Prediction of gestational diabetes using deep learning and Bayesian optimization and traditional machine learning techniques.

The study aimed to develop a clinical diagnosis system to identify patients in the GD risk group and reduce unnecessary oral glucose tolerance test (OGTT) applications for pregnant women who are not in the GD risk group using deep learning algorithms. With this aim, a prospective study was designed and the data was taken from 489 patients between the years 2019 and 2021, and informed consent was obtained. The clinical decision support system for the diagnosis of GD was developed using the generated dataset with deep learning algorithms and Bayesian optimization. As a result, a novel successful decision support model was developed using RNN-LSTM with Bayesian optimization that gave 95% sensitivity and 99% specificity on the dataset for the diagnosis of patients in the GD risk group by obtaining 98% AUC (95% CI (0.95-1.00) and p < 0.001). Thus, with the clinical diagnosis system developed to assist physicians, it is planned to save both cost and time, and reduce possible adverse effects by preventing unnecessary OGTT for patients who are not in the GD risk group.

A prospective study for gestational diabetes mellitus: Analysis of risk factors in Turkish women for early prediction.

OBJECTIVE: To define risk factors for the early prediction of gestational diabetes mellitus (GDM) because the risk of pre-eclampsia and preterm birth increases in mothers who are diagnosed with GDM. MATERIALS AND METHODS: A prospective study was designed and the data were collected by physicians prospectively from the patients who came to the clinic between the years 2019 and 2021; informed consent was obtained from the women. The prospective data comprised 489 patient records with 72 variables and the risk factors for early prediction of GDM were determined using logistic regression and random forest (RF), which is an advanced analysis method. RESULTS: The obtained sensitivity and specificity values are 90% and 75% for logistic regression and 71% and 90% for the RF, respectively. CONCLUSION: In this prospective study of GDM in Turkish women; age, body mass index, level of hemoglobin A1c, level of fasting blood sugar, physical activity time in first trimester, gravidity, triglycerides, and high-density lipoprotein cholesterol were confirmed to be risk factors in analysis results.

NMSDR: Drug repurposing approach based on transcriptome data and network module similarity.

Computational drug repurposing aims to discover new treatment regimens by analyzing approved drugs on the market. This study proposes previously approved compounds that can change the expression profile of disease-causing proteins by developing a network theory-based drug repurposing approach. The novelty of the proposed approach is an exploration of module similarity between a disease-causing network and a compound-specific interaction network; thus, such an association leads to more realistic modeling of molecular cell responses at a system biology level. The overlap of the disease network and each compound-specific network is calculated based on a shortest-path similarity of networks by accounting for all protein pairs between networks. A higher similarity score indicates a significant potential of a compound. The approach was validated for breast and lung cancers. When all compounds are sorted by their normalized-similarity scores, 36 and 16 drugs are proposed as new candidates for breast and lung cancer treatment, respectively. A literature survey on candidate compounds revealed that some of our predictions have been clinically investigated in phase II/III trials for the treatment of two cancer types. As a summary, the proposed approach has provided promising initial results by modeling biochemical cell responses in a network-level data representation.

Computational drug repurposing study of the RNA binding domain of SARS-CoV-2 nucleocapsid protein with antiviral agents.

The recent outbreak of coronavirus disease (COVID-19) in China caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to worldwide human infections and deaths. The nucleocapsid (N) protein of coronaviruses (CoVs) is a multifunctional RNA binding protein necessary for viral RNA replication and transcription. Therefore, it is a potential antiviral drug target, serving multiple critical functions during the viral life cycle. This study addresses the potential to repurpose antiviral compounds approved or in development for treating human CoV induced infections against SARS-CoV-2 N. For this purpose, we used the docking methodology to better understand the inhibitory mechanism of this protein with the existing 34 antiviral compounds. The results of this analysis indicate that rapamycin, saracatinib, camostat, trametinib, and nafamostat were the top hit compounds with binding energy (-11.87, -10.40, -9.85, -9.45, -9.35 kcal/mol, respectively). This analysis also showed that the most common residues that interact with the compounds are Phe66, Arg68, Gly69, Tyr123, Ile131, Trp132, Val133, and Ala134. Subsequently, protein-ligand complex stability was examined with molecular dynamics simulations for these five compounds, which showed the best binding affinity. According to the results of this study, the interaction between these compounds and crucial residues of the target protein were maintained. These results suggest that these residues are potential drug targeting sites for the SARS-CoV-2 N protein. This study information will contribute to the development of novel compounds for further in vitro and in vivo studies of SARS-CoV-2, as well as possible new drug repurposing strategies to treat COVID-19 disease.

Comparison of enhancement methods for mammograms with performance measures.

Mammograms are generally contaminated by noise which assures the need for image enhancement to aid interpretation. The enhancement of mammograms is a very important problem for easy extraction of suspicious regions known as regions of interest (ROIs). This paper introduces comparison of various hybrid enhancement algorithms based on mathematical morphology, contrast stretching, wavelet transform, anisotropic diffusion filter and contrast limited adaptive histogram equalization (CLAHE). The performances of algorithms have been compared by using three global image enhancement evaluation measures; Enhancement Measure (EME), Absolute Mean Brightness Error (AMBE) and Peak Signal-to-Noise Ratio (PSNR). For this study, we have used MIAS database. Experimental results show that the combination of mathematical morphology, anisotropic diffusion filter and CLAHE methods, yields significantly superior image quality and provides more visibility for the suspicious regions.

A novel automatic suspicious mass regions identification using Havrda & Charvat entropy and Otsu's N thresholding.

Mass detection is a very important process for breast cancer diagnosis and computer aided systems. It can be very complex when the mass is small or invisible because of dense breast tissue. Therefore, the extraction of suspicious mass region can be very challenging. This paper proposes a novel segmentation algorithm to identify mass candidate regions in mammograms. The proposed system includes three parts: breast region and pectoral muscle segmentation, image enhancement and suspicious mass regions identification. The first two parts have been examined in previous studies. In this study, we focused on suspicious mass regions identification using a combination of Havrda & Charvat entropy method and Otsu's N thresholding method. An open access Mammographic Image Analysis Society (MIAS) database, which contains 59 masses, was used for the study. The proposed system obtained a 93% sensitivity rate for suspicious mass regions identification in 56 abnormal and 40 normal images.

Does instructor evaluation by students using a WEB-based questionnaire impact instructor performance?

BACKGROUND: Student feedback is a valuable method to evaluate the quality of education. Using a WEB-based questionnaire, the objective of this study was to evaluate the factors that may affect the ratings given by the students and the impact of those ratings on the instructor's teaching performance. METHODS: The questionnaire was organized into four areas: containment, presentation skills, measurement and assessment, and communication skills. In addition, there was a final area in which the students could express their opinions about their instructor. The students were asked to rank their instructors in each of the four areas using a scale of 1-5. In both May 2002 and 2003, the students ranked their instructors using the WEB-based questionnaire. RESULTS: In 2002, 468 students evaluated 146 instructors; while in 2003, 360 students evaluated 144 instructors. Of the total number of instructors evaluated, 140 were evaluated both in 2002 and 2003. The mean point scores for these 140 instructors were 3.64 +/- 0.51 in 2002 and 3.65 +/- 0.54 in 2003. There was no statistically significant difference according to the titles of the instructors. For both 2002 and 2003, regarding the last section in the questionnaire where students could present their opinions, 80 of the students, indicated the instructors had communication problems. All instructors with low scores were mentioned to have poor communication skills. The changes in the mean point scores were evaluated comparing results from 2002 and 2003. Fourteen professors, four associate professors, three assistant professors, two lecturers were found to have higher scores, three professors, seven associate professors, five assistant professors, and one lecturer were found to have lower scores. CONCLUSION: No significant improvement was found in the mean points of the total group. In the second year, only 16.4 of the instructors were affected positively.