Age Estimation Using Machine Learning Algorithms with Parameters Obtained from X-ray Images of the Calcaneus.

BACKGROUND: Determination of bone age is a critical issue for forensics, surgery, and basic sciences. AIM: This study aims to estimate age with high accuracy and precision using Machine Learning (ML) algorithms with parameters obtained from calcaneus x-ray images of healthy individuals. METHOD: The study was carried out by retrospectively examining the foot X-ray images of 341 people aged 18-65 years. Maximum width of the calcaneus (MW), body width (BW), maximum length (MAXL), minimum length (MINL), facies articularis cuboidea height (FACH), maximum height (MAXH), and tuber calcanei width (TKW) parameters were measured from the images. The measurements were then grouped as 20-45 years of age, 46-64 years of age, 65 and older, and age estimation was made by using these at the input of ML models. RESULTS: As a result of the ML input of the measurements obtained, a 0.85 Accuracy (Acc) rate was obtained with the Extra Tree Classifier algorithm. The accuracy rate of other algorithms was found to vary between 0.78 and 0.82. The contribution of parameters to the overall result was evaluated by using the shapley additive explanations (SHAP) analyzer of Random Forest algorithm and the MAXH parameter was found to have the highest contribution in age estimation. CONCLUSIONS: As a result of our study, calcaneus bone was found to have high accuracy and precision in age estimations.

The diagnostic, predictive, and prognostic role of serum epithelial cell adhesion molecule (EpCAM) and vascular cell adhesion molecule-1 (VCAM-1) levels in breast cancer.

The purpose of this study was to determine the clinical significance of vascular cell adhesion molecule-1 (VCAM-1) and epithelial cell adhesion molecule (EpCAM) in breast cancer (BC) patients. Ninety-six BC patients and 30 age- and sex-matched healthy controls were enrolled into this study. Pretreatment serum markers were determined by the solid-phase sandwich (enzyme-linked immunosorbent assay (ELISA)). The median age at diagnosis was 48 years (range 29-80 years). Majority of the patients (71 %) had luminal subtype, and 38.5 % had metastatic disease. Twenty-nine (30 %) patients showed tumor progression, and 20 (21 %) patients died during follow-up. Median progression-free survival (PFS) and overall survival (OS) were 8.6 ± 1.7 and 35.5 ± 1.5 months, respectively. The baseline serum EpCAM levels of the patients were significantly higher than those of the controls (p < 0.001). There was no significant difference in the serum levels of VCAM-1 between the patients and controls (p = 0.47). No significant correlation was detected between the levels of the serum markers and other clinical parameters (p > 0.05). Patients with HER-2-positive and triple-negative tumors had significantly poorer PFS (p = 0.04 and p = 0.001, respectively), while metastatic disease and chemotherapy unresponsiveness had significantly adverse effect on OS analysis (p < 0.001 and p < 0.001, respectively). Neither serum VCAM-1 levels nor serum EpCAM levels were identified to have a prognostic role on either PFS or OS (VCAM-1 p = 0.76 and p = 0.32; EpCAM p = 0.16 and p = 0.69, respectively). Even though any predictive or prognostic role could not be determined for both markers, serum levels of EpCAM were found to have diagnostic value in BC patients.

Is there any diagnostic value of serum protease-activated receptor-1 (PAR1) levels on determination of epithelial ovarian carcinoma?

The role of molecular markers in ovarian cancer is still a matter of debate. Protease-activated receptor-1 (PAR1) might be a good marker in some types of malignant tumors and might provide useful information in diagnosis and prognosis. The objective of this study was to evaluate the serum levels of PAR1 in regard to diagnostic, predictive, and prognostic value in epithelial ovarian cancer (EOC) patients. Forty-four EOC patients were enrolled in this study. Serum PAR1 levels were determined by enzyme-linked immunosorbent assay (ELISA) method. Twenty-five age- and sex-matched healthy controls were included in the analysis. The median age of patients was 58 years old, ranging from 22 to 83 years, where most of them had advanced disease (stage III-IV) (n = 40, 91%). The median serum PAR1 values were significantly elevated in patients compared to healthy controls (1.52 ng/ml vs. 1.13 ng/ml) (p = 0.03), whereas any clinical variables including response to chemotherapy did not associate with serum assay (p > 0.05). Progression-free survival (PFS) and overall survival (OS) of patients who did not respond to chemotherapy nor had platinum resistance in relapsed disease were poorer in the analyses. On the other hand, serum PAR1 levels showed no significant adverse effect on either PFS or OS (p = 0.43 and p = 0.49, respectively). These results proved that baseline serum PAR1 levels of patients with EOC were significantly higher than those of healthy people. However, these assays suggested no predictive or prognostic value in this group of patients.

The role of surgical methods in the treatment of anorectal malignant melanoma (AMM).

PURPOSE: Anorectal malignant melanoma (AMM) is a rare tumor with a poor prognosis. The aim of this study was to investigate the clinicopathological characteristics and treatment outcomes in patients with AMM. METHODS: The study included 21 patients diagnosed with AMM between 2000 and 2010 that were evaluated with regard to age, sex, disease stage, treatment modality, and survival. Stage I, II, and III were defined as localized primary malignant melanoma, regional lymph node metastasis, and distant metastasis, respectively. RESULTS: In all, 12 (57%) patients were female and 9 (43%) were male ; median age was 61 years (range : 30-84 years). Among the 21 patients, 7 (47%) underwent abdominoperineal resection and 8 (53%) were treated using wide local excision. Four (19%) patients were classified as stage I, 10 (48%) as stage II, and 7 (33%) patients as stage III. In total, 10 patients received adjuvant therapy. Median overall and progression-free survival was 12 and 9 months, respectively. The 1-year and 5-year overall survival estimates were 59% and 42%, and progression free survival were 49% and 7%, respectively. Patients aged > 60 years (P = 0.145), female patients (P = 0.076), patients with localized disease (P = 0.045), patients that underwent wide local excision (P = 0.619), and patients that received adjuvant therapy (P = 0.962) had longer survival. CONCLUSIONS: The prognosis of AMM remains very poor and disease stage is the only predictor of survival. Abdominoperineal resection does not confer an advantage, in terms of survival, in patients with AMM.