Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2310.20204 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911962633338880 |
|---|---|
| author | Kim, Junu Shim, Chaeeun Yang, Bosco Seong Kyu Im, Chami Lim, Sung Yoon Jeong, Han-Gil Choi, Edward |
| author_facet | Kim, Junu Shim, Chaeeun Yang, Bosco Seong Kyu Im, Chami Lim, Sung Yoon Jeong, Han-Gil Choi, Edward |
| contents | Machine learning (ML) has recently shown promising results in medical predictions using electronic health records (EHRs). However, since ML models typically have a limited capability in terms of input sizes, selecting specific medical events from EHRs for use as input is necessary. This selection process, often relying on expert opinion, can cause bottlenecks in development. We propose Retrieval-Enhanced Medical prediction model (REMed) to address such challenges. REMed can essentially evaluate unlimited medical events, select the relevant ones, and make predictions. This allows for an unrestricted input size, eliminating the need for manual event selection. We verified these properties through experiments involving 27 clinical prediction tasks across four independent cohorts, where REMed outperformed the baselines. Notably, we found that the preferences of REMed align closely with those of medical experts. We expect our approach to significantly expedite the development of EHR prediction models by minimizing clinicians' need for manual involvement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_20204 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | General-Purpose Retrieval-Enhanced Medical Prediction Model Using Near-Infinite History Kim, Junu Shim, Chaeeun Yang, Bosco Seong Kyu Im, Chami Lim, Sung Yoon Jeong, Han-Gil Choi, Edward Machine Learning Computation and Language Machine learning (ML) has recently shown promising results in medical predictions using electronic health records (EHRs). However, since ML models typically have a limited capability in terms of input sizes, selecting specific medical events from EHRs for use as input is necessary. This selection process, often relying on expert opinion, can cause bottlenecks in development. We propose Retrieval-Enhanced Medical prediction model (REMed) to address such challenges. REMed can essentially evaluate unlimited medical events, select the relevant ones, and make predictions. This allows for an unrestricted input size, eliminating the need for manual event selection. We verified these properties through experiments involving 27 clinical prediction tasks across four independent cohorts, where REMed outperformed the baselines. Notably, we found that the preferences of REMed align closely with those of medical experts. We expect our approach to significantly expedite the development of EHR prediction models by minimizing clinicians' need for manual involvement. |
| title | General-Purpose Retrieval-Enhanced Medical Prediction Model Using Near-Infinite History |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2310.20204 |