibition of glutaminase in chondrosarcoma xenografts reduced overall tumor burden partially because glutamine-derived non-essential amino acids played an important role in preventing cell apoptosis. This study demonstrates that glutamine metabolism plays different roles in tumor initiation and cancer maintenance. Supplementation of α-ketoglutarate and inhibiting GLS may provide a therapeutic approach to suppress enchondroma and chondrosarcoma tumor growth, respectively. © 2022 The Authors. Journal of Bone and Mineral Research published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research (ASBMR).
8 June 2025 in Journal of Biomedical Informatics