Artificial Intelligence in Medicine and Dentistry: Transforming Research into Clinical Impact
Artificial Intelligence (AI) is revolutionizing medicine and dentistry, driving advancements that enhance clinical decision-making, optimize workflows, and improve patient outcomes. This presentation explores AI’s impact in two key areas: medical image segmentation and early Parkinson’s disease (PD...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca
2025-05-01
|
| Series: | Applied Medical Informatics |
| Subjects: | |
| Online Access: | https://ami.info.umfcluj.ro/index.php/AMI/article/view/1206 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850218524154265600 |
|---|---|
| author | Robert ILEŞAN Paul FARAGO |
| author_facet | Robert ILEŞAN Paul FARAGO |
| author_sort | Robert ILEŞAN |
| collection | DOAJ |
| description |
Artificial Intelligence (AI) is revolutionizing medicine and dentistry, driving advancements that enhance clinical decision-making, optimize workflows, and improve patient outcomes. This presentation explores AI’s impact in two key areas: medical image segmentation and early Parkinson’s disease (PD) detection.
Medical image segmentation remains a crucial yet labor-intensive process, traditionally requiring expert input. The advent of convolutional neural networks (CNNs) has enabled fully automated segmentation. In one of our projects, we developed an in-house segmentation software and benchmarked it against commercial cloud-based solutions, an inexperienced user, and an expert as the ground truth. While established solutions demonstrated high accuracy (Dice similarity coefficient: 0.912–0.949) with segmentation times ranging from 3′54″ to 85′54″, our model achieved 94.24% accuracy with the shortest mean segmentation time of 2′03″. This collaboration between academia and industry highlighted challenges in clinical implementation and the need for ongoing refinement.
In neurology, AI facilitates early PD detection through speech and handwriting analysis. Parkinson’s disease, the fastest-growing neurological disorder, presents significant socio-economic challenges, with cases projected to double by 2040. Our transdisciplinary studies leveraged AI models to analyze biomarkers from biosensors, such as running speech and continuous handwriting, revealing distinct patterns between PD patients and controls. One of our CNN-based models, ParkinsonNet, achieved predictive accuracy with F1 scores of 95.74% (speech) and 96.72% (handwriting), demonstrating the potential of AI-driven biomarkers for early diagnosis.
These case studies illustrate AI’s transformative role in medicine and dentistry, emphasizing the need for interdisciplinary collaboration to ensure seamless clinical integration. Further research and validation will be essential to fully harness AI’s potential through decision support systems (DSS), maintaining ethical medical principles.
|
| format | Article |
| id | doaj-art-3f8c6c71167d4c529e7753dd3c6f183a |
| institution | OA Journals |
| issn | 2067-7855 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca |
| record_format | Article |
| series | Applied Medical Informatics |
| spelling | doaj-art-3f8c6c71167d4c529e7753dd3c6f183a2025-08-20T02:07:41ZengIuliu Hatieganu University of Medicine and Pharmacy, Cluj-NapocaApplied Medical Informatics2067-78552025-05-0147Suppl. 1Artificial Intelligence in Medicine and Dentistry: Transforming Research into Clinical ImpactRobert ILEŞAN0Paul FARAGO1The Oral and Maxillofacial Surgery Clinic Luzerner Kantonsspital, Luzern, SwitzerlandTechnical University of Cluj-Napoca, Bariţiu Str., no. 26-28, 400027 Cluj-Napoca, Romania Artificial Intelligence (AI) is revolutionizing medicine and dentistry, driving advancements that enhance clinical decision-making, optimize workflows, and improve patient outcomes. This presentation explores AI’s impact in two key areas: medical image segmentation and early Parkinson’s disease (PD) detection. Medical image segmentation remains a crucial yet labor-intensive process, traditionally requiring expert input. The advent of convolutional neural networks (CNNs) has enabled fully automated segmentation. In one of our projects, we developed an in-house segmentation software and benchmarked it against commercial cloud-based solutions, an inexperienced user, and an expert as the ground truth. While established solutions demonstrated high accuracy (Dice similarity coefficient: 0.912–0.949) with segmentation times ranging from 3′54″ to 85′54″, our model achieved 94.24% accuracy with the shortest mean segmentation time of 2′03″. This collaboration between academia and industry highlighted challenges in clinical implementation and the need for ongoing refinement. In neurology, AI facilitates early PD detection through speech and handwriting analysis. Parkinson’s disease, the fastest-growing neurological disorder, presents significant socio-economic challenges, with cases projected to double by 2040. Our transdisciplinary studies leveraged AI models to analyze biomarkers from biosensors, such as running speech and continuous handwriting, revealing distinct patterns between PD patients and controls. One of our CNN-based models, ParkinsonNet, achieved predictive accuracy with F1 scores of 95.74% (speech) and 96.72% (handwriting), demonstrating the potential of AI-driven biomarkers for early diagnosis. These case studies illustrate AI’s transformative role in medicine and dentistry, emphasizing the need for interdisciplinary collaboration to ensure seamless clinical integration. Further research and validation will be essential to fully harness AI’s potential through decision support systems (DSS), maintaining ethical medical principles. https://ami.info.umfcluj.ro/index.php/AMI/article/view/1206Artificial Intelligence (AI)Convolutional Neural Networks (CNNs)Decision Support Systems (DSS) |
| spellingShingle | Robert ILEŞAN Paul FARAGO Artificial Intelligence in Medicine and Dentistry: Transforming Research into Clinical Impact Applied Medical Informatics Artificial Intelligence (AI) Convolutional Neural Networks (CNNs) Decision Support Systems (DSS) |
| title | Artificial Intelligence in Medicine and Dentistry: Transforming Research into Clinical Impact |
| title_full | Artificial Intelligence in Medicine and Dentistry: Transforming Research into Clinical Impact |
| title_fullStr | Artificial Intelligence in Medicine and Dentistry: Transforming Research into Clinical Impact |
| title_full_unstemmed | Artificial Intelligence in Medicine and Dentistry: Transforming Research into Clinical Impact |
| title_short | Artificial Intelligence in Medicine and Dentistry: Transforming Research into Clinical Impact |
| title_sort | artificial intelligence in medicine and dentistry transforming research into clinical impact |
| topic | Artificial Intelligence (AI) Convolutional Neural Networks (CNNs) Decision Support Systems (DSS) |
| url | https://ami.info.umfcluj.ro/index.php/AMI/article/view/1206 |
| work_keys_str_mv | AT robertilesan artificialintelligenceinmedicineanddentistrytransformingresearchintoclinicalimpact AT paulfarago artificialintelligenceinmedicineanddentistrytransformingresearchintoclinicalimpact |