SBIR Phase I: Medical Device for Monitoring Respiratory Disease

这项小企业创新研究（SBIR）一期项目的更广泛影响/商业潜力将是一种新型可穿戴设备，用于不引人注目地检测慢性呼吸系统疾病患者肺部健康的变化。这种被动式无干扰肺功能监测仪（PULMO）将是唯一一种可以自动测量患者肺部健康信息的设备，无需临床医生的任何积极参与，也不会对患者的日常生活造成任何干扰。PULMO可广泛应用于呼吸系统疾病，如肺移植术后护理、哮喘管理和呼吸治疗研究，这些需要持续、客观和不显眼地监测肺功能变化。由于PULMO技术与低成本微控制器兼容，它有可能主导肺活量测市场和呼吸临床试验领域的大批量生产。肺活量测定市场预计从2018年到2025年的复合年增长率为9.4%，到2025年市场价值将达到14亿美元，而新的呼吸治疗药物的临床试验支出预计将在2025年达到17亿美元。这项小企业创新研究（SBIR）第一阶段项目解决了目前最先进的呼吸系统疾病持续监测的主要缺点，即它需要患者的日常纪律、努力和适当的技术，从而导致数据丢失、无效或伪造。在本项目中，将采用智能事件检测单元结合低功耗微控制器实现制造的PULMO测试装置，总平均功耗低于300微瓦。PULMO的测量误差将在+/- 5%以内，这对于检测肺损伤的变化是必要的。智能事件检测单元将作为非线性动态系统在定制集成电路中实现。一个针对嵌入式低资源系统优化的门控递归神经网络将在低功耗微控制器中实现，并将用于检测呼吸系统疾病症状。将使用硅胶假体胸进行控制试验，以评估PULMO装置的测量精度。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project will be a novel wearable device for unobtrusively detecting changes in the lung health of patients with chronic respiratory disease. This Passive Unobtrusive Lung function Monitor (PULMO) will be the only device that can automatically measure a patient's lung health information without requiring any active engagement from the clinician, and without imposing any obtrusive changes to the patient's daily routine. The PULMO is useful in a broad range of respiratory disease applications, such as lung transplant post-operative care, asthma management and respiratory therapy research, that require continuous, objective and unobtrusive monitoring of lung function change. Since PULMO technology is compatible with low-cost microcontrollers, it has the potential to dominate the spirometry market and respiratory clinical trials space with high-volume production. The spirometry market has an expected CAGR of 9.4 % from 2018 to 2025, reaching a $1.4 billion market value by 2025, while clinical trials expenditures on new respiratory therapy drugs is forecast to reach $1.7 billion in 2025.This Small Business Innovation Research (SBIR) Phase I project addresses the major drawback of the state-of-the-art in continuous monitoring of respiratory disease, which is that it demands daily discipline, effort and proper technique of the patient, resulting in missing, invalid or fabricated data. In this project, a manufactured PULMO test device will be implemented with an intelligent event detection unit combined with a low power microcontroller, and the total average power consumption will be less than 300 microWatts. The measurement error of the PULMO will be within +/- 5 %, which is necessary for detecting changes in lung impairment. The intelligent event detection unit will be implemented as a nonlinear dynamical system in a custom integrated circuit. A gated recurrent neural network that is optimized for embedded low resource systems will be implemented in the low power microcontroller and will be used to detect respiratory disease symptoms. Controlled tests will be performed with a silicone phantom chest to evaluate the measurement accuracy of the PULMO device.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.