Estimating personalized diagnostic rules depending on individualized characteristics.

TitleEstimating personalized diagnostic rules depending on individualized characteristics.
Publication TypeJournal Article
Year of Publication2017
AuthorsLiu, Ying, Yuanjia Wang, Chaorui Huang, and Donglin Zeng
JournalStat Med
Volume36
Issue7
Pagination1099-1117
Date Published2017 03 30
ISSN1097-0258
KeywordsBrain, Decision Support Techniques, Diagnosis, Diffusion Tensor Imaging, Humans, Individuality, Machine Learning, Models, Statistical, Parkinson Disease, Positron-Emission Tomography, Precision Medicine, Risk Factors, ROC Curve, Statistics as Topic
Abstract

There is an increasing demand for personalization of disease screening based on assessment of patient risk and other characteristics. For example, in breast cancer screening, advanced imaging technologies have made it possible to move away from 'one-size-fits-all' screening guidelines to targeted risk-based screening for those who are in need. Because diagnostic performance of various imaging modalities may vary across subjects, applying the most accurate modality to the patients who would benefit the most requires personalized strategy. To address these needs, we propose novel machine learning methods to estimate personalized diagnostic rules for medical screening or diagnosis by maximizing a weighted combination of sensitivity and specificity across subgroups of subjects. We first develop methods that can be applied when competing modalities or screening strategies that are observed on the same subject (paired design). Next, we present methods for studies where not all subjects receive both modalities (unpaired design). We study theoretical properties including consistency and risk bound of the personalized diagnostic rules and conduct simulation studies to examine performance of the proposed methods. Lastly, we analyze data collected from a brain imaging study of Parkinson's disease using positron emission tomography and diffusion tensor imaging with paired and unpaired designs. Our results show that in some cases, a personalized modality assignment is estimated to improve empirical area under the receiver operating curve compared with a 'one-size-fits-all' assignment strategy. Copyright © 2016 John Wiley & Sons, Ltd.

DOI10.1002/sim.7182
Alternate JournalStat Med
Original PublicationEstimating personalized diagnostic rules depending on individualized characteristics.
PubMed ID27917508
PubMed Central IDPMC5334177
Grant ListP01 CA142538 / CA / NCI NIH HHS / United States
R01 NS073671 / NS / NINDS NIH HHS / United States
U01 NS082062 / NS / NINDS NIH HHS / United States