Prediction of Cervical Lymph Node Metastasis in Clinically Node-Negative T1 and T2 Papillary Thyroid Carcinoma Using Supervised Machine Learning Approach.

Papillary thyroid carcinoma (PTC) is generally considered an indolent cancer. However, patients with cervical lymph node metastasis (LNM) have a higher risk of local recurrence. This study evaluated and compared four machine learning (ML)-based classifiers to predict the presence of cervical LNM in clinically node-negative (cN0) T1 and T2 PTC patients. The algorithm was developed using clinicopathological data from 288 patients who underwent total thyroidectomy and prophylactic central neck dissection, with sentinel lymph node biopsy performed to identify lateral LNM. The final ML classifier was selected based on the highest specificity and the lowest degree of overfitting while maintaining a sensitivity of 95%. Among the models evaluated, the k-Nearest Neighbor (k-NN) classifier was found to be the best fit, with an area under the receiver operating characteristic curve of 0.72, and sensitivity, specificity, positive and negative predictive values, F1 and F2 scores of 98%, 27%, 56%, 93%, 72%, and 85%, respectively. A web application based on a sensitivity-optimized kNN classifier was also created to predict the potential of cervical LNM, allowing users to explore and potentially build upon the model. These findings suggest that ML can improve the prediction of LNM in cN0 T1 and T2 PTC patients, thereby aiding in individual treatment planning.

Comparison of Different Machine Learning Models in Prediction of Postirradiation Recurrence in Prostate Carcinoma Patients.

After primary treatment of localized prostate carcinoma (PC), up to a third of patients have disease recurrence. Different predictive models have already been used either for initial stratification of PC patients or to predict disease recurrence. Recently, artificial intelligence has been introduced in the diagnosis and management of PC with a potential to revolutionize this field. The aim of this study was to analyze machine learning (ML) classifiers in order to predict disease progression in the moment of prostate-specific antigen (PSA) elevation during follow-up. The study cohort consisted of 109 PC patients treated with external beam radiotherapy alone or in combination with androgen deprivation therapy. We developed and evaluated the performance of two ML algorithms based on artificial neural networks (ANN) and naïve Bayes (NB). Of all patients, 72.5% was randomly selected for a training set while the remaining patients were used for testing of the models. The presence/absence of disease progression was defined as the output variable. The input variables for models were conducted from the univariate analysis preformed among two groups of patients in the training set. They included two pretreatment variables (UICC stage and Gleason's score risk group) and five posttreatment variables (nadir PSA, time to nadir PSA, PSA doubling time, PSA velocity, and PSA in the moment of disease reevaluation). The area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, and predictive accuracy was calculated to test the models' performance. The results showed that specificity was similar for both models, while NB achieved better sensitivity then ANN (100.0% versus 94.4%). The ANN showed an accuracy of 93.3%, and the matching for NB model was 96.7%. In this study, ML classifiers have shown potential for application in routine clinical practice during follow-up when disease progression was suspected.

The association of circulating sclerostin level with markers of bone metabolism in patients with thyroid dysfunction.

BACKGROUND: The aim of this study was to compare serum sclerostin concentrations in patients with thyroid dysfunction with euthyroid control subjects and to assess the relationship between sclerostin and markers of bone metabolism (osteocalcin and beta-cross-laps). METHODS: The study included 30 patients with thyroid dysfunction (hypothyroidism, hyperthyroidism and subclinical hyperthyroidism) and ten euthyroid controls. Free thyroxine (FT4) was measured by radioimmunoassay, while thyroid stimulating hormone (TSH) concentration was determined immunoradiometrically. We used an ELISA kit to determine the sclerostin level. The electrochemiluminescence method was applied for measuring the bone markers. RESULTS: Sclerostin levels were significantly lower in hypothyroid patients (p=0.009) and significantly elevated in hyperthyroid patients (p=0.008) compared to control values. Hyperthyroid patients also had higher sclerostin than patients with subclinical hyperthyroidism (p=0.013). Sclerostin concentrations were negatively correlated with TSH levels (r=-0.746, p<0.001), but positively with FT4 (r=0.696, p < 0.001). Moreover, sclerostin was positively associated with osteocalcin (r=0.605, p=0.005) and beta-cross-laps levels (r=0.573, p=0.008) in all thyroid patients. CONCLUSIONS: Serum sclerostin is significantly affected in subjects with thyroid dysfunction. Both sclerostin and thyroid status affect bone homeostasis, which is reflected through the significant correlations with osteocalcin and beta-cross-laps.

Eosinophil Cationic Protein in Patients with Differentiated Thyroid Cancer Treated with Radioactive Iodine 131.

Published data indicate the involvement of eosinophil granulocytes and eosinophil cationic protein (ECP) in tumor defense. The aim of this study was to analyze serum ECP concentrations in patients with differentiated thyroid cancer (DTC) before, 3 days and 7 days after radioactive iodine (131-I) therapy. Association of ECP concentrations with histological type of tumor, stage of disease and/or levels of selected T-helper 2 (Th2) cytokines was examined. The study population included 17 DTC patients and 10 control subjects. ECP was measured by fluoroimmunoassay (FIA). Th2 (cytokines interleukin 4 (IL-4), interleukin 5 (IL-5), and interleukin 13 (IL-13)) were determined by enzyme-linked immunosorbent assays (ELISA). We found that ECP values in DTC patients before radioactive iodine therapy were approximately two-fold higher than in the controls, but the difference was statistically significant only if the patients with DTC and associated Hashimoto thyroiditis (HT) were included. There was no correlation between the serum concentrations of IL-5 and ECP. Radioactive iodine therapy led to a decrease in serum ECP level which did not follow the decline in serum protein levels. Additional studies are needed to determine the significance of these findings.

Transforming Growth Factor Beta 1 (TGF-ß1) in Thyroid Cancer Patients: a View from the Peripheral Blood.

Transforming growth factor beta (TGF-ß) plays an important role in many pathophysiological conditions, including cancer. The level of TGF-ß in patients with differentiated thyroid cancer (DTC) has not been examined so far. The aim of this study was to measure TGF-ß concentration in serum samples and in PHA-stimulated whole blood culture in vitro and to analyze possible associations of TGF-ß1 levels with leukocyte, lymphocyte and platelets counts, the histological type of thyroid cancer, and stage of disease. TGF-ß1 was measured in 22 DTC patients and 20 healthy controls using the duoSet ELISA Development kit for human TGF-ß1. The concentration of TGF-ß1 in serum samples from both groups correlated positively with the platelet counts. There was no statistically significant difference in the serum concentrations of TGF-ß1 between DTC patients and control subjects, but PHA stimulated whole blood cultures of DTC patients produced less TGF-ß1 than those from controls. Additional studies are needed to determine the significance of these in vitro findings.

Blood cells in thyroid cancer patients: a possible influence of apoptosis.

The side effects of radioactive iodine (131-I) treatment of differentiated thyroid cancer (DTC) patients include reduction of peripheral blood cell counts. The aim of this study was to analyze some potential changes in blood cell counts of DTC patients after 131-I therapy, especially CD3-positive, CD19-positive, and CD56-positive peripheral blood lymphocytes (PBL), as well as the possible role of apoptosis in selected lymphocyte populations. The study group included 24 thyroid cancer patients and 24 control subjects. Peripheral blood samples from patients and controls were analyzed using 5-color flow cytometry. Apoptotic cells were detected using an Annexin V-FITC/7-AAD kit. There was a statistically significant decrease of all blood cells after the 131-I therapy. The CD19+ B lymphocyte population was the most affected (5.82 ± 3.21% before therapy vs. 3.93 ± 2.60% after therapy, p = 0.008). This decrease was correlated with the degree of apoptosis of peripheral blood lymphocytes (Spearman's r = 0.563, p =0.013). We concluded that 131-I therapy of DTC patients led to a decrease of all peripheral blood cells, especially CD19+ B lymphocytes. This directly correlated with apoptosis of PBLs, indicating that radiation damage to B cells leads to subsequent elimination by apoptosis.

Cytokine production in patients with papillary thyroid cancer and associated autoimmune Hashimoto thyroiditis.

Hashimoto thyroiditis (HT) is the most frequent thyroid autoimmune disease, while papillary thyroid cancer (PTC) is one of the most common endocrine malignancies. A few patients with HT also develop PTC. The aim of this study was to analyze cytokine profiles in patients with PTC accompanied with autoimmune HT in comparison with those in patients with PTC alone or HT alone and healthy subjects. Cytokine levels were determined in supernatants obtained from phytohemagglutinin (PHA)-stimulated whole blood cultures in vitro. The concentrations of selected cytokines: Th1-interferon gamma (IFN-γ); Th2-interleukin 4 (IL-4), interleukin 5 (IL-5), interleukin 6 (IL-6), interleukin 10 (IL-10) and interleukin 13 (IL-13); Th9-interleukin 9 (IL-9); and Th17-interleukin 17 (IL-17A) were measured using multiplex cytokine detection systems for human Th1/Th2/Th9/Th17/Th22. We found that PTC patients with HT produced significantly higher concentrations of IL-4, IL-6, IL-9, IL-13 and IFN-γ than PTC patients without HT. In conclusion, autoimmune HT affects the cytokine profile of patients with PTC by stimulating secretion of Th1/Th2/Th9 types of cytokines. Th1/Th2 cytokine ratios in PTC patients with associated autoimmune HT indicate a marked shift toward Th2 immunity.

Correlation between micronuclei frequency in peripheral blood lymphocytes and retention of 131-I in thyroid cancer patients.

Differentiated thyroid cancers (DTCs) derive from thyroid follicular cells and include papillary and follicular cancers. In patients with DTCs, the initial treatment includes thyroidectomy and radioactive iodine (131-I) therapy. The objective of this study was to examine whether the intensity of DNA damage in peripheral blood lymphocytes (PBLs) of DTC patients depends on the amount of 131-I retained in the selected regions of interest (thyroid and abdominal region) as well as in the whole-body 72 hours after therapy. In addition, the possible influence of other factors that may affect micronuclei (MN) frequency, such as age, gender, smoking habits, and histological type of tumour was analyzed. The study population consisted of 22 DTC patients and 20 healthy donors. Data on the distribution of 131-I were obtained from the whole-body scans. MN frequency and cytokinesis-block proliferation index (CBPI) were measured using cytokinesis-block micronucleus assay. 131-I therapy significantly increased the MN frequency (19.50±6.90 vs. 27.10±19.50 MN) and significantly decreased the CBPI (1.52±0.20 vs. 1.38±0.17) in patients' lymphocytes. There was a clear correlation between the increased MN frequency and 131-I accumulation in the thyroid region in patients without metastases. The MN values did not differ in relation to the factors that could affect MN, such as age, gender, smoking habits, and histological type of tumour. In conclusion, the MN frequency in PBLs of DTC patients without metastases depends on the accumulation of 131-I in the thyroid region and does not depend on the other factors examined.