Sequential pattern transformer (SPT): a generative and interpretable framework for predicting disease trajectories.
Saved in:
| Title: | Sequential pattern transformer (SPT): a generative and interpretable framework for predicting disease trajectories. |
|---|---|
| Authors: | Assadi Shalmani, Mohammad1 (AUTHOR), Khani, Masoud1 (AUTHOR), Taleban, Amirsajjad1 (AUTHOR), Yi, Zihao1 (AUTHOR), Fink, Jennifer T.2 (AUTHOR), Weber, Christopher E.3 (AUTHOR), Lu, Qiang4 (AUTHOR), Luo, Jake1 (AUTHOR) Jakeluo@uwm.edu |
| Source: | Neural Computing & Applications. Feb2026, Vol. 38 Issue 3, p1-23. 23p. |
| Subjects: | Disease progression, Sequential pattern mining, Probabilistic generative models, Predictive validity, Type 2 diabetes, Health information systems, Artificial intelligence |
| Abstract: | The effective integration of artificial intelligence into clinical workflows requires models that go beyond simple prediction to generate comprehensive, explainable, and actionable disease trajectories. Addressing the limitations of opaque deep learning architectures and the noise inherent in electronic health records, we introduce the sequential pattern transformer (SPT), a novel framework that synergizes sequential pattern mining with generative transformer modeling. Using four years of inpatient data from 258,460 type 2 diabetes patients, we applied the PrefixSpan algorithm to distill noisy diagnostic histories into a curated vocabulary of 95,630 statistically validated disease progression patterns. A decoder-only transformer was trained exclusively on these evidence-based sequences to learn the temporal dynamics of disease evolution. This pattern-guided approach shifts the modeling paradigm from classification to probabilistic trajectory generation. The model achieved a robust 85.78% Top-5 accuracy, significantly outperforming a standard LSTM baseline (71.47%). Beyond predictive accuracy, the framework constructs a dynamic Disease Atlas, a branching tree structure that visualizes likely future pathways, augmented by multi-level explainable AI (XAI) including learned clinical clusters, SHAP-based feature attribution, and counterfactual simulations. Crucially, this methodology is domain-agnostic and capable of efficient fine-tuning, making it a transferable solution for adapting to diverse clinical conditions and local hospital settings. SPT thus offers a transparent, robust, and scalable framework for mapping the complex temporal dynamics of disease, bridging the gap between high-performance AI and interpretable clinical application. [ABSTRACT FROM AUTHOR] |
| Copyright of Neural Computing & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 191288418 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Sequential pattern transformer (SPT): a generative and interpretable framework for predicting disease trajectories. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Assadi+Shalmani%2C+Mohammad%22">Assadi Shalmani, Mohammad</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Khani%2C+Masoud%22">Khani, Masoud</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Taleban%2C+Amirsajjad%22">Taleban, Amirsajjad</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yi%2C+Zihao%22">Yi, Zihao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Fink%2C+Jennifer+T%2E%22">Fink, Jennifer T.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Weber%2C+Christopher+E%2E%22">Weber, Christopher E.</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lu%2C+Qiang%22">Lu, Qiang</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Luo%2C+Jake%22">Luo, Jake</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> Jakeluo@uwm.edu</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Neural+Computing+%26+Applications%22">Neural Computing & Applications</searchLink>. Feb2026, Vol. 38 Issue 3, p1-23. 23p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Disease+progression%22">Disease progression</searchLink><br /><searchLink fieldCode="DE" term="%22Sequential+pattern+mining%22">Sequential pattern mining</searchLink><br /><searchLink fieldCode="DE" term="%22Probabilistic+generative+models%22">Probabilistic generative models</searchLink><br /><searchLink fieldCode="DE" term="%22Predictive+validity%22">Predictive validity</searchLink><br /><searchLink fieldCode="DE" term="%22Type+2+diabetes%22">Type 2 diabetes</searchLink><br /><searchLink fieldCode="DE" term="%22Health+information+systems%22">Health information systems</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: The effective integration of artificial intelligence into clinical workflows requires models that go beyond simple prediction to generate comprehensive, explainable, and actionable disease trajectories. Addressing the limitations of opaque deep learning architectures and the noise inherent in electronic health records, we introduce the sequential pattern transformer (SPT), a novel framework that synergizes sequential pattern mining with generative transformer modeling. Using four years of inpatient data from 258,460 type 2 diabetes patients, we applied the PrefixSpan algorithm to distill noisy diagnostic histories into a curated vocabulary of 95,630 statistically validated disease progression patterns. A decoder-only transformer was trained exclusively on these evidence-based sequences to learn the temporal dynamics of disease evolution. This pattern-guided approach shifts the modeling paradigm from classification to probabilistic trajectory generation. The model achieved a robust 85.78% Top-5 accuracy, significantly outperforming a standard LSTM baseline (71.47%). Beyond predictive accuracy, the framework constructs a dynamic Disease Atlas, a branching tree structure that visualizes likely future pathways, augmented by multi-level explainable AI (XAI) including learned clinical clusters, SHAP-based feature attribution, and counterfactual simulations. Crucially, this methodology is domain-agnostic and capable of efficient fine-tuning, making it a transferable solution for adapting to diverse clinical conditions and local hospital settings. SPT thus offers a transparent, robust, and scalable framework for mapping the complex temporal dynamics of disease, bridging the gap between high-performance AI and interpretable clinical application. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Neural Computing & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=191288418 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s00521-025-11695-4 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 23 StartPage: 1 Subjects: – SubjectFull: Disease progression Type: general – SubjectFull: Sequential pattern mining Type: general – SubjectFull: Probabilistic generative models Type: general – SubjectFull: Predictive validity Type: general – SubjectFull: Type 2 diabetes Type: general – SubjectFull: Health information systems Type: general – SubjectFull: Artificial intelligence Type: general Titles: – TitleFull: Sequential pattern transformer (SPT): a generative and interpretable framework for predicting disease trajectories. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Assadi Shalmani, Mohammad – PersonEntity: Name: NameFull: Khani, Masoud – PersonEntity: Name: NameFull: Taleban, Amirsajjad – PersonEntity: Name: NameFull: Yi, Zihao – PersonEntity: Name: NameFull: Fink, Jennifer T. – PersonEntity: Name: NameFull: Weber, Christopher E. – PersonEntity: Name: NameFull: Lu, Qiang – PersonEntity: Name: NameFull: Luo, Jake IsPartOfRelationships: – BibEntity: Dates: – D: 21 M: 02 Text: Feb2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 09410643 Numbering: – Type: volume Value: 38 – Type: issue Value: 3 Titles: – TitleFull: Neural Computing & Applications Type: main |
| ResultId | 1 |
