A 5 item version of the Workplace Activity Limitation Scale successfully identifies impaired work productivity in rheumatoid arthritis patients: A split-sample factor analysis approach.

BACKGROUND: There is a growing interest in studying the effects of arthritis on a person's work productivity using a growing variety of outcome indicators. OBJECTIVES: To develop a valid and reliable shortened version of the Workplace Activity Limitation Scale 12 (WALS-12) for assessing work productivity limitations in rheumatoid arthritis (RA) patients. METHODS: A cross-sectional study involving 277 RA patients was conducted. An exploratory factor analysis on WALS-12 was used for item reduction on the first sample. Then confirmatory factor analysis (CFA) was run to establish the best fit indices of the reduced version. On the second sample, CFA and linear discriminant analysis were performed to assess the diagnostic performance and discriminant ability of the reduced form. A Bland-Altman method was used to find the agreement between the WALS-12 and the reduced one. RESULTS: The WALS-12 was reduced to 5 items. The Cronbach α was 0.817, with a composite reliability of 0.715. The Spearman rho correlation coefficient ranged between 0.675 and 0.795 for WALS-5, which was higher for the scale items with their domains than the correlation of WALS-5 with the domains of Work Limitations Questionnaire-25. Also, the root square of the average variant extracted from WALS-5 was 0.802. WALS-5 showed excellent discriminant ability with an area under the curve of 0.98 (P < .001), sensitivity of 97%, specificity of 82%, and accuracy of 94%. The reduced version WALS-5 was in agreement with the original version WALS-12. CONCLUSIONS: WALS-5 is a valid and reliable tool to assess the work productivity limitations in RA patients.

Transfer learning with different modified convolutional neural network models for classifying digital mammograms utilizing Local Dataset.

BACKGROUND: Breast cancer is the leading cause of cancer-related mortality among women worldwide. The incidence and mortality increased globally since starting registration in 1990. Artificial intelligence is being widely experimented in aiding in breast cancer detection, radiologically or cytologically. It has a beneficial role in classification when used alone or combined with radiologist evaluation. The objectives of this study are to evaluate the performance and accuracy of different machine learning algorithms in diagnostic mammograms using a local four-field digital mammogram dataset. METHODOLOGY: The dataset of the mammograms was fullfield digital mammography collected from the oncology teaching hospital in Baghdad. All the mammograms of the patients were studied and labeled by an experienced radiologist. Dataset was composed of two views CranioCaudal (CC) and Mediolateral-oblique (MLO) of one or two breasts. The dataset included 383 cases that were classified based on their BIRADS grade. Image processing included filtering, contrast enhancement using contrast limited adaptive histogram equalization (CLAHE), then removal of labels and pectoral muscle for improving performance. Data augmentation was also applied including horizontal and vertical flipping and rotation within 90 degrees. The data set was divided into a training set and a testing set with a ratio 9:1. Transfer learning of many models trained on the Imagenet dataset was used with fine-tuning. The performance of various models was evaluated using metrics including Loss, Accuracy, and Area under the curve (AUC). Python v3.2 was used for analysis with the Keras library. Ethical approval was obtained by the ethical committee from the College of Medicine University of Baghdad Results: NASNetLarge model achieved the highest accuracy and area under curve 0.8475 and 0.8956 respectively. The least performance was achieved using DenseNet169 and InceptionResNetV2. With accuracy 0.72. The longest time spent for analyzing one hundred image was seven seconds. DISCUSSION AND CONCLUSION: This study presents a newly emerging strategy in diagnostic and screening mammography by using AI with the help of transferred learning and fine-tuning. Using these models can achieve acceptable performance in a very fast way which may reduce the workload burden among diagnostic and screening units.

Pattern of Presentation of Patients With Breast Cancer in Iraq in 2018: A Cross-Sectional Study.

PURPOSE: This study aims to describe the pattern of presentation of Iraqi female patients with breast cancer by assessing the grades and stages of their cancers at the time of presentation, to identify patients' main complaints, and to discover whether there is any difference in presentation between patients in Iraq and those in other countries. PATIENTS AND METHODS: This is a retrospective cross-sectional study that was performed in the National Center of Cancer in 2018. The target population was female patients with breast cancer who came to the Center for treatment and follow-up. A sample of 171 patients was drawn from this population. Self-evaluation forms were used in interviews with the patients to collect personal and sociodemographic data; clinical and histologic characteristics of the patients' tumors were obtained from their medical records. Ethical approval was obtained. RESULTS: Forty-five percent of the patients were younger than age 50 years, and 25% were younger than age 45 years. In all, 42.9% of the patients were diagnosed with stage III and 25% with stage IV cancer, and metastasis was diagnosed in 24.1%. In our study population, 53.4% of the tumors were found in the right breast, and 3.9% of patients had bilateral breast tumors. The most common histopathologic type was invasive ductal carcinoma (81.4%) followed by invasive lobular carcinoma (6.9%) and tubular carcinoma (5.9%). The patients' most common complaints were breast lump (71.3%) and pain (18.9%). No correlation was found between tumor stage and breast self-examination, family history, education, occupation, histopathology, or grade. CONCLUSION: Most of the patients are diagnosed at a late stage when treatment is less effective.