1
|
Song X, Tong Y, Xian F, Luo Y, Tong R. Predicting 1 year readmission for heart failure: A comparative study of machine learning and the LACE index. ESC Heart Fail 2024. [PMID: 38778700 DOI: 10.1002/ehf2.14855] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/23/2024] [Revised: 03/29/2024] [Accepted: 04/24/2024] [Indexed: 05/25/2024] Open
Abstract
AIMS There is a lack of tools for accurately identifying the risk of readmission for heart failure in elderly patients with arrhythmia. The aim of this study was to establish and compare the performance of the LACE [length of stay ('L'), acute (emergent) admission ('A'), Charlson comorbidity index ('C') and visits to the emergency department during the previous 6 months ('E')] index and machine learning in predicting 1 year readmission for heart failure in elderly patients with arrhythmia. METHODS Elderly patients with arrhythmia who were hospitalized at Sichuan Provincial People's Hospital between 1 June 2018 and 31 May 2020 were enrolled. The LACE index was calculated for each patient, and the area under the receiver operating characteristic curve (AUROC) was calculated. Six machine learning algorithms, combined with three variable selection methods and clinically relevant features available at the time of hospital discharge, were used to develop machine learning models. AUROC and area under the precision-recall curve (AUPRC) were used to assess discrimination. Shapley additive explanations (SHAP) analysis was used to explain the contributions of the features. RESULTS A total of 523 patients were enrolled, and 108 patients experienced 1 year hospital readmission for heart failure. The AUROC of the LACE index was 0.5886. The complete machine learning model had the best predictive performance, with an AUROC of 0.7571 and an AUPRC of 0.4096. The most important predictors for 1 year readmission were educational level, total triiodothyronine (TT3), aspartate aminotransferase/alanine aminotransferase (AST/ALT), number of medications (NOM) and triglyceride (TG) level. CONCLUSIONS Compared with the LACE index, the machine learning model can accurately identify the risk of 1 year readmission for heart failure in elderly patients with arrhythmia.
Collapse
Affiliation(s)
- Xuewu Song
- Department of Pharmacy, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China
| | - Yitong Tong
- Chengdu Second People's Hospital, Chengdu, China
| | - Feng Xian
- Department of Oncology, Nanchong Central Hospital, the Second Clinical Medical College, North Sichuan Medical College, Nanchong, China
| | - Yi Luo
- Department of Pharmacy, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China
| | - Rongsheng Tong
- Department of Pharmacy, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China
| |
Collapse
|
2
|
Bortolani A, Fantin F, Giani A, Zivelonghi A, Pernice B, Bortolazzi E, Urbani S, Zoico E, Micciolo R, Zamboni M. Predictors of hospital readmission rate in geriatric patients. Aging Clin Exp Res 2024; 36:22. [PMID: 38321332 PMCID: PMC10847193 DOI: 10.1007/s40520-023-02664-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Accepted: 11/11/2023] [Indexed: 02/08/2024]
Abstract
BACKGROUND Hospital readmissions among older adults are associated with progressive functional worsening, increased institutionalization and mortality. AIM Identify the main predictors of readmission in older adults. METHODS We examined readmission predictors in 777 hospitalized subjects (mean age 84.40 ± 6.77 years) assessed with Comprehensive Geriatric Assessment (CGA), clinical, anthropometric and biochemical evaluations. Comorbidity burden was estimated by Charlson Comorbidity Index (CCI). Median follow-up was 365 days. RESULTS 358 patients (46.1%) had a second admission within 365 days of discharge. Estimated probability of having a second admission was 0.119 (95%C.I. 0.095-0.141), 0.158 (95%C.I. 0.131-0.183), and 0.496 (95%C.I. 0.458-0.532) at 21, 30 and 356 days, respectively. Main predictors of readmission at 1 year were length of stay (LOS) > 14 days (p < 0.001), albumin level < 30 g/l (p 0.018), values of glomerular filtration rate (eGFR) < 40 ml/min (p < 0.001), systolic blood pressure < 115 mmHg (p < 0.001), CCI ≥ 6 (p < 0.001), and cardiovascular diagnoses. When the joint effects of selected prognostic variables were accounted for, LOS > 14 days, worse renal function, systolic blood pressure < 115 mmHg, higher comorbidity burden remained independently associated with higher readmission risk. DISCUSSION Selected predictors are associated with higher readmission risk, and the relationship evolves with time. CONCLUSIONS This study highlights the importance of performing an accurate CGA, since defined domains and variables contained in the CGA (i.e., LOS, lower albumin and systolic blood pressure, poor renal function, and greater comorbidity burden), when combined altogether, may offer a valid tool to identify the most fragile patients with clinical and functional impairment enhancing their risk of unplanned early and late readmission.
Collapse
Affiliation(s)
- Arianna Bortolani
- Section of Geriatric Medicine, Department of Surgery, Dentistry, Pediatric and Gynecology, University of Verona, 37126, Verona, Italy.
| | - Francesco Fantin
- Section of Geriatric Medicine, Centre for Medical Sciences - CISMed, Department of Psychology and Cognitive Science, University of Trento, Rovereto (TN), Italy
| | - Anna Giani
- Section of Geriatric Medicine, Department of Surgery, Dentistry, Pediatric and Gynecology, University of Verona, 37126, Verona, Italy
| | - Alessandra Zivelonghi
- Section of Geriatric Medicine, Department of Surgery, Dentistry, Pediatric and Gynecology, University of Verona, 37126, Verona, Italy
| | - Bruno Pernice
- Section of Geriatric Medicine, Department of Surgery, Dentistry, Pediatric and Gynecology, University of Verona, 37126, Verona, Italy
| | - Elena Bortolazzi
- Section of Geriatric Medicine, Department of Surgery, Dentistry, Pediatric and Gynecology, University of Verona, 37126, Verona, Italy
| | - Silvia Urbani
- Section of Geriatric Medicine, Department of Surgery, Dentistry, Pediatric and Gynecology, University of Verona, 37126, Verona, Italy
| | - Elena Zoico
- Section of Geriatric Medicine, Department of Medicine, University of Verona, Verona, Italy
| | - Rocco Micciolo
- Centre for Medical Sciences, Department of Psychology and Cognitive Sciences, University of Trento, Trento, Italy
| | - Mauro Zamboni
- Section of Geriatric Medicine, Department of Surgery, Dentistry, Pediatric and Gynecology, University of Verona, 37126, Verona, Italy
| |
Collapse
|
3
|
Ruiz Ramos J, Alquézar-Arbé A, Juanes Borrego A, Burillo Putze G, Aguiló S, Jacob J, Fernández C, Llorens P, Quero Espinosa FDB, Gordo Remartinez S, Hernando González R, Moreno Martín M, Sánchez Aroca S, Sara Knabe A, González González R, Carrión Fernández M, Artieda Larrañaga A, Adroher Muñoz M, Hong Cho JU, Escolar Martínez Berganza MT, Gayoso Martín S, Sánchez Sindín G, Silva Penas M, Gómez y Gómez B, Arenos Sambro R, González del Castillo J, Miró Ò. Short-term prognosis of polypharmacy in elderly patients treated in emergency departments: results from the EDEN project. Ther Adv Drug Saf 2024; 15:20420986241228129. [PMID: 38323189 PMCID: PMC10846059 DOI: 10.1177/20420986241228129] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2023] [Accepted: 01/06/2024] [Indexed: 02/08/2024] Open
Abstract
Background Polypharmacy is a growing phenomenon among elderly individuals. However, there is little information about the frequency of polypharmacy among the elderly population treated in emergency departments (EDs) and its prognostic effect. This study aims to determine the prevalence and short-term prognostic effect of polypharmacy in elderly patients treated in EDs. Methods A retrospective analysis of the Emergency Department Elderly in Needs (EDEN) project's cohort was performed. This registry included all elderly patients who attended 52 Spanish EDs for any condition. Mild and severe polypharmacy was defined as the use of 5-9 drugs and ⩾10 drugs, respectively. The assessed outcomes were ED revisits, hospital readmissions, and mortality 30 days after discharge. Crude and adjusted logistic regression analyses, including the patient's comorbidities, were performed. Results A total of 25,557 patients were evaluated [mean age: 78 (IQR: 71-84) years]; 10,534 (41.2%) and 5678 (22.2%) patients presented with mild and severe polypharmacy, respectively. In the adjusted analysis, mild polypharmacy and severe polypharmacy were associated with an increase in ED revisits [odds ratio (OR) 1.13 (95% confidence interval (CI): 1.04-1.23) and 1.38 (95% CI: 1.24-1.51)] and hospital readmissions [OR 1.18 (95% CI: 1.04-1.35) and 1.36 (95% CI: 1.16-1.60)], respectively, compared to non-polypharmacy. Mild and severe polypharmacy were not associated with increased 30-day mortality [OR 1.05 (95% CI: 0.89-2.26) and OR 0.89 (95% CI: 0.72-1.12)], respectively. Conclusion Polypharmacy was common among the elderly treated in EDs and associated with increased risks of ED revisits and hospital readmissions ⩽30 days but not with an increased risk of 30-day mortality. Patients with polypharmacy had a higher risk of ED revisits and hospital readmissions ⩽30 days after discharge.
Collapse
Affiliation(s)
- Jesus Ruiz Ramos
- Pharmacy Department, Hospital de la Santa Creu I Sant Pau, Institut de Recerca Sant Pau (IR SANT PAU), C/San Quintin 56-58, Barcelona 08025, Spain
| | - Aitor Alquézar-Arbé
- Emergency Department, Hospital de la Santa Creu I Sant Pau, Institut de Recerca Sant Pau (IR SANT PAU), Barcelona, Spain
| | - Ana Juanes Borrego
- Pharmacy Department, Hospital de la Santa Creu I Sant Pau, Institut de Recerca Sant Pau (IR SANT PAU), Barcelona, Spain
| | - Guillermo Burillo Putze
- Facultad de Ciencias de la Salud, Universidad Europea de Canarias, Santa Cruz de Tenerife, Spain
| | - Sira Aguiló
- Emergency Department, Hospital Clínic, IDIBAPS, University of Barcelona, Barcelona, Spain
| | - Javier Jacob
- Emergency Department, Hospital Universitari de Bellvitge, l’Hospitalet de Llobregat, Spain
| | - Cesáreo Fernández
- Emergency Department, Hospital Clínico San Carlos, IDISSC, Universidad Complutense, Madrid, Spain
| | - Pere Llorens
- Emergency Department, Hospital Doctor Balmis, Instituto de Investigación Sanitaria y Biómedica de Alicante (ISABIAL), Universidad Miguel Hernández, Alicante, Spain
| | | | | | | | | | - Sara Sánchez Aroca
- Emergency Department, Hospital Universitario Morales Meseguer, Murcia, Spain
| | | | | | | | | | | | | | | | - Sara Gayoso Martín
- Emergency Department, Hospital Comarcal El Escorial, San Lorenzo de El Escorial, Spain
| | | | | | | | | | | | - Òscar Miró
- Emergency Department, Hospital Clínic, IDIBAPS, University of Barcelona, Barcelona, Spain
| |
Collapse
|