Scalable Clinical Data Infrastructure and Comparative ML Evaluation for Hospitalisation Risk Prediction in Elderly Patients with Multiple Long-Term Conditions using CPRD

Asra Aslam, Volodymyr Chapman, Maurice M. O’Connell, Aseel S Abuzour, Micheal Abaho, Danushka Bollegala, Gary Leeming, Eduard Shantsila, Andrew Clegg, Lauren E Walker, Iain Edward Buchan, Samuel D Relton
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:141-167, 2026.

Abstract

Deep learning architectures are increasingly proposed for patient trajectory modeling in electronic health records (EHRs), yet their advantage over simpler, more interpretable models is rarely subjected to rigorous empirical scrutiny in real-world clinical settings. We present a comprehensive patient timeline pipeline applied to elderly patients in CPRD Aurum, incorporating 260 clinical conditions classified via a three-tier automated framework including specialised detection logic for 17 complex conditions. Using this infrastructure, we benchmark Temporal Graph Convolutional Neural Networks (TG-CNN) against Logistic Regression with LASSO regularisation and Random Forests for predicting 12-month all-cause emergency hospitalisation risk, motivated by (but not filtered to) the elevated risk of adverse drug reactions. Under cross-validation, TG-CNN achieves a marginally higher mean AUC-ROC than LASSO (0.712 vs. 0.705), whereas on the held-out test set LASSO achieves the highest discrimination of three models (AUC-ROC 0.733, versus 0.710 for Random Forest and 0.702 for TG-CNN). We show, that discrimination alone is an incomplete criterion for clinical deployment: after Platt calibration, LASSO is the only model with an acceptable calibration slope (0.817), while Random Forest (0.759) and, TG-CNN (0.391) remain substantially miscalibrated. We argue that LASSO, not the highest-discriminating model, is the model best suited to direct clinical deployment. We present lessons for the machine learning and healthcare community regarding data infrastructure, model selection, and value of calibration and interpretability in high-stakes decision support.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-aslam26a, title = {Scalable Clinical Data Infrastructure and Comparative ML Evaluation for Hospitalisation Risk Prediction in Elderly Patients with Multiple Long-Term Conditions using CPRD}, author = {Aslam, Asra and Chapman, Volodymyr and O'Connell, Maurice M. and Abuzour, Aseel S and Abaho, Micheal and Bollegala, Danushka and Leeming, Gary and Shantsila, Eduard and Clegg, Andrew and Walker, Lauren E and Buchan, Iain Edward and Relton, Samuel D}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {141--167}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/aslam26a/aslam26a.pdf}, url = {https://proceedings.mlr.press/v340/aslam26a.html}, abstract = {Deep learning architectures are increasingly proposed for patient trajectory modeling in electronic health records (EHRs), yet their advantage over simpler, more interpretable models is rarely subjected to rigorous empirical scrutiny in real-world clinical settings. We present a comprehensive patient timeline pipeline applied to elderly patients in CPRD Aurum, incorporating 260 clinical conditions classified via a three-tier automated framework including specialised detection logic for 17 complex conditions. Using this infrastructure, we benchmark Temporal Graph Convolutional Neural Networks (TG-CNN) against Logistic Regression with LASSO regularisation and Random Forests for predicting 12-month all-cause emergency hospitalisation risk, motivated by (but not filtered to) the elevated risk of adverse drug reactions. Under cross-validation, TG-CNN achieves a marginally higher mean AUC-ROC than LASSO (0.712 vs. 0.705), whereas on the held-out test set LASSO achieves the highest discrimination of three models (AUC-ROC 0.733, versus 0.710 for Random Forest and 0.702 for TG-CNN). We show, that discrimination alone is an incomplete criterion for clinical deployment: after Platt calibration, LASSO is the only model with an acceptable calibration slope (0.817), while Random Forest (0.759) and, TG-CNN (0.391) remain substantially miscalibrated. We argue that LASSO, not the highest-discriminating model, is the model best suited to direct clinical deployment. We present lessons for the machine learning and healthcare community regarding data infrastructure, model selection, and value of calibration and interpretability in high-stakes decision support.} }
Endnote
%0 Conference Paper %T Scalable Clinical Data Infrastructure and Comparative ML Evaluation for Hospitalisation Risk Prediction in Elderly Patients with Multiple Long-Term Conditions using CPRD %A Asra Aslam %A Volodymyr Chapman %A Maurice M. O’Connell %A Aseel S Abuzour %A Micheal Abaho %A Danushka Bollegala %A Gary Leeming %A Eduard Shantsila %A Andrew Clegg %A Lauren E Walker %A Iain Edward Buchan %A Samuel D Relton %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-aslam26a %I PMLR %P 141--167 %U https://proceedings.mlr.press/v340/aslam26a.html %V 340 %X Deep learning architectures are increasingly proposed for patient trajectory modeling in electronic health records (EHRs), yet their advantage over simpler, more interpretable models is rarely subjected to rigorous empirical scrutiny in real-world clinical settings. We present a comprehensive patient timeline pipeline applied to elderly patients in CPRD Aurum, incorporating 260 clinical conditions classified via a three-tier automated framework including specialised detection logic for 17 complex conditions. Using this infrastructure, we benchmark Temporal Graph Convolutional Neural Networks (TG-CNN) against Logistic Regression with LASSO regularisation and Random Forests for predicting 12-month all-cause emergency hospitalisation risk, motivated by (but not filtered to) the elevated risk of adverse drug reactions. Under cross-validation, TG-CNN achieves a marginally higher mean AUC-ROC than LASSO (0.712 vs. 0.705), whereas on the held-out test set LASSO achieves the highest discrimination of three models (AUC-ROC 0.733, versus 0.710 for Random Forest and 0.702 for TG-CNN). We show, that discrimination alone is an incomplete criterion for clinical deployment: after Platt calibration, LASSO is the only model with an acceptable calibration slope (0.817), while Random Forest (0.759) and, TG-CNN (0.391) remain substantially miscalibrated. We argue that LASSO, not the highest-discriminating model, is the model best suited to direct clinical deployment. We present lessons for the machine learning and healthcare community regarding data infrastructure, model selection, and value of calibration and interpretability in high-stakes decision support.
APA
Aslam, A., Chapman, V., O’Connell, M.M., Abuzour, A.S., Abaho, M., Bollegala, D., Leeming, G., Shantsila, E., Clegg, A., Walker, L.E., Buchan, I.E. & Relton, S.D.. (2026). Scalable Clinical Data Infrastructure and Comparative ML Evaluation for Hospitalisation Risk Prediction in Elderly Patients with Multiple Long-Term Conditions using CPRD. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:141-167 Available from https://proceedings.mlr.press/v340/aslam26a.html.

Related Material