A Systematic Review of Time Series Classification Techniques Used in Biomedical Applications

Abstract

Background: Digital clinical measures collected via various digital sensing technologies such as smartphones, smartwatches, wearables, and ingestible and implantable sensors are increasingly used by individuals and clinicians to capture the health outcomes or behavioral and physiological characteristics of individuals. Time series classification (TSC) is very commonly used for modeling digital clinical measures. While deep learning models for TSC are very common and powerful, there exist some fundamental challenges. This review presents the non-deep learning models that are commonly used for time series classification in biomedical applications that can achieve high performance. Objective: We performed a systematic review to characterize the techniques that are used in time series classification of digital clinical measures throughout all the stages of data processing and model building. Methods: We conducted a literature search on PubMed, as well as the Institute of Electrical and Electronics Engineers (IEEE), Web of Science, and SCOPUS databases using a range of search terms to retrieve peer-reviewed articles that report on the academic research about digital clinical measures from a five-year period between June 2016 and June 2021. We identified and categorized the research studies based on the types of classification algorithms and sensor input types. Results: We found 452 papers in total from four different databases: PubMed, IEEE, Web of Science Database, and SCOPUS. After removing duplicates and irrelevant papers, 135 articles remained for detailed review and data extraction. Among these, engineered features using time series methods that were subsequently fed into widely used machine learning classifiers were the most commonly used technique, and also most frequently achieved the best performance metrics (77 out of 135 articles). Statistical modeling (24 out of 135 articles) algorithms were the second most common and also the second-best classification technique. Conclusions: In this review paper, summaries of the time series classification models and interpretation methods for biomedical applications are summarized and categorized. While high time series classification performance has been achieved in digital clinical, physiological, or biomedical measures, no standard benchmark datasets, modeling methods, or reporting methodology exist. There is no single widely used method for time series model development or feature interpretation, however many different methods have proven successful.

Keywords: digital clinical measures; feature engineering; machine learning; systematic review; time series classification.

Figure 1

(a). Review results and the number of papers through each selection process. (b). Flow chart of the common steps in time series classification techniques found in this review. Raw time series signals usually go through some steps of preprocessing for artifact removal or noise reduction, and then are passed through the modeling stage. The modeling stage can use many different types of algorithms, such as feature engineering and selection, statistical modeling, and distance calculation (Table 1). Classifiers are then tuned, trained, validated, and compared to find the best model for a specific task.

Figure 1

(a). Review results and the number of papers through each selection process. (b). Flow chart of the common steps in time series classification techniques found in this review. Raw time series signals usually go through some steps of preprocessing for artifact removal or noise reduction, and then are passed through the modeling stage. The modeling stage can use many different types of algorithms, such as feature engineering and selection, statistical modeling, and distance calculation (Table 1). Classifiers are then tuned, trained, validated, and compared to find the best model for a specific task.

Figure 2

(a). Numbers of papers found in this review focusing on each different biosignal type specified on the horizontal axis. (b). Conceptual representation of non-deep learning time series classification modeling types. [1,16,17,18,19,20]. (c). Number of articles found for the categories of time series classification methods (horizontal axis) used in biomedical applications.

Figure 2

(a). Numbers of papers found in this review focusing on each different biosignal type specified on the horizontal axis. (b). Conceptual representation of non-deep learning time series classification modeling types. [1,16,17,18,19,20]. (c). Number of articles found for the categories of time series classification methods (horizontal axis) used in biomedical applications.

Figure 2

(a). Numbers of papers found in this review focusing on each different biosignal type specified on the horizontal axis. (b). Conceptual representation of non-deep learning time series classification modeling types. [1,16,17,18,19,20]. (c). Number of articles found for the categories of time series classification methods (horizontal axis) used in biomedical applications.

Figure 3

Percentages of performance metrics reported in studies reviewed.

Figure 4

Illustration of different types of feature engineering techniques [30].