Importance

Despite data aggregation and removal of protected health information, there is concern that deidentified physical activity (PA) data collected from wearable devices can be reidentified. Organizations collecting or distributing such data suggest that the aforementioned measures are sufficient to ensure privacy. However, no studies, to our knowledge, have been published that demonstrate the possibility or impossibility of reidentifying such activity data.

Objective

To evaluate the feasibility of reidentifying accelerometer-measured PA data, which have had geographic and protected health information removed, using support vector machines (SVMs) and random forest methods from machine learning.

Design, setting, and participants

In this cross-sectional study, the National Health and Nutrition Examination Survey (NHANES) 2003-2004 and 2005-2006 data sets were analyzed in 2018. The accelerometer-measured PA data were collected in a free-living setting for 7 continuous days. NHANES uses a multistage probability sampling design to select a sample that is representative of the civilian noninstitutionalized household (both adult and children) population of the United States.

Exposures

The NHANES data sets contain objectively measured movement intensity as recorded by accelerometers worn during all walking for 1 week.

Main outcomes and measures

The primary outcome was the ability of the random forest and linear SVM algorithms to match demographic and 20-minute aggregated PA data to individual-specific record numbers, and the percentage of correct matches by each machine learning algorithm was the measure.

Results

A total of 4720 adults (mean [SD] age, 40.0 [20.6] years) and 2427 children (mean [SD] age, 12.3 [3.4] years) in NHANES 2003-2004 and 4765 adults (mean [SD] age, 45.2 [19.9] years) and 2539 children (mean [SD] age, 12.1 [3.4] years) in NHANES 2005-2006 were included in the study. The random forest algorithm successfully reidentified the demographic and 20-minute aggregated PA data of 4478 adults (94.9%) and 2120 children (87.4%) in NHANES 2003-2004 and 4470 adults (93.8%) and 2172 children (85.5%) in NHANES 2005-2006 (P < .001 for all). The linear SVM algorithm successfully reidentified the demographic and 20-minute aggregated PA data of 4043 adults (85.6%) and 1695 children (69.8%) in NHANES 2003-2004 and 4041 adults (84.8%) and 1705 children (67.2%) in NHANES 2005-2006 (P < .001 for all).

Conclusions and relevance

This study suggests that current practices for deidentification of accelerometer-measured PA data might be insufficient to ensure privacy. This finding has important policy implications because it appears to show the need for deidentification that aggregates the PA data of multiple individuals to ensure privacy for single individuals.

Through next generation sequencing, this study evaluated the circulating tumor DNA (ctDNA) of advanced breast cancer patients to prospectively explore the relationship between specific DNA mutations and prognosis as well as therapeutic decision making. The target region covered 1021 gene totally. Clinical characteristics, treatment and outcome data were collected. We analyzed progression-free survival (PFS) from first-line therapy and overall survival (OS), and found that their endpoints were correlated with observed gene mutations. We enrolled 54 patients, with a median follow-up time of 8 years. Mutations were found in TP53, PIK3CA, and ERBB family, at 40.7%, 35.2%, and 25.9%, respectively. PIK3CA more frequently occurred in the site of 3140 A>G (p.H1047R) for 20.4% and HER2+ diseases, and it was associated with shorter median PFS and worse OS among HER2+ patients [mutant vs. wild type: 4 (range 2-9) vs. 8 (range 2-22) months, P=0.006], and [mutant vs. wild type: 29 (range 12-74) vs. 64 (range 20-96) months, P=0.043], respectively. The patients with mutations in TP53 had shorter OS (median 64 vs. 121 months, P=0.006). Multivariate analysis for HER2+ disease demonstrated that the PIK3CA p.H1047R mutation was the only factor associated with shorter PFS (P=0.025); while the receiver operating characteristic (ROC) analysis produces an area under the curve (AUC) of 0.789. The ctDNA analysis, found PIK3CA p.H1047R mutation was more frequent in HER2+ disease and associated with worse OS. It was also the only mutation associated with shorter PFS through a multivariate analysis of HER2+ patients who were treated with trastuzumab, suggesting trastuzumab had lower activity in these patients. The presence of a TP53 mutation was associated with worse OS.