Recovery Outcome Management System (ROMS)

描述（由申请人提供）：ROMS系统将帮助医疗保健提供者为SPMI和双重诊断的消费者提供高质量，具有成本效益的循证护理。具体来说，ROMS将提供：深度治疗计划：ROMS将为临床医生提供关于消费者优势、功能和症状以及在治疗开始时需要立即注意的关键“体征”或“行为”的可靠信息。治疗管理：根据消费者长期的反应，临床医生将根据预测的病程和住院风险水平评估消费者的进展，以便根据需要改变治疗策略以避免不良后果。随着消费者优势、症状、行为和风险因素数据库的增长，其评估“什么对谁有效”的能力不断完善，为SPMI消费者的治疗创造了第一个“学习系统”。ROMS的设计是为了方便地集成到办公实践中，并提供了许多功能来克服SPMI消费者可靠的自我报告的障碍。消费者及其护理人员使用个人电脑或手持设备（如PDA）完成问卷调查。报告表明消费者的状况和进展立即提供给临床医生。与护理水平和临床风险/严重程度相关的临床医生评级显示在单独的报告中，适合临床病例记录和病例管理人员使用。第二阶段的研究包括收集300名SPMI消费者的纵向数据。分层线性模型将与此数据集一起用于开发用于预测治疗反应和住院风险的算法。

DESCRIPTION (provided by applicant): The ROMS system will help healthcare providers to offer high quality, cost-effective, evidence-based care for SPMI and dually diagnosed consumers. Specifically, ROMS will provide: In depth treatment planning: ROMS will provide clinicians with reliable information on consumer strengths, functioning and symptomology as well as critical "signs" or "behaviors" requiring immediate attention at the beginning of treatment. Treatment management: Based on consumer responses over time, clinicians will evaluate a consumer' s progress in relation to a predicted course and level of risk for hospitalization, so that treatment strategies can be altered as necessary to avoid adverse outcomes. Continual refinement of its ability to evaluate "what works for whom" as its database of consumer strengths, symptoms, behaviors and risk factors grows, creating the first "learning system" for the treatment of SPMI consumers. ROMS is designed for easy integration into office practices, and offers numerous features to overcome obstacles to reliable self-report by SPMI consumers. Consumers and their caregivers complete questionnaires using a PC, or handheld device (e.g., PDA). Reports indicating the consumer's condition and progress are immediately available to clinicians. Clinician ratings relating to level of care and clinical risk/severity are displayed on a separate report, suitable for clinical case documentation and use by case managers. Phase II research includes the collection of longitudinal data from 300 SPMI consumers. Hierarchical linear modeling will be used with this dataset to develop algorithms for the prediction of treatment response and risk for hospitalization.