College of Nursing, Chungnam National University, Daejeon, South Korea.
Department of Biobehavioral Nursing Science, University of Florida, Gainesville, Florida, USA.
J Adv Nurs. 2023 Feb;79(2):641-651. doi: 10.1111/jan.15549. Epub 2022 Dec 19.
AIMS: The aim of this study was to develop a predictive model that can identify the suicidal ideation risk group among older adults in rural areas using machine learning methods. DESIGN: This study applied an exploratory, descriptive and cross-sectional design. METHODS: The participants were older adults (N = 650) aged over 65 living in rural areas of South Korea. Self-report questionnaires were used to collect the demographics, suicidal ideation, depression, socioeconomic information and basic health information from September to October 2020. The collected data were analysed using machine learning methods with R statistical software 4.1.0. RESULTS: The predictive models indicated that depression, pain, age and loneliness were significant factors of suicidal ideation. Good performance was observed based on the area under the receiver operating characteristic curve in the decision tree, random forest and logistic regression. Finally, the evaluation of model performance indicated moderate to high sensitivity and specificity. CONCLUSION: The predictive models using machine learning methods may be useful to predict the risk of suicidal ideation. Furthermore, depression with pain, age and feelings of loneliness should be included in the initial screening to assess suicide risk among older adults in rural areas. IMPACT: Identifying suicidal risk among older adults is challenging. Thus, employing predictive models that can assess depression, pain, age and loneliness can enable public healthcare providers to detect suicidal risk groups. Particularly, the presented models from this study can facilitate healthcare providers with initiating early interventions to prevent suicide among older adults in clinical and community nursing care settings. REPORTING METHOD: The reporting of this study (Observational, cross-sectional study) conforms to the STROBE statement. PATIENT OR PUBLIC CONTRIBUTION: No patient or public contribution. This study did not involve patients, service users, caregivers or members of the public. IMPLICATION FOR THE PROFESSION AND/OR PATIENTS CARE: Applying this model may help to prevent geriatric suicide because the nursing staff will have a greater awareness regarding the suicide ideation risk of older adults, thereby reducing the possibility of their suicide.
目的：本研究旨在应用机器学习方法，为农村老年人创建一个能够识别自杀意念风险人群的预测模型。
设计：本研究采用了探索性、描述性和横断面设计。
方法：参与者为韩国农村地区 65 岁以上的老年人（N=650）。2020 年 9 月至 10 月，使用自报问卷收集人口统计学资料、自杀意念、抑郁、社会经济信息和基本健康信息。使用 R 统计软件 4.1.0 分析收集的数据。
结果：预测模型表明，抑郁、疼痛、年龄和孤独感是自杀意念的重要因素。决策树、随机森林和逻辑回归的接收者操作特征曲线下面积显示出良好的性能。最终，模型性能的评估表明具有中度到高度的敏感性和特异性。
结论：应用机器学习方法的预测模型可能有助于预测自杀意念的风险。此外，应在初始筛查中纳入伴有疼痛的抑郁、年龄和孤独感，以评估农村老年人的自杀风险。
意义：识别老年人的自杀风险具有挑战性。因此，使用能够评估抑郁、疼痛、年龄和孤独感的预测模型可以使公共卫生保健提供者能够识别自杀风险人群。特别是，本研究提出的模型可以为临床和社区护理环境中的卫生保健提供者提供便利，以启动早期干预措施，预防老年人自杀。
报告方法：本研究的报告（观察性、横断面研究）符合 STROBE 声明。
患者或公众贡献：本研究未涉及患者、服务使用者、护理人员或公众。
对专业人员和/或患者护理的影响：应用该模型有助于预防老年自杀，因为护理人员会更加了解老年人自杀意念的风险，从而降低其自杀的可能性。
BMC Public Health. 2017-6-15
PLOS Digit Health. 2024-8-23
Zotero 插件