Advances in AI Technology in Healthcare
1. Introduction
2. Key Research Contributions
- Assistive technologies for disabilities: Puthu Vedu et al. [1] proposed a new tactile learning tool for visually and hearing-impaired people, which used 3D convolutional neural networks (CNNs) and bidirectional LSTM networks to convert spoken words into Morse code for communication through a wearable device. This tool enhanced the learning experience of deafblind students by offering them a more effective means of communication, which went beyond the traditional tactile methods.
- Health-related quality of life prediction: Abegaz et al. [2] used machine learning algorithms to predict health-related quality of life (HRQOL) based on social determinants of health (SDOH). The study’s findings show that non-medical factors, such as social, educational, and environmental variables, are important in determining overall health outcomes, thus offering a new approach for personalized healthcare that includes a wider range of determinants.
- Surgical instrument recognition: Haider et al. [3] assessed the performance of ChatGPT-4o and other specialized mobile applications for recognizing surgical instruments using large language models (LLMs). It is apparent from their study that while LLMs do effectively classify instruments, they still struggle with subtype distinctions. These findings stress the possibility of using AI-powered technologies to automate surgical instrument control, thus improving patient protection during procedures.
- Coronary artery disease: Wang et al. [4] examined the co-occurrence patterns of comorbidities and diagnoses in patients with coronary artery disease (CAD) through network analysis. They picked up on hypertension as an intermediate node where unstable angina and myocardial infarction often co-occurred with metabolic diseases. There were sex- and age-based differences for which there needs to be individualized treatment, as well as further studies.
- Cervical cancer prediction: ViT-PSO-SVM, a recent method by AlMohimeed et al. [5], integrated vision transformers (ViT) with particle swarm optimization (PSO) and support vector machines (SVM) to detect cervical cancer precisely. This method provides exceptional performance, specifically with respect to cervical cancer classification from image datasets, providing a strong, non-invasive diagnosis tool for early detection.
- Skin disease diagnosis: Malik et al. [6] designed a deep learning-based skin disease diagnosis platform with 87.64% accuracy based on a convolutional neural network (CNN) from dermoscopic images. This platform is a vital breakthrough in dermatology diagnosis when compared to the conventional method, providing a reliable means of offering real-time diagnosis in clinical practice.
- Cost-effective medicine analysis: Machine learning was employed by Long et al. [7] to uncover key drivers for the cost-effectiveness of over-the-counter medicines. According to their study, products that qualify as flexible spending accounts (FSAs) or health savings accounts (HSAs), medicines, products that cure a wider set of symptoms, and products with tiny packaging are seen as more cost-effective. They can assist customers and manufacturers in making better purchasing and marketing decisions based on knowledge when consumers and firms make decisions.
- Ventricular dysfunction detection: Makimoto et al. [8] utilized deep learning models in recognizing ventricular dysfunction from electrocardiograms (ECGs). The test indicates that the artificial intelligence models developed can enhance diagnostics to become more precise, especially when handling two-beat ECGs, thus presenting a superior instrument with which to identify heart diseases and aid clinicians in better decision-making.
- Kidney volume measurement in ADPKD: Hsu et al. [9] applied deep learning models for the precise measurement of total kidney volume (TKV) in patients with autosomal dominant polycystic kidney disease (ADPKD) from MRI scans. The results indicate that medical experts are not as capable as deep learning models, which deliver a reliable, non-invasive method for estimating the level of disease and better patient care.
- Cervical cancer screening using pap smears: Ando et al. [10] proposed an explainable deep learning method for the cervical cancer screening of pap smear images. Their OCC- and VAE-based method discriminates between normal and abnormal cells using unlabeled abnormalities and is thus a strong candidate for use in automated, trustworthy cervical cancer screening.
- AI support for informal caregivers: Borna et al. [11] conducted a systematic review of AI contributions to informal patient caregiving assistance. The findings of their review establish the potential of AI-based applications to minimize caregiver burden, enhance efficiency, and support caregiver health. Regardless of variations in methodology, the studies reviewed consistently indicate that AI can provide adaptive and intelligent support to caregivers.
3. Trends and Insights
4. Challenges and Gaps
5. Future Directions
6. Conclusions
Author Contributions
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Puthu Vedu, S.Z.; Altulyan, M.; Singh, P.K. A Novel Tactile Learning Assistive Tool for the Visually and Hearing Impaired with 3D-CNN and Bidirectional LSTM Leveraging Morse Code Technology. Bioengineering 2025, 12, 253. [Google Scholar] [CrossRef] [PubMed]
- Abegaz, T.M.; Ahmed, M.; Ali, A.A.; Bhagavathula, A.S. Predicting Health-Related Quality of Life Using Social Determinants of Health: A Machine Learning Approach with the All of Us Cohort. Bioengineering 2025, 12, 166. [Google Scholar] [CrossRef] [PubMed]
- Haider, S.A.; Ho, O.A.; Borna, S.; Gomez-Cabello, C.A.; Pressman, S.M.; Cole, D.; Sehgal, A.; Leibovich, B.C.; Forte, A.J. Use of Multimodal Artificial Intelligence in Surgical Instrument Recognition. Bioengineering 2025, 12, 72. [Google Scholar] [CrossRef] [PubMed]
- Wang, J.; Qi, Z.; Liu, X.; Li, X.; Cao, Z.; Zeng, D.D.; Wang, H. Population and Co-Occurrence Characteristics of Diagnoses and Comorbidities in Coronary Artery Disease Patients: A Case Study from a Hospital in Guangxi, China. Bioengineering 2024, 11, 1284. [Google Scholar] [CrossRef] [PubMed]
- Makimoto, H.; Okatani, T.; Suganuma, M.; Kabutoya, T.; Kohro, T.; Agata, Y.; Ogata, Y.; Harada, K.; Llubani, R.; Bejinariu, A. Identifying Ventricular Dysfunction Indicators in Electrocardiograms via Artificial Intelligence-Driven Analysis. Bioengineering 2024, 11, 1069. [Google Scholar] [CrossRef] [PubMed]
- Hsu, J.L.; Singaravelan, A.; Lai, C.Y.; Li, Z.L.; Lin, C.N.; Wu, W.S.; Kao, T.W.; Chu, P.L. Applying a Deep Learning Model for Total Kidney Volume Measurement in Autosomal Dominant Polycystic Kidney Disease. Bioengineering 2024, 11, 963. [Google Scholar] [CrossRef] [PubMed]
- Malik, S.G.; Jamil, S.S.; Aziz, A.; Ullah, S.; Ullah, I.; Abohashrh, M. High-Precision Skin Disease Diagnosis Through Deep Learning on Dermoscopic Images. Bioengineering 2024, 11, 867. [Google Scholar] [CrossRef] [PubMed]
- Long, B.; Zhou, J.; Tan, F.; Bellur, S. Deciphering Factors Contributing to Cost-Effective Medicine Using Machine Learning. Bioengineering 2024, 11, 818. [Google Scholar] [CrossRef] [PubMed]
- AlMohimeed, A.; Shehata, M.; El-Rashidy, N.; Mostafa, S.; Samy Talaat, A.; Saleh, H. ViT-PSO-SVM: Cervical Cancer Prediction Based on Integrating Vision Transformer with Particle Swarm Optimization and Support Vector Machine. Bioengineering 2024, 11, 729. [Google Scholar] [CrossRef] [PubMed]
- Ando, Y.; Cho, J.; Park, N.J.Y.; Ko, S.; Han, H. Toward Interpretable Cell Image Representation and Abnormality Scoring for Cervical Cancer Screening Using Pap Smears. Bioengineering 2024, 11, 567. [Google Scholar] [CrossRef] [PubMed]
- Borna, S.; Maniaci, M.J.; Haider, C.R.; Gomez-Cabello, C.A.; Pressman, S.M.; Haider, S.A.; Demaerschalk, B.M.; Cowart, J.B.; Forte, A.J. Artificial Intelligence Support for Informal Patient Caregivers: A Systematic Review. Bioengineering 2024, 11, 483. [Google Scholar] [CrossRef] [PubMed]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Shehata, M.; Elhosseini, M. Advances in AI Technology in Healthcare. Bioengineering 2025, 12, 506. https://doi.org/10.3390/bioengineering12050506
Shehata M, Elhosseini M. Advances in AI Technology in Healthcare. Bioengineering. 2025; 12(5):506. https://doi.org/10.3390/bioengineering12050506
Chicago/Turabian StyleShehata, Mohamed, and Mostafa Elhosseini. 2025. "Advances in AI Technology in Healthcare" Bioengineering 12, no. 5: 506. https://doi.org/10.3390/bioengineering12050506
APA StyleShehata, M., & Elhosseini, M. (2025). Advances in AI Technology in Healthcare. Bioengineering, 12(5), 506. https://doi.org/10.3390/bioengineering12050506