MISDP: multi-task fusion visit interval for sequential diagnosis prediction
Abstract Backgrounds Diagnostic prediction is a central application that spans various medical specialties and scenarios, sequential diagnosis prediction is the process of predicting future diagnoses based on patients' historical visits. Prior research has underexplored the impact of irregular...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-12-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-024-05998-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850100561260576768 |
|---|---|
| author | Shengrong Zhu Ruijia Yang Zifeng Pan Xuan Tian Hong Ji |
| author_facet | Shengrong Zhu Ruijia Yang Zifeng Pan Xuan Tian Hong Ji |
| author_sort | Shengrong Zhu |
| collection | DOAJ |
| description | Abstract Backgrounds Diagnostic prediction is a central application that spans various medical specialties and scenarios, sequential diagnosis prediction is the process of predicting future diagnoses based on patients' historical visits. Prior research has underexplored the impact of irregular intervals between patient visits on predictive models, despite its significance. Method We developed the Multi-task Fusion Visit Interval for Sequential Diagnosis Prediction (MISDP) framework to address this research gap. The MISDP framework integrated sequential diagnosis prediction with visit interval prediction within a multi-task learning paradigm. It uses positional encoding and interval encoding to handle irregular patient visit intervals. Furthermore, it incorporates historical attention residue to enhance the multi-head self-attention mechanism, focusing on extracting long-term dependencies from clinical historical visits. Results The MISDP model exhibited superior performance across real-world healthcare dataset, irrespective of the training data scarcity or abundance. With only 20% training data, MISDP achieved a 4. 2% improvement over KAME; when training data ranged from 60 to 80%, MISDP surpassed SETOR, the top baseline, by 0. 8% in accuracy, underscoring its robustness and efficacy in sequential diagnosis prediction task. Conclusions The MISDP model significantly improves the accuracy of Sequential Diagnosis Prediction. The result highlights the advantage of multi-task learning in synergistically enhancing the performance of individual sub-task. Notably, irregular visit interval factors and historical attention residue has been particularly instrumental in refining the precision of sequential diagnosis prediction, suggesting a promising avenue for advancing clinical decision-making through data-driven modeling approaches. |
| format | Article |
| id | doaj-art-cee58672904d4e7685b68a1008744914 |
| institution | DOAJ |
| issn | 1471-2105 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj-art-cee58672904d4e7685b68a10087449142025-08-20T02:40:17ZengBMCBMC Bioinformatics1471-21052024-12-0125111410.1186/s12859-024-05998-xMISDP: multi-task fusion visit interval for sequential diagnosis predictionShengrong Zhu0Ruijia Yang1Zifeng Pan2Xuan Tian3Hong Ji4Department of Information Management and Big Data Center, Peking University Third HospitalSchool of Information Science and Technology, Beijing Forestry UniversitySchool of Information Science and Technology, Beijing Forestry UniversitySchool of Information Science and Technology, Beijing Forestry UniversityDepartment of Information Management and Big Data Center, Peking University Third HospitalAbstract Backgrounds Diagnostic prediction is a central application that spans various medical specialties and scenarios, sequential diagnosis prediction is the process of predicting future diagnoses based on patients' historical visits. Prior research has underexplored the impact of irregular intervals between patient visits on predictive models, despite its significance. Method We developed the Multi-task Fusion Visit Interval for Sequential Diagnosis Prediction (MISDP) framework to address this research gap. The MISDP framework integrated sequential diagnosis prediction with visit interval prediction within a multi-task learning paradigm. It uses positional encoding and interval encoding to handle irregular patient visit intervals. Furthermore, it incorporates historical attention residue to enhance the multi-head self-attention mechanism, focusing on extracting long-term dependencies from clinical historical visits. Results The MISDP model exhibited superior performance across real-world healthcare dataset, irrespective of the training data scarcity or abundance. With only 20% training data, MISDP achieved a 4. 2% improvement over KAME; when training data ranged from 60 to 80%, MISDP surpassed SETOR, the top baseline, by 0. 8% in accuracy, underscoring its robustness and efficacy in sequential diagnosis prediction task. Conclusions The MISDP model significantly improves the accuracy of Sequential Diagnosis Prediction. The result highlights the advantage of multi-task learning in synergistically enhancing the performance of individual sub-task. Notably, irregular visit interval factors and historical attention residue has been particularly instrumental in refining the precision of sequential diagnosis prediction, suggesting a promising avenue for advancing clinical decision-making through data-driven modeling approaches.https://doi.org/10.1186/s12859-024-05998-xSequential diagnosis predictionMulti-task learningIrregular visit intervalsHistorical attention residue |
| spellingShingle | Shengrong Zhu Ruijia Yang Zifeng Pan Xuan Tian Hong Ji MISDP: multi-task fusion visit interval for sequential diagnosis prediction BMC Bioinformatics Sequential diagnosis prediction Multi-task learning Irregular visit intervals Historical attention residue |
| title | MISDP: multi-task fusion visit interval for sequential diagnosis prediction |
| title_full | MISDP: multi-task fusion visit interval for sequential diagnosis prediction |
| title_fullStr | MISDP: multi-task fusion visit interval for sequential diagnosis prediction |
| title_full_unstemmed | MISDP: multi-task fusion visit interval for sequential diagnosis prediction |
| title_short | MISDP: multi-task fusion visit interval for sequential diagnosis prediction |
| title_sort | misdp multi task fusion visit interval for sequential diagnosis prediction |
| topic | Sequential diagnosis prediction Multi-task learning Irregular visit intervals Historical attention residue |
| url | https://doi.org/10.1186/s12859-024-05998-x |
| work_keys_str_mv | AT shengrongzhu misdpmultitaskfusionvisitintervalforsequentialdiagnosisprediction AT ruijiayang misdpmultitaskfusionvisitintervalforsequentialdiagnosisprediction AT zifengpan misdpmultitaskfusionvisitintervalforsequentialdiagnosisprediction AT xuantian misdpmultitaskfusionvisitintervalforsequentialdiagnosisprediction AT hongji misdpmultitaskfusionvisitintervalforsequentialdiagnosisprediction |