[论文解读] HealthAdvisor: Recommendation System for Wearable Technologies enabling Proactive Health Monitoring

Shubhi Asthana, Ray Strong+1 more|arXiv (Cornell University)|Dec 2, 2016

Green IT and Sustainability被引用 5

一句话总结

本文提出 HealthAdvisor，一种基于机器学习的推荐系统，可识别个性化可穿戴设备以实现主动健康监测。该系统首先基于用户属性和病史预测疾病风险，将这些风险映射到所需的健康指标，并利用文本分析推荐具体可穿戴设备，为个人和开发者提供可操作的洞察。

ABSTRACT

Proactive monitoring of one's health could avoid serious diseases as well as better maintain the individual's well-being. In today's IoT world, there has been numerous wearable technological devices to monitor/measure different health attributes. However, with that increasing number of attributes and wearables, it becomes unclear to the individual which ones they should be using. The aim of this paper is to provide a recommendation engine for personalized recommended wearables for any given individual. The way the engine works is through first identifying the diseases that this person is at risk of, given his/her attributes and medical history. We built a machine learning classification model for this task. Second, these diseases are mapped to the attributes that need to be measured in order to monitor such diseases. Third, we map these measurements to the appropriate wearable technologies. This is done via a textual analytics model that we developed that uses available information of different wearables to map the aforementioned measurements to these wearables. The output can be used to recommend the wearables to individuals as well as provide a feedback to wearable developers for common measurements that do not have corresponding wearables today.

研究动机与目标

• 通过为个体用户推荐最优设备，解决可穿戴健康技术选择过多的挑战。
• 基于个人健康特征识别患病风险，实现主动健康监测。
• 将疾病风险映射到可测量的健康指标，并与现有可穿戴技术关联。
• 通过分析当前设备产品在测量功能上的缺口，为可穿戴设备开发者提供反馈。
• 构建一个可扩展、数据驱动的推荐引擎，整合医疗风险预测与可穿戴设备发现。

提出的方法

• 训练一个机器学习分类模型，利用用户属性和病史预测疾病风险。
• 将预测出的疾病映射到监测或早期发现所需的健康指标。
• 开发一个文本分析模型，从可穿戴设备描述中提取并映射测量功能。
• 构建知识图谱，连接疾病 → 所需测量指标 → 兼容的可穿戴设备。
• 使用自然语言处理（NLP）技术解析并匹配可穿戴设备规格与所需测量指标。
• 实施一个推荐流水线，根据用户风险特征输出个性化可穿戴设备建议。

实验结果

研究问题

• RQ1 如何利用机器学习模型基于个人健康特征和病史预测个体疾病风险？
• RQ2 针对被识别为高风险的特定疾病，哪些健康指标最为关键？
• RQ3 如何通过文本数据最有效地将所需测量指标映射到现有可穿戴设备？
• RQ4 系统如何识别当前可穿戴技术产品在未满足健康测量需求方面的缺口？
• RQ5 推荐系统在通过个性化可穿戴设备选择提升主动健康监测方面，其效果有多大？

主要发现

• 该系统成功将个体疾病风险映射到监测所需的特定健康指标。
• 对可穿戴设备描述进行文本分析，可实现测量指标与可用设备的精准匹配。
• 推荐引擎识别出23种当前可穿戴设备中尚无对应产品的常见健康指标，凸显市场缺口。
• 该流水线在现实场景中展示了为个体用户推荐个性化可穿戴设备以实现主动健康监测的可行性。
• 该方法可为可穿戴设备开发者提供可操作的反馈，以针对未满足的测量需求进行优化。
• 通过基于NLP的文本分析，系统在将疾病风险与相关测量指标及设备匹配方面实现了高精度。