Differences
This shows you the differences between two versions of the page.
| Both sides previous revision
Previous revision
Next revision
|
Previous revision
|
motor [2023/12/13 10:54]
nigam |
motor [2024/03/05 17:37] (current)
nigam |
| ====== MOTOR (Many Outcome Time Oriented Representations) ====== | ====== MOTOR (Many Outcome Time Oriented Representations) ====== |
| |
| | MOTOR is a self-supervised, time-to-event (TTE) 143M parameter foundation model which is pretrained on timestamped sequences of events in 55 million electronic health records (EHR) comprising 9 billion clinical events. |
| |
| MOTOR is a self-supervised, time-to-event (TTE) foundation model which is pretrained on timestamped sequences of events in electronic health records (EHR) and health insurance claims. TTE models are used for estimating the probability distribution of the time until a specific event occurs, which is an important task in medical settings. TTE models provide many advantages over classification using fixed time horizons, including naturally handling censored observations, but are challenging to train with limited labeled data. MOTOR addresses this challenge by pretraining on up to 55M patient records (9B clinical events). We evaluate MOTOR's transfer learning performance on 19 tasks, across 3 patient databases (a private EHR system, MIMIC-IV, and Merative claims data). Task-specific models adapted from MOTOR improve time-dependent C statistics by 4.6% over state-of-the-art, improve label efficiency by up to 95% ,and are more robust to temporal distributional shifts. We further evaluate cross-site portability by adapting our MOTOR foundation model for six prediction tasks on the MIMIC-IV dataset, where it outperforms all baselines. MOTOR is the first foundation model for medical TTE predictions and we are working to release a 143M parameter pretrained model for research use. | TTE models are used for estimating the probability distribution of the time until a specific event occurs, which is an important task in medical settings. We evaluate MOTOR's performance on 19 tasks, across 3 patient databases (a private EHR system, MIMIC-IV, and Merative claims data). Task-specific models adapted from MOTOR improve time-dependent C statistics by 4.6% over state-of-the-art, improve label efficiency by up to 95% ,and are more robust to temporal distributional shifts. We also evaluate cross-site portability by adapting our MOTOR foundation model for six prediction tasks on the MIMIC-IV dataset, where it outperforms all baselines. |
| | |
| | Steinberg et al, in ICLR 2024 [[https://arxiv.org/abs/2301.03150 |MOTOR: A Time-To-Event Foundation Model For Structured Medical Records]]. \\ |
| | Open review at https://openreview.net/forum?id=NialiwI2V6 \\ |
| | Model at https://huggingface.co/StanfordShahLab/motor-t-base |
