Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Division of Gastroenterology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA 02115, USA; Koch Institute for Integrative Cancer Research, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
Division of Gastroenterology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA 02115, USA; Koch Institute for Integrative Cancer Research, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
J Control Release. 2022 Mar;343:31-42. doi: 10.1016/j.jconrel.2022.01.001. Epub 2022 Jan 6.
Glycemic control through titration of insulin dosing remains the mainstay of diabetes mellitus treatment. Insulin therapy is generally divided into dosing with long- and short-acting insulin, where long-acting insulin provides basal coverage and short-acting insulin supports glycemic excursions associated with eating. The dosing of short-acting insulin often involves several steps for the user including blood glucose measurement and integration of potential carbohydrate loads to inform safe and appropriate dosing. The significant burden placed on the user for blood glucose measurement and effective carbohydrate counting can manifest in substantial effects on adherence. Through the application of computer vision, we have developed a smartphone-based system that is able to detect the carbohydrate load of food by simply taking a single image of the food and converting that information into a required insulin dose by incorporating a blood glucose measurement. Moreover, we report the development of comprehensive all-in-one insulin delivery systems that streamline all operations that peripheral devices require for safe insulin administration, which in turn significantly reduces the complexity and time required for titration of insulin. The development of an autonomous system that supports maximum ease and accuracy of insulin dosing will transform our ability to more effectively support patients with diabetes.
通过调整胰岛素剂量来控制血糖仍然是糖尿病治疗的主要方法。胰岛素治疗通常分为长效和短效胰岛素的剂量，长效胰岛素提供基础覆盖，短效胰岛素则支持与进食相关的血糖波动。短效胰岛素的剂量通常涉及用户的几个步骤，包括血糖测量和潜在碳水化合物负荷的整合，以告知安全和适当的剂量。用户在血糖测量和有效的碳水化合物计数方面的巨大负担可能会对其依从性产生重大影响。通过计算机视觉的应用，我们开发了一种基于智能手机的系统，只需拍摄食物的单张照片，就可以检测食物的碳水化合物负荷，并通过结合血糖测量，将该信息转换为所需的胰岛素剂量。此外，我们还报告了综合一体化胰岛素输送系统的开发，该系统简化了外围设备进行安全胰岛素给药所需的所有操作，从而大大减少了胰岛素滴定所需的复杂性和时间。开发一种支持胰岛素剂量最大程度简便和精确的自主系统，将改变我们为糖尿病患者提供有效支持的能力。
