Applications of AI and Wearable Biosensors in Precision, Personalized and Predictive Medicine

A special issue of Biosensors (ISSN 2079-6374). This special issue belongs to the section "Biosensors and Healthcare".

Deadline for manuscript submissions: closed (31 October 2023) | Viewed by 13781

Special Issue Editors


E-Mail Website
Guest Editor
Institute of Computer Science of the Romanian Academy, Iasi Branch, 700481 Iasi, Romania
Interests: biosignal processing; biomedical image processing; artificial intelligence (neural networks, fuzzy systems, bio-inspired algorithms); (bio)sensors/transducers; e-health and telemedicine; assistive technologies
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Science and Technology, Nottingham Trent University, Nottingham NG11 8NS, UK
Interests: signal processing; biomedical signal processing; machine learning; body sensor networking
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Institute of Computer Science of the Romanian Academy, Iasi Branch, 700481 Iasi, Romania
Interests: video analysis; human motion analysis with applications in medical recovery; Nature-inspired optimization algorithms; geographic information systems; image processing; image fusion; multispectral; remote sensing; biomedical images

Special Issue Information

Dear Colleagues,

Today’s healthcare benefits from advances in technology to discover, diagnose, and predict diseases, which were hardly possible in the past. Genome sequencing, the diagnosis of psychosis in neonates and predicting psychological abnormalities in adulthood, the use of robots for surgery, injecting bubbles for low-hazard cancer treatment, and stimulating peripheral nerves for rehabilitation using AI and biosignal processing are only a few examples. In addition, the development of new bio- and bio-compatible sensors, together with large archives and high-performance computing, make it possible to incorporate the patient history and their multimodal data for their precise diagnosis and more accurately planning for their treatment. These advances make personalized medicine, as the major goal in current healthcare, thoroughly achievable. 

Precision medicine is an approach of modern medicine that uses information about a person’s genes, proteins, or clinical information to prevent, diagnose, or treat their disease. Thus, precision medicine is an evolving healthcare branch focused on tailoring medical decisions, treatments, practices, and products to individual patients based on their genetic, environmental, lifestyle, and other factors. AI is expected to help realize the promise of precision medicine in three major areas: (1) disease prevention, (2) personalized diagnosis, and (3) personalized treatment. It is expected that AI technologies, if applied openly, fairly, robustly, and in close relation to human intelligence, will open new doors for effective and personalized healthcare worldwide. In this respect, salient topics include the AI-aided diagnosis and early detection of diseases; AI-enhanced treatment and delivery; applications of wearable and implantable biosensor technologies for precision and personalized medicine; clinical decision support with AI techniques; enhancing patient care via AI applications; radiomics and quantitative imaging; bioinformatics for more effective healthcare; and innovative AI applications for patient safety.

Another branch of research is enabled by the development of high-throughput, data-intensive biomedical research assays and technologies such as DNA sequencing, imaging protocols, and wireless health monitoring biosensors and devices, which has created a need for researchers to develop strategies for analyzing, integrating and interpreting the massive amounts of data they generate. The application of data-intensive biomedical technologies in research studies has revealed that humans vary widely at the genetic, biochemical, physiological, exposure and behavioral levels, especially with respect to disease variability and treatment responsiveness. This suggests that there is often a need to tailor or personalize, medicines to the nuanced and often unique features possessed by individual patients. This personalization often goes together with the above presented precision medicine, and seldom is any distinction made between them.

The so-called predictive medicine entails predicting the probability of disease and institutes preventive measures (by means of proteomics, cytomics or screening procedures which allow for the early detection of disease) in order to either prevent the disease altogether or significantly decrease its impact upon the patient, such as by preventing mortality or limiting morbidity. Often these preventive actions are also provided by wearable or implantable biosensors attached to the patient’s body.

These three approaches of modern medicine are parts of the so called “5P medicine”. The other “P medicines” are participatory and purpose-driven approaches. Therefore, the AI used in healthcare and big data technologies are prominent tools that help modern medicine to provide high-quality and personalized healthcare.

Prof. Dr. Hariton-Nicolae Costin
Prof. Dr. Saeid Sanei
Dr. Silviu-Ioan Bejinariu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Biosensors is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • wearable biosensors
  • artificial intelligence
  • biosignal and image processing
  • multimodal data processing
  • precision, personalized and predictive medicine
  • high-performance computing

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

15 pages, 1637 KiB  
Article
Wearable Movement Exploration Device with Machine Learning Algorithm for Screening and Tracking Diabetic Neuropathy—A Cross-Sectional, Diagnostic, Comparative Study
by Goran Radunovic, Zoran Velickovic, Slavica Pavlov-Dolijanovic, Sasa Janjic, Biljana Stojic, Irena Jeftovic Velkova, Nikola Suljagic and Ivan Soldatovic
Biosensors 2024, 14(4), 166; https://doi.org/10.3390/bios14040166 - 29 Mar 2024
Viewed by 1005
Abstract
Background: Diabetic neuropathy is one of the most common complications of diabetes mellitus. The aim of this study is to evaluate the Moveo device, a novel device that uses a machine learning (ML) algorithm to detect and track diabetic neuropathy. The Moveo device [...] Read more.
Background: Diabetic neuropathy is one of the most common complications of diabetes mellitus. The aim of this study is to evaluate the Moveo device, a novel device that uses a machine learning (ML) algorithm to detect and track diabetic neuropathy. The Moveo device comprises 4 sensors positioned on the back of the hands and feet accompanied by a mobile application that gathers data and ML algorithms that are hosted on a cloud platform. The sensors measure movement signals, which are then transferred to the cloud through the mobile application. The cloud triggers a pipeline for feature extraction and subsequently feeds the ML model with these extracted features. Methods: The pilot study included 23 participants. Eleven patients with diabetes and suspected diabetic neuropathy were included in the experimental group. In the control group, 8 patients had suspected radiculopathy, and 4 participants were healthy. All participants underwent an electrodiagnostic examination (EDx) and a Moveo examination, which consists of sensors placed on the feet and back of the participant’s hands and use of the mobile application. The participant performs six tests that are part of a standard neurological examination, and a ML algorithm calculates the probability of diabetic neuropathy. A user experience questionnaire was used to compare participant experiences with regard to both methods. Results: The total accuracy of the algorithm is 82.1%, with 78% sensitivity and 87% specificity. A high linear correlation up to 0.722 was observed between Moveo and EDx features, which underpins the model’s adequacy. The user experience questionnaire revealed that the majority of patients preferred the less painful method. Conclusions: Moveo represents an accurate, easy-to-use device suitable for home environments, showing promising results and potential for future usage. Full article
Show Figures

Figure 1

16 pages, 4655 KiB  
Article
A Smartphone-Based sEMG Signal Analysis System for Human Action Recognition
by Shixin Yu, Hang Zhan, Xingwang Lian, Sze Shin Low, Yifei Xu, Jiangyong Li, Yan Zhang, Xiaojun Sun and Jingjing Liu
Biosensors 2023, 13(8), 805; https://doi.org/10.3390/bios13080805 - 11 Aug 2023
Cited by 1 | Viewed by 1103
Abstract
In lower-limb rehabilitation, human action recognition (HAR) technology can be introduced to analyze the surface electromyography (sEMG) signal generated by movements, which can provide an objective and accurate evaluation of the patient’s action. To balance the long cycle required for rehabilitation and the [...] Read more.
In lower-limb rehabilitation, human action recognition (HAR) technology can be introduced to analyze the surface electromyography (sEMG) signal generated by movements, which can provide an objective and accurate evaluation of the patient’s action. To balance the long cycle required for rehabilitation and the inconvenient factors brought by wearing sEMG devices, a portable sEMG signal acquisition device was developed that can be used under daily scenarios. Additionally, a mobile application was developed to meet the demand for real-time monitoring and analysis of sEMG signals. This application can monitor data in real time and has functions such as plotting, filtering, storage, and action capture and recognition. To build the dataset required for the recognition model, six lower-limb motions were developed for rehabilitation (kick, toe off, heel off, toe off and heel up, step back and kick, and full gait). The sEMG segment and action label were combined for training a convolutional neural network (CNN) to achieve high-precision recognition performance for human lower-limb actions (with a maximum accuracy of 97.96% and recognition accuracy for all actions reaching over 97%). The results show that the smartphone-based sEMG analysis system proposed in this paper can provide reliable information for the clinical evaluation of lower-limb rehabilitation. Full article
Show Figures

Figure 1

14 pages, 2235 KiB  
Article
Early Screening of Colorectal Precancerous Lesions Based on Combined Measurement of Multiple Serum Tumor Markers Using Artificial Neural Network Analysis
by Xing Ke, Wenxue Liu, Lisong Shen, Yue Zhang, Wei Liu, Chaofu Wang and Xu Wang
Biosensors 2023, 13(7), 685; https://doi.org/10.3390/bios13070685 - 27 Jun 2023
Cited by 1 | Viewed by 1170
Abstract
Many patients with colorectal cancer (CRC) are diagnosed in the advanced stage, resulting in delayed treatment and reduced survival time. It is urgent to develop accurate early screening methods for CRC. The purpose of this study is to develop an artificial intelligence (AI)-based [...] Read more.
Many patients with colorectal cancer (CRC) are diagnosed in the advanced stage, resulting in delayed treatment and reduced survival time. It is urgent to develop accurate early screening methods for CRC. The purpose of this study is to develop an artificial intelligence (AI)-based artificial neural network (ANN) model using multiple protein tumor markers to assist in the early diagnosis of CRC and precancerous lesions. In this retrospective analysis, 148 cases with CRC and precancerous diseases were included. The concentrations of multiple protein tumor markers (CEA, CA19-9, CA 125, CYFRA 21-1, CA 72-4, CA 242) were measured by electrochemical luminescence immunoassays. By combining these markers with an ANN algorithm, a diagnosis model (CA6) was developed to distinguish between normal healthy and abnormal subjects, with an AUC of 0.97. The prediction score derived from the CA6 model also performed well in assisting in the diagnosis of precancerous lesions and early CRC (with AUCs of 0.97 and 0.93 and cut-off values of 0.39 and 0.34, respectively), which was better than that of individual protein tumor indicators. The CA6 model established by ANN provides a new and effective method for laboratory auxiliary diagnosis, which might be utilized for early colorectal lesion screening by incorporating more tumor markers with larger sample size. Full article
Show Figures

Figure 1

18 pages, 9921 KiB  
Article
Machine Learning Assisted Wearable Wireless Device for Sleep Apnea Syndrome Diagnosis
by Shaokui Wang, Weipeng Xuan, Ding Chen, Yexin Gu, Fuhai Liu, Jinkai Chen, Shudong Xia, Shurong Dong and Jikui Luo
Biosensors 2023, 13(4), 483; https://doi.org/10.3390/bios13040483 - 17 Apr 2023
Cited by 4 | Viewed by 2266
Abstract
Sleep apnea syndrome (SAS) is a common but underdiagnosed health problem related to impaired quality of life and increased cardiovascular risk. In order to solve the problem of complicated and expensive operation procedures for clinical diagnosis of sleep apnea, here we propose a [...] Read more.
Sleep apnea syndrome (SAS) is a common but underdiagnosed health problem related to impaired quality of life and increased cardiovascular risk. In order to solve the problem of complicated and expensive operation procedures for clinical diagnosis of sleep apnea, here we propose a small and low-cost wearable apnea diagnostic system. The system uses a photoplethysmography (PPG) optical sensor to collect human pulse wave signals and blood oxygen saturation synchronously. Then multiscale entropy and random forest algorithms are used to process the PPG signal for analysis and diagnosis of sleep apnea. The SAS determination is based on the comprehensive diagnosis of the PPG signal and blood oxygen saturation signal, and the blood oxygen is used to exclude the error induced by non-pathological factors. The performance of the system is compared with the Compumedics Grael PSG (Polysomnography) sleep monitoring system. This simple diagnostic system provides a feasible technical solution for portable and low-cost screening and diagnosis of SAS patients with a high accuracy of over 85%. Full article
Show Figures

Figure 1

Review

Jump to: Research

15 pages, 5675 KiB  
Review
Applications of Transistor-Based Biochemical Sensors
by Qiya Gao, Jie Fu, Shuang Li and Dong Ming
Biosensors 2023, 13(4), 469; https://doi.org/10.3390/bios13040469 - 11 Apr 2023
Cited by 5 | Viewed by 3383
Abstract
Transistor-based biochemical sensors feature easy integration with electronic circuits and non-invasive real-time detection. They have been widely used in intelligent wearable devices, electronic skins, and biological analyses and have shown broad application prospects in intelligent medical detection. Field-effect transistor (FET) sensors have high [...] Read more.
Transistor-based biochemical sensors feature easy integration with electronic circuits and non-invasive real-time detection. They have been widely used in intelligent wearable devices, electronic skins, and biological analyses and have shown broad application prospects in intelligent medical detection. Field-effect transistor (FET) sensors have high sensitivity, reasonable specificity, rapid response, and portability and provide unique signal amplification during biochemical detection. Organic field-effect transistor (OFET) sensors are lightweight, flexible, foldable, and biocompatible with wearable devices. Organic electrochemical transistor (OECT) sensors convert biological signals in body fluids into electrical signals for artificial intelligence analysis. In addition to biochemical markers in body fluids, electrophysiology indicators such as electrocardiogram (ECG) signals and body temperature can also cause changes in the current or voltage of transistor-based biochemical sensors. When modified with sensitive substances, sensors can detect specific analytes, improve sensitivity, broaden the detection range, and reduce the limit of detection (LoD). In this review, we introduce three kinds of transistor-based biochemical sensors: FET, OFET, and OECT. We also discuss the fabrication processes for transistor sources, drains, and gates. Furthermore, we demonstrated three sensor types for body fluid biomarkers, electrophysiology signals, and development trends. Transistor-based biochemical sensors exhibit excellent potential in multi-mode intelligent analysis and are good candidates for the next generation of intelligent point-of-care testing (iPOCT). Full article
Show Figures

Figure 1

Back to TopTop