A Transformer-Based Model for Zero-Shot Health Trajectory Prediction
Abstract Integrating modern machine learning and clinical decision-making has great promise for mitigating healthcare’s increasing cost and complexity. We introduce the Enhanced Transformer for Health Outcome Simulation (ETHOS), a novel application of the transformer deep-learning architecture for analyzing high-dimensional, heterogeneous, and episodic health data. ETHOS is trained using Patient Health Timelines (PHTs)—detailed, tokenized records of health events—to predict future health trajectories, leveraging a zero-shot learning approach.ETHOS represents a significant advancement in foundation model development for healthcare analytics, eliminating the need for labeled data and model fine-tuning. Its ability to simulate various treatment pathways and consider patient-specific factors positions ETHOS as a tool for care optimization and addressing biases in healthcare delivery. Future developments will expand ETHOS’ capabilities to incorporate a wider range of data types and data sources. Our work demonstrates a pathway toward accelerated AI development and deployment in healthcare..
Medienart: |
Preprint |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
bioRxiv.org - (2024) vom: 06. März Zur Gesamtaufnahme - year:2024 |
---|
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Renc, Pawel [VerfasserIn] |
---|
Links: |
Volltext [kostenfrei] |
---|
Themen: |
---|
doi: |
10.1101/2024.02.29.24303512 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
XBI04270376X |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | XBI04270376X | ||
003 | DE-627 | ||
005 | 20240307101443.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240305s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1101/2024.02.29.24303512 |2 doi | |
035 | |a (DE-627)XBI04270376X | ||
035 | |a (biorXiv)10.1101/2024.02.29.24303512 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Renc, Pawel |e verfasserin |4 aut | |
245 | 1 | 0 | |a A Transformer-Based Model for Zero-Shot Health Trajectory Prediction |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
520 | |a Abstract Integrating modern machine learning and clinical decision-making has great promise for mitigating healthcare’s increasing cost and complexity. We introduce the Enhanced Transformer for Health Outcome Simulation (ETHOS), a novel application of the transformer deep-learning architecture for analyzing high-dimensional, heterogeneous, and episodic health data. ETHOS is trained using Patient Health Timelines (PHTs)—detailed, tokenized records of health events—to predict future health trajectories, leveraging a zero-shot learning approach.ETHOS represents a significant advancement in foundation model development for healthcare analytics, eliminating the need for labeled data and model fine-tuning. Its ability to simulate various treatment pathways and consider patient-specific factors positions ETHOS as a tool for care optimization and addressing biases in healthcare delivery. Future developments will expand ETHOS’ capabilities to incorporate a wider range of data types and data sources. Our work demonstrates a pathway toward accelerated AI development and deployment in healthcare. | ||
650 | 4 | |a Biology |7 (dpeaa)DE-84 | |
650 | 4 | |a 570 |7 (dpeaa)DE-84 | |
700 | 1 | |a Jia, Yugang |4 aut | |
700 | 1 | |a Samir, Anthony E. |4 aut | |
700 | 1 | |a Was, Jaroslaw |4 aut | |
700 | 1 | |a Li, Quanzheng |0 (orcid)0000-0002-9651-5820 |4 aut | |
700 | 1 | |a Bates, David W. |4 aut | |
700 | 1 | |a Sitek, Arkadiusz |0 (orcid)0000-0002-0677-4002 |4 aut | |
773 | 0 | 8 | |i Enthalten in |t bioRxiv.org |g (2024) vom: 06. März |
773 | 1 | 8 | |g year:2024 |g day:06 |g month:03 |
856 | 4 | 0 | |u http://dx.doi.org/10.1101/2024.02.29.24303512 |z kostenfrei |3 Volltext |
912 | |a GBV_XBI | ||
951 | |a AR | ||
952 | |j 2024 |b 06 |c 03 |