An AI-driven clinical care pathway to reduce 30-day readmission for chronic obstructive pulmonary disease (COPD) patients
Abstract Healthcare regulatory agencies have mandated a reduction in 30-day hospital readmission rates and have targeted COPD as a major contributor to 30-day readmissions. We aimed to develop and validate a simple tool deploying an artificial neural network (ANN) for early identification of COPD pa...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-22434-3 |
| _version_ | 1811315397554601984 |
|---|---|
| author | Lin Wang Guihua Li Chika F. Ezeana Richard Ogunti Mamta Puppala Tiancheng He Xiaohui Yu Solomon S. Y. Wong Zheng Yin Aaron W. Roberts Aryan Nezamabadi Pingyi Xu Adaani Frost Robert E. Jackson Stephen T. C. Wong |
| author_facet | Lin Wang Guihua Li Chika F. Ezeana Richard Ogunti Mamta Puppala Tiancheng He Xiaohui Yu Solomon S. Y. Wong Zheng Yin Aaron W. Roberts Aryan Nezamabadi Pingyi Xu Adaani Frost Robert E. Jackson Stephen T. C. Wong |
| author_sort | Lin Wang |
| collection | DOAJ |
| description | Abstract Healthcare regulatory agencies have mandated a reduction in 30-day hospital readmission rates and have targeted COPD as a major contributor to 30-day readmissions. We aimed to develop and validate a simple tool deploying an artificial neural network (ANN) for early identification of COPD patients with high readmission risk. Using COPD patient data from eight hospitals within a large urban hospital system, four variables were identified, weighted and validated. These included the number of in-patient admissions in the previous 6 months, the number of medications administered on the first day, insurance status, and the Rothman Index on hospital day one. An ANN model was trained to provide a predictive algorithm and validated on an additional dataset from a separate time period. The model was implemented in a smartphone app (Re-Admit) incorporating four input risk factors, and a clinical care plan focused on high-risk readmission candidates was then implemented. Subsequent readmission data was analyzed to assess impact. The areas under the curve of receiver operating characteristics predicting readmission with ANN is 0.77, with sensitivity 0.75 and specificity 0.67 on the separate validation data. Readmission rates in the COPD high-risk subgroup after app and clinical intervention implementation saw a significant 48% decline. Our studies show the efficacy of ANN model on predicting readmission risks for COPD patients. The AI enabled Re-Admit smartphone app predicts readmission risk on day one of the patient’s admission, allowing for early implementation of medical, hospital, and community resources to optimize and improve clinical care pathways. |
| first_indexed | 2024-04-13T11:30:43Z |
| format | Article |
| id | doaj.art-55d2ff9979064e1482b81e7600ef8c13 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-13T11:30:43Z |
| publishDate | 2022-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-55d2ff9979064e1482b81e7600ef8c132022-12-22T02:48:35ZengNature PortfolioScientific Reports2045-23222022-11-011211910.1038/s41598-022-22434-3An AI-driven clinical care pathway to reduce 30-day readmission for chronic obstructive pulmonary disease (COPD) patientsLin Wang0Guihua Li1Chika F. Ezeana2Richard Ogunti3Mamta Puppala4Tiancheng He5Xiaohui Yu6Solomon S. Y. Wong7Zheng Yin8Aaron W. Roberts9Aryan Nezamabadi10Pingyi Xu11Adaani Frost12Robert E. Jackson13Stephen T. C. Wong14AI in Medicine Group, Systems Medicine and Bioengineering Department, Houston Methodist Cancer CenterDepartment of Neurology, Guangdong Second People’s HospitalAI in Medicine Group, Systems Medicine and Bioengineering Department, Houston Methodist Cancer CenterInternal Medicine Department, Mayo Clinic Health SystemAI in Medicine Group, Systems Medicine and Bioengineering Department, Houston Methodist Cancer CenterAI in Medicine Group, Systems Medicine and Bioengineering Department, Houston Methodist Cancer CenterAI in Medicine Group, Systems Medicine and Bioengineering Department, Houston Methodist Cancer CenterBaylor University School of LawT.T. & W.F. Chao Center for BRAIN, Houston Methodist HospitalDivision of Maternal Fetal Medicine, Department of Obstetrics, Gynecology and Reproductive Sciences, Houston McGovern Medical School, University of Texas Health Science CenterDepartment of Medicine, Houston Methodist HospitalDepartment of Neurology, The First Affiliated Hospital of Guangzhou Medical UniversityHouston Methodist Research Institute, Houston Methodist Academic Institute, Houston Methodist HospitalDepartment of Medicine, Houston Methodist Hospital and Weill Cornell MedicineAI in Medicine Group, Systems Medicine and Bioengineering Department, Houston Methodist Cancer CenterAbstract Healthcare regulatory agencies have mandated a reduction in 30-day hospital readmission rates and have targeted COPD as a major contributor to 30-day readmissions. We aimed to develop and validate a simple tool deploying an artificial neural network (ANN) for early identification of COPD patients with high readmission risk. Using COPD patient data from eight hospitals within a large urban hospital system, four variables were identified, weighted and validated. These included the number of in-patient admissions in the previous 6 months, the number of medications administered on the first day, insurance status, and the Rothman Index on hospital day one. An ANN model was trained to provide a predictive algorithm and validated on an additional dataset from a separate time period. The model was implemented in a smartphone app (Re-Admit) incorporating four input risk factors, and a clinical care plan focused on high-risk readmission candidates was then implemented. Subsequent readmission data was analyzed to assess impact. The areas under the curve of receiver operating characteristics predicting readmission with ANN is 0.77, with sensitivity 0.75 and specificity 0.67 on the separate validation data. Readmission rates in the COPD high-risk subgroup after app and clinical intervention implementation saw a significant 48% decline. Our studies show the efficacy of ANN model on predicting readmission risks for COPD patients. The AI enabled Re-Admit smartphone app predicts readmission risk on day one of the patient’s admission, allowing for early implementation of medical, hospital, and community resources to optimize and improve clinical care pathways.https://doi.org/10.1038/s41598-022-22434-3 |
| spellingShingle | Lin Wang Guihua Li Chika F. Ezeana Richard Ogunti Mamta Puppala Tiancheng He Xiaohui Yu Solomon S. Y. Wong Zheng Yin Aaron W. Roberts Aryan Nezamabadi Pingyi Xu Adaani Frost Robert E. Jackson Stephen T. C. Wong An AI-driven clinical care pathway to reduce 30-day readmission for chronic obstructive pulmonary disease (COPD) patients Scientific Reports |
| title | An AI-driven clinical care pathway to reduce 30-day readmission for chronic obstructive pulmonary disease (COPD) patients |
| title_full | An AI-driven clinical care pathway to reduce 30-day readmission for chronic obstructive pulmonary disease (COPD) patients |
| title_fullStr | An AI-driven clinical care pathway to reduce 30-day readmission for chronic obstructive pulmonary disease (COPD) patients |
| title_full_unstemmed | An AI-driven clinical care pathway to reduce 30-day readmission for chronic obstructive pulmonary disease (COPD) patients |
| title_short | An AI-driven clinical care pathway to reduce 30-day readmission for chronic obstructive pulmonary disease (COPD) patients |
| title_sort | ai driven clinical care pathway to reduce 30 day readmission for chronic obstructive pulmonary disease copd patients |
| url | https://doi.org/10.1038/s41598-022-22434-3 |
| work_keys_str_mv | AT linwang anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT guihuali anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT chikafezeana anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT richardogunti anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT mamtapuppala anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT tianchenghe anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT xiaohuiyu anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT solomonsywong anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT zhengyin anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT aaronwroberts anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT aryannezamabadi anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT pingyixu anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT adaanifrost anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT robertejackson anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT stephentcwong anaidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT linwang aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT guihuali aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT chikafezeana aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT richardogunti aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT mamtapuppala aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT tianchenghe aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT xiaohuiyu aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT solomonsywong aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT zhengyin aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT aaronwroberts aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT aryannezamabadi aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT pingyixu aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT adaanifrost aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT robertejackson aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients AT stephentcwong aidrivenclinicalcarepathwaytoreduce30dayreadmissionforchronicobstructivepulmonarydiseasecopdpatients |