Cleveland Clinic Selected as Founding Partner in Quantum Computing Center of Greater Washington, D.C.

Improving hospital stays and outcomes for elderly dementia patients with AI

Newswise – HOUSTON – (September 29, 2022) – Using artificial intelligence, Houston Methodist researchers are able to predict hospital outcomes for geriatric patients with dementia on the first or second day of admission to the hospital. This early assessment of outcomes means faster interventions, better care coordination, smarter resource allocation, targeted care management, and prompt treatment for these more vulnerable, high-risk patients.

Because geriatric patients with dementia have longer hospital stays and incur higher healthcare costs than other patients, the team sought to address this issue by identifying modifiable risk factors and developing a model artificial intelligence that improves patient outcomes, improves their quality of life and reduces their risk of hospital readmission, as well as reducing hospitalization costs once the model is put into practice.

The study, published online September 29 in Alzheimer & Dementia: Translational research and clinical interventions, a journal of the Alzheimer’s Association, reviewed the hospital records of 8,407 geriatric patients with dementia over 10 years within Houston Methodist’s eight-hospital system, identifying risk factors for poor outcomes among patient subgroups suffering from different types of dementia that derive from diseases such as Alzheimer’s, Parkinson’s, vascular dementia and Huntington’s, among others. From this data, the researchers developed a machine learning model to quickly recognize predictive risk factors and their ranked importance for adverse hospital outcomes early in the hospital stay of these patients.

With an accuracy of 95.6%, their model outperformed all other common risk assessment methods for these multiple types of dementia. The researchers add that none of the other current methods have applied AI to comprehensively predict hospitalization outcomes for elderly patients with dementia in this way, nor identify specific risk factors that may be modified by clinical procedures or additional precautions to reduce risk.

“The study showed that if we can identify geriatric patients with dementia as soon as they are hospitalized and recognize important risk factors, then we can implement appropriate interventions immediately,” said Eugene C. Lai, MD, Ph.D., the Robert W. Hervey Distinguished Chair in Parkinson’s Disease Research and Treatment in the Stanley H. Appel Department of Neurology. “By immediately mitigating and correcting modifiable risk factors for adverse outcomes, we are able to improve outcomes and shorten their hospital stays.”

Lai, a neurologist, has worked with these patients for many years and wanted to find ways to better understand how they are managed and their behavior while in hospital, so that clinicians can improve care and quality of life for them. He approached Stephen TC Wong, Ph.D., PE, a bioinformatics expert and director of the TT and WF Chao Center for BRAIN in Houston Methodist, with this idea, as he had previously collaborated with Wong and knew his team had access to the Houston Methodist Patients’ Large Clinical Data Warehouse and the ability to use AI to analyze big data.

Risk factors for each type of dementia have been identified, including those that can be addressed by interventions. The main risk factors for hospitalization identified included encephalopathy, number of medical problems on admission, pressure sores, urinary tract infections, falls, source of admission, age, race and gender. anaemia, with several overlaps in the multiple dementia groups.

Ultimately, researchers aim to implement mitigation measures to guide clinical interventions to reduce these negative outcomes. Wong says the emerging strategy of applying powerful AI predictions to trigger the implementation of “intelligent” clinical pathways in hospitals is novel and will not only improve clinical outcomes and patient experience, but also reduce hospitalization costs.

“Our next steps will be to implement the validated AI model in a mobile app for ICU and senior hospital staff to alert them of geriatric patients with dementia who are at high risk for poor hospitalization outcomes and to guide them on interventional steps to reduce these risks,” said Wong, corresponding author of the paper and holder of the John S. Dunn Distinguished Presidential Chair in Biomedical Engineering at the Houston Methodist Research Institute. “We will work with Hospital IT to integrate this application seamlessly into EPIC as part of a system-wide implementation for routine clinical use.”

He said it will follow the same smart clinical pathway strategy they have been working on to integrate two other new AI applications his team has developed into the EPIC system for routine clinical use to guide interventions that reduce the fall risk of patients with injuries and to better assess the breast. cancer risk to reduce unnecessary biopsies and overdiagnosis.

Wong and Lai’s collaborators on this study were Xin Wang, Chika F. Ezeana, Lin Wang, Mamta Puppala, Yunjie He, Xiaohui Yu, Zheng Yin, and Hong Zhao, all with the TT&WF Chao Center for BRAIN at Houston Methodist Academic Institute, and Yan-Siang Huang of Far Eastern Memorial Hospital in Taiwan.

This study was supported by grants from the National Institutes of Health (R01AG057635 and R01AG069082), the TT and WF Chao Foundation, the John S. Dunn Research Foundation, the Houston Methodist Cornerstone Award, and the Paul Richard Jeanneret Research Fund.

————————

For more information: Risk factors and machine learning model for predicting hospitalization outcomes in geriatric patients with dementia. Alzheimer’s and dementia: translational research and clinical interventions. (online September 29, 2022) Xin Wang, Chika F. Ezeana, Lin Wang, Mamta Puppala, Yan-Siang Huang, Yunjie He, Xiaohui Yu, Zheng Yin, Hong Zhao, Eugene C. Lai and Stephen TC Wong. https://doi.org/10.1002/trc2.12351

###


#Improving #hospital #stays #outcomes #elderly #dementia #patients

Leave a Comment

Your email address will not be published. Required fields are marked *