Rate of various access sites for temporary transvenous pacing and different outcomes at Lady Reading Hospital, Peshawar Pakistan.

Objective: To evaluate the various temporary transvenous pacemaker (TPM) access sites, its indications, procedural complications, and outcomes of patients. Methods: This prospective study conducted in a tertiary care hospital of Peshawar, included 100 patients, who underwent TPM for any reasons, via the trans jugular, subclavian, or trans-femoral route. The duration of the study was from October 1st, 2021 to March 31st, 2022. The demographic, procedure -related complications, causes of complete heart block and in hospital outcomes were recorded. Results: Of the 100 patients who underwent temporary transvenous pacing, 56%were males and 44% were females, with an age range of 46-80 years. In majority of the patients, (N =54) internal jugular vein was used as the venous access site followed by the subclavian vein. (N=24). Coronary artery disease was prevalent in 42% of the patients. 50% had complete AV block, 19% had symptomatic second-degree block, and 10% had sinus nodal diseases. Seventy three percent of the patients needed TPM implantation on an emergency basis, which is statistically significant (p=0.009). Almost 40% of the patient ultimately underwent a permanent pacemaker. Out of 100 patients, 16 patients expired. The major procedure related complications were bleeding 16% overall at the puncture site and 14.8% in the internal jugular group. Other complications were local infection 13% at the insertion site followed by hemopericardium 3%, in the internal jugular group. Conclusion: Atrioventricular block is the commonest indication for temporary pacing in our study. The average time the TPM remained in place was significantly higher in the trans jugular approach group along with a higher complication rate in this group.

Social determinants of pacemaker reuse among patients and family members in Pakistan.

OBJECTIVES: This survey aimed to quantify the opinions of CIED reuse among patients and family members in Pakistan and to identify the social determinants which may predict these views. METHODS: A questionnaire formulating attitudes toward PPM reuse was administered to patients and family members at cardiology institutes in Pakistan from 1 July 2022 to 30 September 2022. The eligibility criteria (age > 18 years; inline for PPM placement) were taken into account and incomplete responses were excluded from the final analysis. RESULTS: A total of 9,246 participants recorded their responses, of which 7,152 (78.16%) accepted pre-used PPMs. The lower social class had more PPM reuse acceptance rate than the middle and upper class (92.72% vs. 60.52% vs. 35.38%), respectively. Age ≥ 65 (OR(95%CI): 0.68 (0.41-0.99); P-value = 0.023), male gender (OR(95%CI): 0.55 (0.35-0.72), P-value = 0.016), unemployment (OR(95%CI): 0.47 (0.25-0.64); P-value = 0.007), poor health status (OR(95%CI): 0.72 (0.53-0.92); P-value = 0.041), and lower social class (OR(95%CI): 0.36 (0.28-0.53); P-value = 0.003) were social determinants of PPM reuse acceptance. CONCLUSION: Patients and their family members endorse the concept of PPM reuse in Pakistan who cannot afford new devices.

Predicting Breast Cancer Leveraging Supervised Machine Learning Techniques.

Breast cancer is one of the leading causes of increasing deaths in women worldwide. The complex nature (microcalcification and masses) of breast cancer cells makes it quite difficult for radiologists to diagnose it properly. Subsequently, various computer-aided diagnosis (CAD) systems have previously been developed and are being used to aid radiologists in the diagnosis of cancer cells. However, due to intrinsic risks associated with the delayed and/or incorrect diagnosis, it is indispensable to improve the developed diagnostic systems. In this regard, machine learning has recently been playing a potential role in the early and precise detection of breast cancer. This paper presents a new machine learning-based framework that utilizes the Random Forest, Gradient Boosting, Support Vector Machine, Artificial Neural Network, and Multilayer Perception approaches to efficiently predict breast cancer from the patient data. For this purpose, the Wisconsin Diagnostic Breast Cancer (WDBC) dataset has been utilized and classified using a hybrid Multilayer Perceptron Model (MLP) and 5-fold cross-validation framework as a working prototype. For the improved classification, a connection-based feature selection technique has been used that also eliminates the recursive features. The proposed framework has been validated on two separate datasets, i.e., the Wisconsin Prognostic dataset (WPBC) and Wisconsin Original Breast Cancer (WOBC) datasets. The results demonstrate improved accuracy of 99.12% due to efficient data preprocessing and feature selection applied to the input data.

Detection of COVID-19 Using Transfer Learning and Grad-CAM Visualization on Indigenously Collected X-ray Dataset.

The COVID-19 outbreak began in December 2019 and has dreadfully affected our lives since then. More than three million lives have been engulfed by this newest member of the corona virus family. With the emergence of continuously mutating variants of this virus, it is still indispensable to successfully diagnose the virus at early stages. Although the primary technique for the diagnosis is the PCR test, the non-contact methods utilizing the chest radiographs and CT scans are always preferred. Artificial intelligence, in this regard, plays an essential role in the early and accurate detection of COVID-19 using pulmonary images. In this research, a transfer learning technique with fine tuning was utilized for the detection and classification of COVID-19. Four pre-trained models i.e., VGG16, DenseNet-121, ResNet-50, and MobileNet were used. The aforementioned deep neural networks were trained using the dataset (available on Kaggle) of 7232 (COVID-19 and normal) chest X-ray images. An indigenous dataset of 450 chest X-ray images of Pakistani patients was collected and used for testing and prediction purposes. Various important parameters, e.g., recall, specificity, F1-score, precision, loss graphs, and confusion matrices were calculated to validate the accuracy of the models. The achieved accuracies of VGG16, ResNet-50, DenseNet-121, and MobileNet are 83.27%, 92.48%, 96.49%, and 96.48%, respectively. In order to display feature maps that depict the decomposition process of an input image into various filters, a visualization of the intermediate activations is performed. Finally, the Grad-CAM technique was applied to create class-specific heatmap images in order to highlight the features extracted in the X-ray images. Various optimizers were used for error minimization purposes. DenseNet-121 outperformed the other three models in terms of both accuracy and prediction.