فهرست مطالب sepehr gohari

Machine learning and artificial intelligence are useful tools to analyze data with multiple variables. It has been shown that the prediction models obtained by Machine learning have better performance than the conventional statistical methods. This study was aimed to assess the risk factors and determine the best machine learning prediction model/s for in-hospital mortality among patients who underwent prosthetic valve replacement surgery.

In this retrospective cross-sectional study, patient’s pre-operative, intra-operative and post-operative data underwent univariate analysis. Feature importance determination was carried out using algorithms including principal component analysis (PCA), support vector machine (SVM), random forest (RF) model-based, and recursive feature elimination (RFE). Then, 13 machine learning classifiers were implemented for in-hospital prediction model.

The In-hospital mortality rate was 6.36%. Data from 2455 patients underwent final analysis. The machine learning results revealed that among pre-operative features, Adaptive boost (AB) and RF classifiers (AUC: 0.82±0.033; 0.78±0.028, respectively); among intra-operative features, AB and K-nearest neighbors (KNN) classifiers (AUC: 0.68±0.014); among postoperative features, AB and RF classifiers (AUC: 0.9±0.1; 0.88±0.095, respectively); and among all features, AB and LR classifiers (AUC: 0.93±0.049; 0.93±0.055, respectively) had the best performance in prediction of in-hospital mortality.

The AB classifier was determined as the best model in prediction of in-hospital mortality in all 4 datasets.

Shone syndrome is a rare congenital cardiac abnormality; however, many of the cases remain undiagnosed until early and middle adulthood. Different imaging modalities are used to assess the related structural abnormalities. In this case study, we report a 32-year-old woman who was planning her first pregnancy. In light of her childhood heart problems, in addition to a history of extended penicillin prescriptions for several years, she was referred for complementary assessments. At the time of presentation, she was asymptomatic. Imaging results showed several structural obstructive left-sided lesions and pulmonary artery hypertension. Ultimately, the patient was diagnosed with congenital shone syndrome, which was initially misdiagnosed. Shone complex in our case was presented in its full form, which could be potentially fatal in case of pregnancy.

The ability of breaking bad news to patients, especially to patients diagnosed with cancer is one of the challengeable issues in the field of medicine. On this basis, this study was designed to assess physicianschr('39') performance as well as importance of their training on how to deliver bad news to patients diagnosed with cancer.

This was a prospective cross-sectional study for assessing physicians’ performance in delivering bad news. The hematologists and oncologists from Imam Khomeini and Shariati hospitals, Tehran, Iran, were included in the study. A questionnaire for physicians (SPIKES model) which comprised six statements was used to evaluate their performance. The time of breaking the cancer diagnosis news to the patients by the physicians and educational records were evaluated with the average score of the physicians in relation to each statement.

Totally, 12 physicians participated in the study. There was no significant difference between the statements and age or gender (P>0.05); but there was a significant relationship between ending the discussion (conversation), summarizing the content, and using the word "cancer” during the conversation (P<0.05). Additionally, there was significant correlation between the time spent on informing the patient about the cancer diagnosis and concluding the discussion and summarizing the statements (P<0.05).

Guidelines which are introducing the most harmless methods for delivering bad news with minimal negative effects on the patients’ mental health can be helpful for the medical staff, so that they can perform this important task with less stress and minimum complications for the patients.

The aim of this study was to determine the consistency of Electrocardiography (ECG) and myocardial perfusion scan findings of patients with myocardial ischemia at Firoozgar and Hazrat-Rasool hospitals.
Electrocardiogram of 80 patients undergoing myocardial perfusion scans was analyzed. All patients had a stable angina. All patients with bundle branch blocks and history of MI and coronary bypass or angiography were excluded. Overall, 120 patients were evaluated with single photon emission tomography/myocardial perfusion imaging for ischemia and 80 patients had a positive test.
Forty-five percent of patients were female and 55% were male. The average age of patients was 61.48 years. Sixty-one patients (76.25%) had normal ECG and 19 patients (23.75) had pathological changes in their ECG. Eleven patients had ST segment depression and 6 patients had T wave inversion. Furthermore, 21 patients (26.25%) had lateral wall ischemia in their myocardial perfusion scan and 13 (16.25%) patients had septal wall ischemia. The ECG changes in male patients and hypertensive cases were more prominent.
This study showed that ST-T changes (ST depression and T inversion) in the ECG are more suggestive of accuracy of myocardial ischemia and ECG.