1
|
Gao Z, Liu X, Kang Y, Hu P, Zhang X, Yan W, Yan M, Yu P, Zhang Q, Xiao W, Zhang Z. Improving the Prognostic Evaluation Precision of Hospital Outcomes for Heart Failure Using Admission Notes and Clinical Tabular Data: Multimodal Deep Learning Model. J Med Internet Res 2024; 26:e54363. [PMID: 38696251 PMCID: PMC11099809 DOI: 10.2196/54363] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2023] [Revised: 01/01/2024] [Accepted: 03/19/2024] [Indexed: 05/04/2024] Open
Abstract
BACKGROUND Clinical notes contain contextualized information beyond structured data related to patients' past and current health status. OBJECTIVE This study aimed to design a multimodal deep learning approach to improve the evaluation precision of hospital outcomes for heart failure (HF) using admission clinical notes and easily collected tabular data. METHODS Data for the development and validation of the multimodal model were retrospectively derived from 3 open-access US databases, including the Medical Information Mart for Intensive Care III v1.4 (MIMIC-III) and MIMIC-IV v1.0, collected from a teaching hospital from 2001 to 2019, and the eICU Collaborative Research Database v1.2, collected from 208 hospitals from 2014 to 2015. The study cohorts consisted of all patients with critical HF. The clinical notes, including chief complaint, history of present illness, physical examination, medical history, and admission medication, as well as clinical variables recorded in electronic health records, were analyzed. We developed a deep learning mortality prediction model for in-hospital patients, which underwent complete internal, prospective, and external evaluation. The Integrated Gradients and SHapley Additive exPlanations (SHAP) methods were used to analyze the importance of risk factors. RESULTS The study included 9989 (16.4%) patients in the development set, 2497 (14.1%) patients in the internal validation set, 1896 (18.3%) in the prospective validation set, and 7432 (15%) patients in the external validation set. The area under the receiver operating characteristic curve of the models was 0.838 (95% CI 0.827-0.851), 0.849 (95% CI 0.841-0.856), and 0.767 (95% CI 0.762-0.772), for the internal, prospective, and external validation sets, respectively. The area under the receiver operating characteristic curve of the multimodal model outperformed that of the unimodal models in all test sets, and tabular data contributed to higher discrimination. The medical history and physical examination were more useful than other factors in early assessments. CONCLUSIONS The multimodal deep learning model for combining admission notes and clinical tabular data showed promising efficacy as a potentially novel method in evaluating the risk of mortality in patients with HF, providing more accurate and timely decision support.
Collapse
Affiliation(s)
- Zhenyue Gao
- Beijing Engineering Research Center of Industrial Spectrum Imaging, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China
| | - Xiaoli Liu
- Center for Artificial Intelligence in Medicine, The General Hospital of People's Liberation Army, Beijing, China
| | - Yu Kang
- Department of Cardiology, West China Hospital, Sichuan University, Chengdu, China
| | - Pan Hu
- Center for Artificial Intelligence in Medicine, The General Hospital of People's Liberation Army, Beijing, China
| | - Xiu Zhang
- Department of Cardiology, West China Hospital, Sichuan University, Chengdu, China
| | - Wei Yan
- Center for Artificial Intelligence in Medicine, The General Hospital of People's Liberation Army, Beijing, China
| | - Muyang Yan
- Center for Artificial Intelligence in Medicine, The General Hospital of People's Liberation Army, Beijing, China
| | - Pengming Yu
- Department of Cardiology, West China Hospital, Sichuan University, Chengdu, China
| | - Qing Zhang
- Department of Cardiology, West China Hospital, Sichuan University, Chengdu, China
| | - Wendong Xiao
- Beijing Engineering Research Center of Industrial Spectrum Imaging, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China
| | - Zhengbo Zhang
- Center for Artificial Intelligence in Medicine, The General Hospital of People's Liberation Army, Beijing, China
| |
Collapse
|
2
|
Zhang Y, Aaronson KD, Gryak J, Wittrup E, Minoccheri C, Golbus JR, Najarian K. Predicting need for heart failure advanced therapies using an interpretable tropical geometry-based fuzzy neural network. PLoS One 2023; 18:e0295016. [PMID: 38015947 PMCID: PMC10684094 DOI: 10.1371/journal.pone.0295016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Accepted: 11/13/2023] [Indexed: 11/30/2023] Open
Abstract
BACKGROUND Timely referral for advanced therapies (i.e., heart transplantation, left ventricular assist device) is critical for ensuring optimal outcomes for heart failure patients. Using electronic health records, our goal was to use data from a single hospitalization to develop an interpretable clinical decision-making system for predicting the need for advanced therapies at the subsequent hospitalization. METHODS Michigan Medicine heart failure patients from 2013-2021 with a left ventricular ejection fraction ≤ 35% and at least two heart failure hospitalizations within one year were used to train an interpretable machine learning model constructed using fuzzy logic and tropical geometry. Clinical knowledge was used to initialize the model. The performance and robustness of the model were evaluated with the mean and standard deviation of the area under the receiver operating curve (AUC), the area under the precision-recall curve (AUPRC), and the F1 score of the ensemble. We inferred membership functions from the model for continuous clinical variables, extracted decision rules, and then evaluated their relative importance. RESULTS The model was trained and validated using data from 557 heart failure hospitalizations from 300 patients, of whom 193 received advanced therapies. The mean (standard deviation) of AUC, AUPRC, and F1 scores of the proposed model initialized with clinical knowledge was 0.747 (0.080), 0.642 (0.080), and 0.569 (0.067), respectively, showing superior predictive performance or increased interpretability over other machine learning methods. The model learned critical risk factors predicting the need for advanced therapies in the subsequent hospitalization. Furthermore, our model displayed transparent rule sets composed of these critical concepts to justify the prediction. CONCLUSION These results demonstrate the ability to successfully predict the need for advanced heart failure therapies by generating transparent and accessible clinical rules although further research is needed to prospectively validate the risk factors identified by the model.
Collapse
Affiliation(s)
- Yufeng Zhang
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, Michigan, United States of America
| | - Keith D. Aaronson
- Department of Internal Medicine, Division of Cardiovascular Medicine, University of Michigan, Ann Arbor, Michigan, United States of America
| | - Jonathan Gryak
- Department of Computer Science, Queens College, City University of New York, New York, New York, United States of America
| | - Emily Wittrup
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, Michigan, United States of America
| | - Cristian Minoccheri
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, Michigan, United States of America
| | - Jessica R. Golbus
- Department of Internal Medicine, Division of Cardiovascular Medicine, University of Michigan, Ann Arbor, Michigan, United States of America
| | - Kayvan Najarian
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, Michigan, United States of America
- Michigan Institute for Data Science, University of Michigan, Ann Arbor, Michigan, United States of America
- Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, Michigan, United States of America
- Department of Emergency Medicine, University of Michigan, Ann Arbor, Michigan, United States of America
| |
Collapse
|
3
|
Docherty KF, Lam CSP, Rakisheva A, Coats AJS, Greenhalgh T, Metra M, Petrie MC, Rosano GMC. Heart failure diagnosis in the general community - Who, how and when? A clinical consensus statement of the Heart Failure Association (HFA) of the European Society of Cardiology (ESC). Eur J Heart Fail 2023; 25:1185-1198. [PMID: 37368511 DOI: 10.1002/ejhf.2946] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Revised: 06/17/2023] [Accepted: 06/19/2023] [Indexed: 06/29/2023] Open
Abstract
A significant proportion of patients experience delays in the diagnosis of heart failure due to the non-specific signs and symptoms of the syndrome. Diagnostic tools such as measurement of natriuretic peptide concentrations are fundamentally important when screening for heart failure, yet are frequently under-utilized. This clinical consensus statement provides a diagnostic framework for general practitioners and non-cardiology community-based physicians to recognize, investigate and risk-stratify patients presenting in the community with possible heart failure.
Collapse
Affiliation(s)
- Kieran F Docherty
- BHF Cardiovascular Research Centre, University of Glasgow, Glasgow, UK
| | - Carolyn S P Lam
- National Heart Centre Singapore, Duke-National University of Singapore, Singapore, Singapore
| | - Amina Rakisheva
- Scientific Research Institute of Cardiology and Internal Medicine, Almaty, Kazakhstan
| | | | - Trisha Greenhalgh
- Nuffield Department of Primary Care Health Sciences, Medical Sciences Division, University of Oxford, Oxford, UK
| | - Marco Metra
- Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, Cardiology. ASST Spedali Civili, University of Brescia, Brescia, Italy
| | - Mark C Petrie
- BHF Cardiovascular Research Centre, University of Glasgow, Glasgow, UK
| | | |
Collapse
|
4
|
Brooksbank JA, Faulkenberg KD, Tang WHW, Martyn T. Novel Strategies to Improve Prescription of Guideline-Directed Medical Therapy in Heart Failure. CURRENT TREATMENT OPTIONS IN CARDIOVASCULAR MEDICINE 2023; 25:93-110. [PMID: 37077616 PMCID: PMC10073621 DOI: 10.1007/s11936-023-00979-4] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 02/22/2023] [Indexed: 04/07/2023]
Abstract
PURPOSE OF REVIEW To examine the emerging data for novel strategies being studied to improve use and dose titration of guideline-directed medical therapy (GDMT) for patients with heart failure (HF). RECENT FINDINGS There is mounting evidence to employ novel multi-pronged strategies to address HF implementation gaps. SUMMARY Despite high-level randomized evidence and clear national society recommendations, a large gap persists in use and dose titration of guideline-directed medical therapy (GDMT) in patients with heart failure (HF). Accelerating the safe implementation of GDMT has proven to reduce the morbidity and mortality associated with HF but remains an ongoing challenge for patients, clinicians, and health systems. In this review, we examine the emerging data for novel strategies to improve the use of GDMT including the use of multidisciplinary team-based approaches, nontraditional patient encounters, patient messaging/engagement, remote patient monitoring, and electronic health record (EHR)-based clinical alerts. While societal guidelines and implementation studies have focused on heart failure with reduced ejection fraction (HFrEF), expanding indications and evidence for the use of sodium glucose cotransporter2 (SGLT2i) will necessitate implementation efforts across the LVEF spectrum.
Collapse
Affiliation(s)
- Jeremy A. Brooksbank
- Robert and Suzanne Tomsich Department of Cardiovascular Medicine, Sydell and Arnold Miller Family Heart and Vascular Institute, Cleveland Clinic, Euclid Ave, Cleveland, OH USA
| | | | - W. H. Wilson Tang
- Robert and Suzanne Tomsich Department of Cardiovascular Medicine, Sydell and Arnold Miller Family Heart and Vascular Institute, Cleveland Clinic, Euclid Ave, Cleveland, OH USA
- George M. and Linda H. Kaufman Center for Heart Failure and Recovery, Cleveland Clinic, Cleveland, OH USA
| | - Trejeeve Martyn
- Robert and Suzanne Tomsich Department of Cardiovascular Medicine, Sydell and Arnold Miller Family Heart and Vascular Institute, Cleveland Clinic, Euclid Ave, Cleveland, OH USA
- George M. and Linda H. Kaufman Center for Heart Failure and Recovery, Cleveland Clinic, Cleveland, OH USA
| |
Collapse
|
5
|
Ma M, Hao X, Zhao J, Luo S, Liu Y, Li D. Predicting heart failure in-hospital mortality by integrating longitudinal and category data in electronic health records. Med Biol Eng Comput 2023:10.1007/s11517-023-02816-z. [PMID: 36959414 DOI: 10.1007/s11517-023-02816-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2022] [Accepted: 03/02/2023] [Indexed: 03/25/2023]
Abstract
Heart failure is a life-threatening syndrome that is diagnosed in 3.6 million people worldwide each year. We propose a deep fusion learning model (DFL-IMP) that uses time series and category data from electronic health records to predict in-hospital mortality in patients with heart failure. We considered 41 time series features (platelets, white blood cells, urea nitrogen, etc.) and 17 category features (gender, insurance, marital status, etc.) as predictors, all of which were available within the time of the patient's last hospitalization, and a total of 7696 patients participated in the observational study. Our model was evaluated against different time windows. The best performance was achieved with an AUC of 0.914 when the observation window was 5 days and the prediction window was 30 days. Outperformed other baseline models including LR (0.708), RF (0.717), SVM (0.675), LSTM (0.757), GRU (0.759), GRU-U (0.766) and MTSSP (0.770). This tool allows us to predict the expected pathway of heart failure patients and intervene early in the treatment process, which has significant implications for improving the life expectancy of heart failure patients.
Collapse
Affiliation(s)
- Meikun Ma
- College of Information and Computer, Taiyuan University of Technology, Taiyuan, 030024, China
- Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province, Taiyuan, 030024, China
- Technology Research Center of Spatial Information Network Engineering of Shanxi, Taiyuan, 030024, China
| | - Xiaoyan Hao
- College of Information and Computer, Taiyuan University of Technology, Taiyuan, 030024, China
| | - Jumin Zhao
- College of Information and Computer, Taiyuan University of Technology, Taiyuan, 030024, China
- Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province, Taiyuan, 030024, China
- Intelligent Perception Engineering Technology Center of Shanxi, Taiyuan, 030024, China
| | - Shijie Luo
- College of Information and Computer, Taiyuan University of Technology, Taiyuan, 030024, China
| | - Yi Liu
- Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province, Taiyuan, 030024, China
- Technology Research Center of Spatial Information Network Engineering of Shanxi, Taiyuan, 030024, China
- College of Data Science, Taiyuan University of Technology, Taiyuan, 030024, China
| | - Dengao Li
- Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province, Taiyuan, 030024, China.
- Technology Research Center of Spatial Information Network Engineering of Shanxi, Taiyuan, 030024, China.
- College of Data Science, Taiyuan University of Technology, Taiyuan, 030024, China.
| |
Collapse
|