Karol Kalka

Karol Kalka

Auto-generated profile, based on publicly available information

Karol Kalka

Kazimierczak Private Medical Practice, Dworcowa 13/u6a, 85-009 Bydgoszcz, Poland

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
Wojciech KazimierczakWojciech Kazimierczak
Wojciech Kazimierczak
RWRóża Wajer
Róża Wajer
AWAdrian Wajer
Adrian Wajer
KKKarol Kalka
Karol Kalka
NKNatalia Anna Kazimierczak
Natalia Anna Kazimierczak
ZSZbigniew Serafin
Zbigniew Serafin
Background/Objectives: The purpose of this preliminary study was to evaluate the diagnostic performance of an AI-driven platform, Diagnocat (Diagnocat Ltd., San Francisco, CA, USA), for assessing endodontic treatment outcomes using panoramic radiographs (PANs). Materials and Methods: The study included 55 PAN images of 55 patients (15 males and 40 females, aged 12–70) who underwent imaging at a private dental center. All images were acquired using a Hyperion X9 PRO digital cephalometer and were evaluated using Diagnocat, a cloud-based AI platform. The AI system assessed the following endodontic treatment features: filling probability, obturation adequacy, density, overfilling, voids in filling, and short filling. Two human observers independently evaluated the images, and their consensus served as the reference standard. The diagnostic accuracy metrics were calculated. Results: The AI system demonstrated high accuracy (90.72%) and a strong F1 score (95.12%) in detecting the probability of endodontic filling. However, the system showed variable performance in other categories, with lower accuracy metrics and unacceptable F1 scores for short filling and voids in filling assessments (8.33% and 14.29%, respectively). The accuracy for detecting adequate obturation and density was 55.81% and 62.79%, respectively. Conclusions: The AI-based system showed very high accuracy in identifying endodontically treated teeth but exhibited variable diagnostic accuracy for other qualitative features of endodontic treatment.