Chengyin Ye1, Jinmei Li2, Shiying Hao3, Modi Liu4, Hua Jin5, Le Zheng6, Minjie Xia7, Bo Jin8, Chunqing Zhu9, Shaun T Alfreds10, Frank Stearns11, Laura Kanov12, Karl G Sylvester13, Eric Widen14, Doff McElhinney15, Xuefeng Bruce Ling16. 1. Department of Health Management, Hangzhou Normal University, Hangzhou, China. Electronic address: yechengyin@hznu.edu.cn. 2. Department of Health Management, Hangzhou Normal University, Hangzhou, China. Electronic address: lijinmei@stu.hznu.edu.cn. 3. Department of Cardiothoracic Surgery, Stanford University, Stanford, CA, United States; Clinical and Translational Research Program, Betty Irene Moore Children's Heart Center, Lucile Packard Children's Hospital, Palo Alto, CA, United States. Electronic address: shiyingh@stanford.edu. 4. HBI Solutions Inc., Palo Alto, CA, United States. Electronic address: mliu@hbisolutions.com. 5. HBI Solutions Inc., Palo Alto, CA, United States. Electronic address: hjin@hbisolutions.cn. 6. Department of Cardiothoracic Surgery, Stanford University, Stanford, CA, United States; Clinical and Translational Research Program, Betty Irene Moore Children's Heart Center, Lucile Packard Children's Hospital, Palo Alto, CA, United States. Electronic address: zhengl07@stanford.edu. 7. HBI Solutions Inc., Palo Alto, CA, United States. Electronic address: cxia@hbisolutions.com. 8. HBI Solutions Inc., Palo Alto, CA, United States. Electronic address: ejin@hbisolutions.com. 9. HBI Solutions Inc., Palo Alto, CA, United States. Electronic address: czhu@hbisolutions.com. 10. HealthInfoNet, Portland, ME, United States. Electronic address: salfreds@hinfonet.org. 11. HBI Solutions Inc., Palo Alto, CA, United States. Electronic address: fstearns@hbisolutions.com. 12. HBI Solutions Inc., Palo Alto, CA, United States. Electronic address: lkanov@hbisolutions.com. 13. Department of Surgery, Stanford University, Stanford, CA, United States. Electronic address: karls@stanford.edu. 14. HBI Solutions Inc., Palo Alto, CA, United States. Electronic address: Ewiden@hbisolutions.com. 15. Department of Cardiothoracic Surgery, Stanford University, Stanford, CA, United States; Clinical and Translational Research Program, Betty Irene Moore Children's Heart Center, Lucile Packard Children's Hospital, Palo Alto, CA, United States. Electronic address: Doff@stanford.edu. 16. Clinical and Translational Research Program, Betty Irene Moore Children's Heart Center, Lucile Packard Children's Hospital, Palo Alto, CA, United States; Department of Surgery, Stanford University, Stanford, CA, United States. Electronic address: bxling@stanford.edu.
Abstract
OBJECTIVE: Predicting the risk of falls in advance can benefit the quality of care and potentially reduce mortality and morbidity in the older population. The aim of this study was to construct and validate an electronic health record-based fall risk predictive tool to identify elders at a higher risk of falls. METHODS: The one-year fall prediction model was developed using the machine-learning-based algorithm, XGBoost, and tested on an independent validation cohort. The data were collected from electronic health records (EHR) of Maine from 2016 to 2018, comprising 265,225 older patients (≥65 years of age). RESULTS: This model attained a validated C-statistic of 0.807, where 50 % of the identified high-risk true positives were confirmed to fall during the first 94 days of next year. The model also captured in advance 58.01 % and 54.93 % of falls that happened within the first 30 and 30-60 days of next year. The identified high-risk patients of fall showed conditions of severe disease comorbidities, an enrichment of fall-increasing cardiovascular and mental medication prescriptions and increased historical clinical utilization, revealing the complexity of the underlying fall etiology. The XGBoost algorithm captured 157 impactful predictors into the final predictive model, where cognitive disorders, abnormalities of gait and balance, Parkinson's disease, fall history and osteoporosis were identified as the top-5 strongest predictors of the future fall event. CONCLUSIONS: By using the EHR data, this risk assessment tool attained an improved discriminative ability and can be immediately deployed in the health system to provide automatic early warnings to older adults with increased fall risk and identify their personalized risk factors to facilitate customized fall interventions.
OBJECTIVE: Predicting the risk of falls in advance can benefit the quality of care and potentially reduce mortality and morbidity in the older population. The aim of this study was to construct and validate an electronic health record-based fall risk predictive tool to identify elders at a higher risk of falls. METHODS: The one-year fall prediction model was developed using the machine-learning-based algorithm, XGBoost, and tested on an independent validation cohort. The data were collected from electronic health records (EHR) of Maine from 2016 to 2018, comprising 265,225 older patients (≥65 years of age). RESULTS: This model attained a validated C-statistic of 0.807, where 50 % of the identified high-risk true positives were confirmed to fall during the first 94 days of next year. The model also captured in advance 58.01 % and 54.93 % of falls that happened within the first 30 and 30-60 days of next year. The identified high-risk patients of fall showed conditions of severe disease comorbidities, an enrichment of fall-increasing cardiovascular and mental medication prescriptions and increased historical clinical utilization, revealing the complexity of the underlying fall etiology. The XGBoost algorithm captured 157 impactful predictors into the final predictive model, where cognitive disorders, abnormalities of gait and balance, Parkinson's disease, fall history and osteoporosis were identified as the top-5 strongest predictors of the future fall event. CONCLUSIONS: By using the EHR data, this risk assessment tool attained an improved discriminative ability and can be immediately deployed in the health system to provide automatic early warnings to older adults with increased fall risk and identify their personalized risk factors to facilitate customized fall interventions.
Authors: Brian J Douthit; Rachel L Walden; Kenrick Cato; Cynthia P Coviak; Christopher Cruz; Fabio D'Agostino; Thompson Forbes; Grace Gao; Theresa A Kapetanovic; Mikyoung A Lee; Lisiane Pruinelli; Mary A Schultz; Ann Wieben; Alvin D Jeffery Journal: Appl Clin Inform Date: 2022-02-09 Impact factor: 2.342
Authors: Anup Kumar Mishra; Marjorie Skubic; Laurel A Despins; Mihail Popescu; James Keller; Marilyn Rantz; Carmen Abbott; Moein Enayati; Shradha Shalini; Steve Miller Journal: Front Digit Health Date: 2022-05-06
Authors: Bob van de Loo; Lotta J Seppala; Nathalie van der Velde; Stephanie Medlock; Michael Denkinger; Lisette Cpgm de Groot; Rose-Anne Kenny; Frank Moriarty; Dietrich Rothenbacher; Bruno Stricker; André Uitterlinden; Ameen Abu-Hanna; Martijn W Heymans; Natasja van Schoor Journal: J Gerontol A Biol Sci Med Sci Date: 2022-07-05 Impact factor: 6.591
Authors: Noman Dormosh; Martijn C Schut; Martijn W Heymans; Nathalie van der Velde; Ameen Abu-Hanna Journal: J Gerontol A Biol Sci Med Sci Date: 2022-07-05 Impact factor: 6.591
Authors: Kathrin Seibert; Dominik Domhoff; Dominik Bruch; Matthias Schulte-Althoff; Daniel Fürstenau; Felix Biessmann; Karin Wolf-Ostermann Journal: J Med Internet Res Date: 2021-11-29 Impact factor: 5.428
Authors: Amit Gupta; Christina Maslen; Madhavi Vindlacheruvu; Richard L Abel; Pinaki Bhattacharya; Paul A Bromiley; Emma M Clark; Juliet E Compston; Nicola Crabtree; Jennifer S Gregory; Eleni P Kariki; Nicholas C Harvey; Eugene McCloskey; Kate A Ward; Kenneth E S Poole Journal: Ther Adv Musculoskelet Dis Date: 2022-03-28 Impact factor: 5.346