1
|
Din Abdul Jabbar MA, Guo L, Nag S, Guo Y, Simmons Z, Pioro EP, Ramasamy S, Yeo CJJ. Predicting amyotrophic lateral sclerosis (ALS) progression with machine learning. Amyotroph Lateral Scler Frontotemporal Degener 2024; 25:242-255. [PMID: 38052485 DOI: 10.1080/21678421.2023.2285443] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2023] [Accepted: 11/14/2023] [Indexed: 12/07/2023]
Abstract
OBJECTIVE To predict ALS progression with varying observation and prediction window lengths, using machine learning (ML). METHODS We used demographic, clinical, and laboratory parameters from 5030 patients in the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database to model ALS disease progression as fast (at least 1.5 points decline in ALS Functional Rating Scale-Revised (ALSFRS-R) per month) or non-fast, using Extreme Gradient Boosting (XGBoost) and Bayesian Long Short Term Memory (BLSTM). XGBoost identified predictors of progression while BLSTM provided a confidence level for each prediction. RESULTS ML models achieved area under receiver-operating-characteristics curve (AUROC) of 0.570-0.748 and were non-inferior to clinician assessments. Performance was similar with observation lengths of a single visit, 3, 6, or 12 months and on a holdout validation dataset, but was better for longer prediction lengths. 21 important predictors were identified, with the top 3 being days since disease onset, past ALSFRS-R and forced vital capacity. Nonstandard predictors included phosphorus, chloride and albumin. BLSTM demonstrated higher performance for the samples about which it was most confident. Patient screening by models may reduce hypothetical Phase II/III clinical trial sizes by 18.3%. CONCLUSION Similar accuracies across ML models using different observation lengths suggest that a clinical trial observation period could be shortened to a single visit and clinical trial sizes reduced. Confidence levels provided by BLSTM gave additional information on the trustworthiness of predictions, which could aid decision-making. The identified predictors of ALS progression are potential biomarkers and therapeutic targets for further research.
Collapse
Affiliation(s)
- Muzammil Arif Din Abdul Jabbar
- Department of Physiology, Development and Neuroscience, University of Cambridge, Cambridge, UK
- Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
| | - Ling Guo
- Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
| | - Sonakshi Nag
- Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
| | - Yang Guo
- Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
| | - Zachary Simmons
- Department of Neurology, Pennsylvania State University College of Medicine, State College, PA, USA
| | - Erik P Pioro
- Department of Neurology, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA
| | - Savitha Ramasamy
- Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
| | - Crystal Jing Jing Yeo
- Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
- Department of Neurology, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA
- Lee Kong Chien School of Medicine, Imperial College London and Nanyang Technological University Singapore, Singapore, Singapore
- School of Medicine, Medical Sciences and Nutrition, University of Aberdeen, Aberdeen, UK
- National Neuroscience Institute, Singapore, Singapore
- Duke-NUS Medical School, Singapore, Singapore
| |
Collapse
|