Integrating Social Determinants of Health in a Multi-Modal Deep Clustering Survival Model for Injury-Risk in Alzheimer’s and Related Dementia Patients

Kazi Noshin; Mary Regina Boland; Bojian Hou; Weiqing He; Victoria Lu; Li Shen; Aidong Zhang

Integrating Social Determinants of Health in a Multi-Modal Deep Clustering Survival Model for Injury-Risk in Alzheimer’s and Related Dementia Patients

Kazi Noshin, Mary Regina Boland, Bojian Hou, Weiqing He, Victoria Lu, Li Shen, Aidong Zhang

Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare, PMLR 281:155-164, 2025.

Abstract

As our population ages, the prevalence of Alzheimer’s Disease and Related Dementias (ADRD) and its associated burdens continue to rise. Social Determinants of Health (SDOH) significantly influence both ADRD development and progression. Using Electronic Health Records (EHR) from a quaternary care academic medical center in a diverse urban setting, we investigated SDOH’s impact on multi-modal deep clustering survival machines. Our findings revealed that SDOH improved model performance across feature selection methods (DeepCox roll-out vs. SHAP DeepExplainer) and EHR clinical modalities (medication vs. laboratory). Additionally, Laboratory features proved more informative than medications for predicting injury-fall risk. Our results highlight SDOH’s crucial role in ADRD progression, particularly regarding injury-fall risk. We found that feature importance varied by selection method when analyzing multi-modality EHR data, with education emerging as a key SDOH factor among our top 10 features, underscoring its significance in ADRD progression.

Cite this Paper

BibTeX

@InProceedings{pmlr-v281-noshin25a,
  title = 	 {Integrating Social Determinants of Health in a Multi-Modal Deep Clustering Survival Model for Injury-Risk in Alzheimer’s and Related Dementia Patients},
  author =       {Noshin, Kazi and Boland, Mary Regina and Hou, Bojian and He, Weiqing and Lu, Victoria and Shen, Li and Zhang, Aidong},
  booktitle = 	 {Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare},
  pages = 	 {155--164},
  year = 	 {2025},
  editor = 	 {Wu, Junde and Zhu, Jiayuan and Xu, Min and Jin, Yueming},
  volume = 	 {281},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {25 Feb},
  publisher =    {PMLR},
  pdf = 	 {https://raw.githubusercontent.com/mlresearch/v281/main/assets/noshin25a/noshin25a.pdf},
  url = 	 {https://proceedings.mlr.press/v281/noshin25a.html},
  abstract = 	 {As our population ages, the prevalence of Alzheimer’s Disease and Related Dementias (ADRD) and its associated burdens continue to rise. Social Determinants of Health (SDOH) significantly influence both ADRD development and progression. Using Electronic Health Records (EHR) from a quaternary care academic medical center in a diverse urban setting, we investigated SDOH’s impact on multi-modal deep clustering survival machines. Our findings revealed that SDOH improved model performance across feature selection methods (DeepCox roll-out vs. SHAP DeepExplainer) and EHR clinical modalities (medication vs. laboratory). Additionally, Laboratory features proved more informative than medications for predicting injury-fall risk. Our results highlight SDOH’s crucial role in ADRD progression, particularly regarding injury-fall risk. We found that feature importance varied by selection method when analyzing multi-modality EHR data, with education emerging as a key SDOH factor among our top 10 features, underscoring its significance in ADRD progression.}
}

Endnote

%0 Conference Paper
%T Integrating Social Determinants of Health in a Multi-Modal Deep Clustering Survival Model for Injury-Risk in Alzheimer’s and Related Dementia Patients
%A Kazi Noshin
%A Mary Regina Boland
%A Bojian Hou
%A Weiqing He
%A Victoria Lu
%A Li Shen
%A Aidong Zhang
%B Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare
%C Proceedings of Machine Learning Research
%D 2025
%E Junde Wu
%E Jiayuan Zhu
%E Min Xu
%E Yueming Jin	
%F pmlr-v281-noshin25a
%I PMLR
%P 155--164
%U https://proceedings.mlr.press/v281/noshin25a.html
%V 281
%X As our population ages, the prevalence of Alzheimer’s Disease and Related Dementias (ADRD) and its associated burdens continue to rise. Social Determinants of Health (SDOH) significantly influence both ADRD development and progression. Using Electronic Health Records (EHR) from a quaternary care academic medical center in a diverse urban setting, we investigated SDOH’s impact on multi-modal deep clustering survival machines. Our findings revealed that SDOH improved model performance across feature selection methods (DeepCox roll-out vs. SHAP DeepExplainer) and EHR clinical modalities (medication vs. laboratory). Additionally, Laboratory features proved more informative than medications for predicting injury-fall risk. Our results highlight SDOH’s crucial role in ADRD progression, particularly regarding injury-fall risk. We found that feature importance varied by selection method when analyzing multi-modality EHR data, with education emerging as a key SDOH factor among our top 10 features, underscoring its significance in ADRD progression.

APA

Noshin, K., Boland, M.R., Hou, B., He, W., Lu, V., Shen, L. & Zhang, A.. (2025). Integrating Social Determinants of Health in a Multi-Modal Deep Clustering Survival Model for Injury-Risk in Alzheimer’s and Related Dementia Patients. Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare, in Proceedings of Machine Learning Research 281:155-164 Available from https://proceedings.mlr.press/v281/noshin25a.html.

Related Material

Download PDF