Theory-Guided Randomized Neural Networks for Decoding Medication-Taking Behavior.
Theory-Guided Randomized Neural Networks for Decoding Medication-Taking Behavior.
复制标题
DOI：
10.1109/bhi50953.2021.9508614
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Gong J
中科院分区：
文献类型：
--
作者：
Kaur N;Gonzales M 4th;Garcia Alcaraz C;Barnes LE;Wells KJ;Gong J
长期内分泌治疗（如他莫昔芬，芳香化酶抑制剂）对预防乳腺癌复发至关重要，但这些药物的依从性很低。为了开发、评估和维持未来的干预措施，可以使用个体水平的建模来了解乳腺癌幸存者服药的行为机制。本文介绍了跨学科的研究，其中采用随机神经网络的模型开发，以预测乳腺癌幸存者的日常服药行为的基础上，他们在三个时间段（基线，4个月，8个月）的调查数据。神经网络结构由心理学和行为经济学中发展起来的随机效用理论指导。对比分析表明，该模型在随机性条件下的预测精度优于现有的计算模型。
Long-term endocrine therapy (e.g. Tamoxifen, aromatase inhibitors) is crucial to prevent breast cancer recurrence, yet rates of adherence to these medications are low. To develop, evaluate, and sustain future interventions, individual-level modeling can be used to understand breast cancer survivors’ behavioral mechanisms of medication-taking. This paper presents interdisciplinary research, wherein a model employing randomized neural networks was developed to predict breast cancer survivors’ daily medication-taking behavior based on their survey data over three time periods (baseline, 4 months, 8 months). The neural network structure was guided by random utility theory developed in psychology and behavioral economics. Comparative analysis indicates that the proposed model outperforms existing computational models in terms of prediction accuracy under conditions of randomness.