Introduction: The aim of this study is to investigate the effect of kinesiotaping on pain scores in patients with rib fractures following isolated thoracic trauma. Materials and Methods: In this randomized prospective study, patients with isolated thoracic trauma and rib fractures were randomized into kinesiotaping and control groups between January 24, 2024, and October 1, 2024. Patients in the control group received standard analgesic treatment. In the kinesiotaping group, kinesiotaping bands were applied in addition to the standard treatment. Pain scores using the visual analog scale (VAS) were recorded at admission, the 24th hour, the 4th day, and the 7th day, and the results were statistically compared. Results: A total of 118 patients were evaluated. Eighty-four patients did not meet the inclusion criteria. The 34 patients included in the study were randomized into kinesiotaping and control groups. The two groups were demographically homogeneous. On the 4th day, the mean VAS score was significantly lower in the kinesiotaping group (2.7 ± 1.2) compared to the control group (4.1 ± 1.9) (p = 0.037). No statistically significant difference in VAS scores was observed on the other days. Conclusion: In patients with rib fractures, pain scores decreased more rapidly in those treated with analgesics plus kinesiotaping compared to those treated with analgesics alone. Trial Registration: ClinicalTrials.gov, NCT06222320. Registered on January 15, 2024.
Background: Pneumothorax (PTX) requires rapid recognition in emergency and critical care. Lung ultrasound (LUS) offers a fast, radiation-free alternative to computed tomography (CT), but its accuracy is limited by operator dependence. Artificial intelligence (AI) may standardize interpretation and improve performance. Methods: This retrospective single-center study included 46 patients (23 with CT-confirmed PTX and 23 controls). Sixty B-mode and M-mode frames per patient were extracted using a Clarius C3 HD3 wireless device, yielding 2760 images. CT served as the diagnostic reference. Experimental studies were conducted within the framework of three scenarios. Transformer-based models, Vision Transformer (ViT) and DINOv2, were trained and tested under two scenarios: random frame split and patient-level split. Also, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) classifiers were trained on the feature maps extracted by using Video Vision Transformer (ViViT) for ultrasound video sequences in Scenario 3. Model performance was evaluated using accuracy, sensitivity, specificity, F1-score, and area under the ROC curve (AUC). Results: Both transformers achieved high diagnostic accuracy, with B-mode images outperforming M-mode inputs in the first two scenarios. In Scenario 1, ViT reached 99.1% accuracy, while DINOv2 achieved 97.3%. In Scenario 2, which avoided data leakage, DINOv2 performed best in the B-mode region (90% accuracy, 80% sensitivity, 100% specificity, F1-score 88.9%). ROC analysis confirmed strong discriminative ability, with AUC values of 0.973 for DINOv2 and 0.964 for ViT on B-mode images. Also, both RF and XGBoost classifiers trained on the ViViT feature maps reached 90% accuracy on the video sequences. Conclusions: AI-assisted LUS substantially improves PTX detection, with transformers—particularly DINOv2—achieving near-expert accuracy. Larger multicenter datasets are required for validation and clinical integration.
30 May 2025 in Journal of Health Sciences and Medicine
Aims: This study aims to evaluate the usefulness and reliability of artificial intelligence (AI) applications in thoracic surgery internship education and exam preparation. Methods: Claude Sonnet 3.7 AI was provided with core topics covered in the 5th-year thoracic surgery internship and was instructed to generate a 20-question multiple-choice exam, including an answer key. Four thoracic surgery specialists assessed the AI-generated questions using the Delphi panel method, classifying them as correct, minor error, or major error. Major errors included the absence of the correct answer among choices, incorrect AI-marked answers, or contradictions with established medical knowledge. A second exam was manually created by a thoracic surgery specialist and evaluated using the same methodology. Seven volunteer 5th-year medical students completed both exams, and the correlation between their scores was statistically analyzed. Results: Among AI-generated questions, 8 (40%) contained major errors, while 1 (5%) had a minor error. The expert-generated exam had a perfect accuracy rate, whereas the AI-generated exam had significantly lower accuracy (p=0.001). Median scores were 75 (67-100) for the AI exam and 85 (70-95) for the expert exam. No significant correlation was found between students’ scores (r=0.042, p=0.929). Conclusion: AI-generated questions had a high error rate (40% major, 5% minor), making them unreliable for unsupervised use in medical education. While AI may provide partial benefits under expert supervision, it currently lacks the accuracy required for independent implementation in thoracic surgery education.
19 December 2023 in Muğla Sıtkı Koçman Üniversitesi Tıp Dergisi
Primary tumors of the chest wall are rare tumors comprising 5% of thoracic neoplasms. The current study was designed to evaluate the effect of histopathological subtype on the 5-year and 10-year overall survival and regional recurrence in primary malignant tumors of the chest wall. From December 2007 to December 2019, the data of 20 patients were analyzed. Overall survival rates, median overall survival, regional tumor recurrence and median disease-free survival rates were compared retrospectively between histopathological subtypes. Chondrosarcoma (n=7), desmoid tumor (n=6), undifferentiated pleomorphic sarcoma [(UPS), (n=4)], Ewing's sarcoma (n=1), malignant peripheral nerve sheath tumor (n=1), and liposarcoma (n=1) were the subtypes identified. A lower median overall survival was detected in the UPS histopathological subtype (p = 0.004). The 5 and 10-year overall survival rates in the chondrosarcoma group were 71% and 37%, respectively; desmoid tumors were found in 83% and 42%, respectively. There was no patient with 5-year survival in UPS. A shorter median overall survival was found in lateral wall masses compared to anterior and posterior wall masses (p = 0.001). During the follow-up, 10 patients (50%) died. It was observed that the median disease-free survival in the UPS subtype was shorter compared to the other subtypes (p = 0.002). The regional recurrence rate was 57%, 17% and 75% in chondrosarcoma, desmoid tumor and UPS, respectively. In UPS, a primary malignant tumor of the chest wall, 5-year and 10-year overall survival rates and median overall survival; it was found to be significantly shorter than the chondrosarcoma and desmoid tumor groups.
Aims: This retrospective study aimed to investigate the role of immature granulocytes (IGs) in the early diagnosis of pneumonia secondary to rib fractures. Methods: This study was conducted on patients who applied to the emergency department of our hospital between 2019 and 2022. Patients aged between 18 and 100 years who were found to have rib fractures in the thorax CT report and were hospitalized, who had hemogram data in the hospital’s database, were included in the study. Patients with detected COVID-19 infection without hemogram data and patients who refused examination and treatment were excluded from the study. Patients’ blood tests, radiological images, and epicrisis reports were analyzed. The data of patients with and without pneumonia were compared statistically. Results: Overall, 155 patients, 117 men and 38 women were included in the study. Pneumonia developed in 11 patients, and two patient died. In our study, it was determined that the risk of pneumonia increased by 38% in each additional rib fracture, and the risk of pneumonia increased 9.44 times if the IG value at the 48th hour was greater than 0.06. In addition, when the receiver operating characteristic curves in our study were examined, it was observed that the IG number at 48 hours gave excellent results in the diagnosis of pneumonia, with 75% sensitivity and 88% specificity (cut off: 0.055, AUC: 0.827, p = 0.002). Conclusion: Our study showed that IGs are an effective marker in the early diagnosis of pneumonia secondary to rib fractures.
Background: Pneumothorax (PTX) requires rapid recognition in emergency and critical care. Lung ultrasound (LUS) offers a fast, radiation-free alternative to computed tomography (CT), but its accuracy is limited by operator dependence. Artificial intelligence (AI) may standardize interpretation and improve performance. Methods: This retrospective single-center study included 46 patients (23 with CT-confirmed PTX and 23 controls). Sixty B-mode and M-mode frames per patient were extracted using a Clarius C3 HD3 wireless device, yielding 2,760 images. CT served as the diagnostic reference. Two transformer-based models, Vision Transformer (ViT) and DINOv2, were trained and tested under two scenarios: random frame split and patient-level split. Model performance was evaluated using accuracy, sensitivity, specificity, F1-score, and area under the ROC curve (AUC). Results: Both transformers achieved high diagnostic accuracy, with B-mode images outperforming M-mode inputs. In Scenario 1, ViT reached 99.1% accuracy, while DINOv2 achieved 97.3%. In Scenario 2, which avoided data leakage, DINOv2 performed best in the B-mode region (90% accuracy, 80% sensitivity, 100% specificity, F1-score 88.9%). ROC analysis confirmed strong discriminative ability, with AUC values of 0.973 for DINOv2 and 0.964 for ViT on B-mode images. Conclusions: AI-assisted LUS substantially improves PTX detection, with transformers—particularly DINOv2—achieving near-expert accuracy. Larger multicenter datasets are required for validation and clinical integration.