Search

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. [ABSTRACT FROM AUTHOR]

Blood glucose concentration is important for metabolic homeostasis in humans and animals. Many diabetic patients need to detect blood glucose daily which burdens community hospitals and family healthcare. Optical fiber sensors are widely used in biomedical detection because of their compact structure, fast response, high sensitivity, low cost, and ease of operation. In this work, we constructed a Fabry-Perot (FP) cavity biosensor for the fast detection of glucose concentration in serum. The femtosecond laser micromachining was applied to fabricate the FP cavity by printing the fiber-tip fixed-supported bridge at the end face of the optical fiber. An additional hemisphere was printed at the center of the outer surface of the bridge to avoid multi-beam interference. The results demonstrated that the proposed biosensor had high refractive index (RI) detection sensitivity, roughly 1039 nm/RIU at a wavelength of 1590 nm, and the detection sensitivity for glucose was around 0.185 nm/ (mg/mL) at a wavelength of 1590 nm. Due to its high sensitivity, compact structure, and fast response, the FP cavity biosensor has great potential to be applied in family healthcare for glucose concentration detection of diabetic patients. [ABSTRACT FROM AUTHOR]

Power equipment operates under high voltages, inducing space charge accumulation on the surface of key insulating structures, which increases the risk of discharge/breakdown and the possibility of maintenance workers experiencing electric shock accidents. Hence, a visualized non-equipment space charge detection method is of great demand in the power industry. Typical electrochromic phenomenon is based on redox of the material, triggered by a voltage smaller than 5 V with a continuous current in μA~mA level, which is not applicable to high electric fields above 106 V/m with pA~nA operation current in power equipment. Until now, no naked-eye observation technique has been realized for space charge detection to ensure the operation of power systems as well as the safety of maintenance workers. In this work, a viologen/poly(vinylidene fluoride-co-hexafluoropropylene)(P(VDF–HFP)) composite is investigated from gel to insulating bulk configurations to achieve high-voltage electrical-insulating electrochromism. The results show that viologen/P(VDF–HFP) composite bulk can withstand high electric fields at the 107 V/m level, and its electrochromism is triggered by space charges. This electrochromism phenomenon can be visually extended by increasing viologen content towards 5 wt.% and shows a positive response to voltage amplitude and application duration. As viologen/P(VDF–HFP) composite bulk exhibits a typical electrical insulating performance, it could be attached to the surface of insulating structures or clamped between metal and insulating materials as a space charge accumulation indicator in high-voltage power equipment. [ABSTRACT FROM AUTHOR]

The dynamic time warping (DTW) algorithm is widely used in pattern matching and sequence alignment tasks, including speech recognition and time series clustering. However, DTW algorithms perform poorly when aligning sequences of uneven sampling frequencies. This makes it difficult to apply DTW to practical problems, such as aligning signals that are recorded simultaneously by sensors with different, uneven, and dynamic sampling frequencies. As multi-modal sensing technologies become increasingly popular, it is necessary to develop methods for high quality alignment of such signals. Here we propose a DTW algorithm called EventDTW which uses information propagated from defined events as basis for path matching and hence sequence alignment. We have developed two metrics, the error rate (ER) and the singularity score (SS), to define and evaluate alignment quality and to enable comparison of performance across DTW algorithms. We demonstrate the utility of these metrics on 84 publicly-available signals in addition to our own multi-modal biomedical signals. EventDTW outperformed existing DTW algorithms for optimal alignment of signals with different sampling frequencies in 37% of artificial signal alignment tasks and 76% of real-world signal alignment tasks. [ABSTRACT FROM AUTHOR]