Risk modeling and shared decision making for postpartum depression

产后抑郁症的风险建模和共同决策

• 批准号: 10454932
• 负责人: Michael B. Laskoff
• 金额: $ 43.43万
• 依托单位: IRIS OB HEALTH INC.
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-21 至 2024-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10454932
• 关键词: Address; Affect; Area; Businesses; Child; Childbirth; Clinical; Clinical Data; Complex; Conceptions; Conflict (Psychology); Data; Decision Aid; Depression screen; Development; Diagnosis; Discipline of obstetrics; Electronic Health Record; Evaluation; Evidence based intervention; Family; Feeling; Feeling hopeless; Funding; Future; Goals; Group Health Insurance; Gynecology; Health; Health Insurance; Health Personnel; Health Professional; Health Sciences; Health Services Accessibility; Impairment; Infant Mortality; Intervention; Iris; Lead; Licensing; Life; Machine Learning; Medicine; Mental Depression; Mental Health; Methods; Mission; Modeling; Mothers; Natural Language Processing; New York City; Outcome; Patient risk; Patient-Focused Outcomes; Patients; Phase; Postpartum Depression; Postpartum Period; Pregnancy; Pregnant Women; Prevention strategy; Preventive treatment; Primary Prevention; Process; Provider; Psychiatry; Research; Risk; Secondary Prevention; Site; Small Business Technology Transfer Research; Stress; Symptoms; Techniques; Testing; Woman; child bearing; clinical care; clinical research site; commercialization; deep learning; depression prevention; depressive symptoms; digital; digital health; disability; effectiveness clinical trial; evidence base; experience; heuristics; high risk; hospitalization rates; improved; machine learning algorithm; motherhood; novel; patient stratification; phase 1 study; population health; practice setting; project-based learning; prospective; risk prediction model; routine screening; screening; shared decision making; social stigma; software as a service; support tools; tool; treatment choice; usability; user centered design

PROJECT ABSTRACT Postpartum depression (PPD) is a strikingly common and potentially life-threatening mental health condition, affecting 1 in 5 mothers in the US. PPD poses serious health concerns, not only to mothers but also their children and the family. PPD has been associated with increased infant mortality, higher rates of hospitalizations, impaired mother-child attachment, developmental problems in children, and increased stress within families. However, in reality, women who are at high risk for depression during the childbearing years are usually neither identified nor treated. In addition, even when depression is detected by health professionals, women rarely obtain assistance, despite the wide availability of treatment choices. In this project, we plan to leverage large-scale, integrated electronic health record and claims from the New York City Clinical Data Research Network to develop automated, scalable risk prediction models for PPD. We will also develop a digital shared decision-making (SDM) tool for PPD treatment by working collaboratively with healthcare providers and patients. The PPD risk model and the digital SDM tool for PPD treatment developed in this STTR Phase I project will be used to conduct a future large, prospective, multi-site clinical effectiveness trial to test their feasibility and utility in routine clinical care of women during the postpartum period.

项目摘要 产后抑郁症（PPD）是一种非常普遍的，潜在的威胁生命的心理健康状况， 在美国影响五分之一的母亲。 PPD不仅对母亲，而且对孩子提出了严重的健康问题 和家人。 PPD与婴儿死亡率升高，住院率更高有关， 母子的依恋受损，儿童的发育问题以及家庭内部的压力增加。 但是，实际上，在育儿年中患抑郁症的高风险通常都不是 确定或处理。此外，即使卫生专业人员发现抑郁症，妇女也很少获得 尽管有广泛的治疗选择，但协助。在这个项目中，我们计划利用大规模的 综合电子健康记录和纽约市临床数据研究网络的主张 PPD的自动化，可扩展的风险预测模型。我们还将制定数字共享决策（SDM） 通过与医疗保健提供者和患者合作，用于PPD治疗的工具。 PPD风险模型 在此STTR I期项目中开发的用于PPD处理的数字SDM工具将用于进行 未来的大型，前瞻性，多站点的临床有效性试验，以测试其在常规临床中的可行性和效用 产后照顾妇女。