Key result
Data binning around missing intervals improves wearable time-series imputation over using the entire dataset.
Why the study?
The performance of methods to impute missing time-series data varies widely depending on data type and correlations, presenting a challenge for wearable tracker datasets.
Does data binning improve the imputation of missing time series data from wearables compared to using the whole dataset?
Does data binning improve the imputation of missing time series data from wearables compared to using the whole dataset?
Using data binned around missing time intervals provides better imputation of missing wearable time-series data than using the entire dataset, particularly with the expectation maximization algorithm.
Binning may aid imputation in wearable studies; leaves open clinical utility and generalizability pending validation.
The presence of missing values in a time-series dataset is a very common and well-known problem. Various statistical and machine learning methods have been developed to overcome this problem, with the aim of filling in the missing values in the data. However, the performances of these methods vary widely, showing a high dependence on the type of data and correlations within the data. In our study, we performed some of the well-known imputation methods, such as expectation maximization, k-nearest neighbor, iterative imputer, random forest, and simple imputer, to impute missing data obtained from smart, wearable health trackers. In this manuscript, we proposed the use of data binning for imputation. We showed that the use of data binned around the missing time interval provides a better imputation than the use of a whole dataset. Imputation was performed for 15 min and 1 h of continuous missing data. We used a dataset with different bin sizes, such as 15 min, 30 min, 45 min, and 1 h, and we carried out evaluations using root mean square error (RMSE) values. We observed that the expectation maximization algorithm worked best for the use of binned data. This was followed by the simple imputer, iterative imputer, and k-nearest neighbor, whereas the random forest method had no effect on data binning during imputation. Moreover, the smallest bin sizes of 15 min and 1 h were observed to provide the lowest RMSE values for the majority of the time frames during the imputation of 15 min and 1 h of missing data, respectively. Although applicable to digital health data, we think that this method will also find applicability in other domains.
No takes yet. Share an insight, caveat, or question.
Chakrabarti et al. (2023) studied Missing time series data from wearables. Data binning for imputation vs. Whole dataset imputation was evaluated on Root mean square error (RMSE). Data binning around missing time intervals provided better imputation with lower RMSE for wearable time-series data compared to using the whole dataset, especially using expectation maximization.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: