A Deep Learning Model to Predict Knee Osteoarthritis Based on Nonimage Longitudinal Medical Record.

PURPOSE: To develop deep learning model (Deep-KOA) that can predict the risk of knee osteoarthritis (KOA) within the next year by using the previous three years nonimage-based electronic medical record (EMR) data. PATIENTS AND METHODS: We randomly selected information of two million patients from the Taiwan National Health Insurance Research Database (NHIRD) from January 1, 1999 to December 31, 2013. During the study period, 132,594 patients were diagnosed with KOA, while 1,068,464 patients without KOA were chosen randomly as control. We constructed a feature matrix by using the three-year history of sequential diagnoses, drug prescriptions, age, and sex. Deep learning methods of convolutional neural network (CNN) and artificial neural network (ANN) were used together to develop a risk prediction model. We used the area under the receiver operating characteristic (AUROC), sensitivity, specificity, and precision to evaluate the performance of Deep-KOA. Then, we explored the important features using stepwise feature selection. RESULTS: This study included 132,594 KOA patients, 83,111 females (62.68%), 49,483 males (37.32%), mean age 64.2 years, and 1,068,464 non-KOA patients, 545,902 females (51.09%), 522,562 males (48.91%), mean age 51.00 years. The Deep-KOA achieved an overall AUROC, sensitivity, specificity, and precision of 0.97, 0.89, 0.93, and 0.80 respectively. The discriminative analysis of Deep-KOA showed important features from several diseases such as disorders of the eye and adnexa, acute respiratory infection, other metabolic and immunity disorders, and diseases of the musculoskeletal and connective tissue. Age and sex were not found as the most discriminative features, with AUROC of 0.9593 (-0.76% loss) and 0.9644 (-0.25% loss) respectively. Whereas medications including antacid, cough suppressant, and expectorants were identified as discriminative features. CONCLUSION: Deep-KOA was developed to predict the risk of KOA within one year earlier, which may provide clues for clinical decision support systems to target patients with high risk of KOA to get precision prevention program.

Digital interventions self-management education for type 1 and 2 diabetes: A systematic review and meta-analysis.

OBJECTIVE: To describe and assess digital health-led diabetes self-management education and support (DSMES) effectiveness in improving glycosylated hemoglobin, diabetes knowledge, and health-related quality of life (HrQoL) of Type 1 and 2 Diabetes in the past 10 years. DESIGN: Systematic Review and Meta-Analysis. The protocol was registered on PROSPERO registration number CRD42019139884. DATA SOURCES: PubMed, EMBASE, Cochrane library, Web of Science, and Scopus between January 2010 and August 2019. Study Selection and Appraisal: Randomized control trials of digital health-led DSMES for Type 1 (T1DM) or 2 (T2DM) diabetes compared to usual care were included. Outcomes were change in HbA1c, diabetes knowledge, and HrQoL. Cochrane Risk of Bias 2.0 tool was used to assess bias and GRADEpro for overall quality. The analysis involved narrative synthesis, subgroup and pooled meta-analyses. RESULTS: From 4286 articles, 39 studies (6861 participants) were included. Mean age was 51.62 years, range (13-70). Meta-analysis revealed intervention effects on HbA1c for T2DM with difference in means (MD) from baseline -0.480% (-0.661, -0.299), I275% (6 months), -0.457% (-0.761, -0.151), I2 81% (12 months), and for T1DM -0.41% (-1.022, 0.208) I2 83% (6 months), -0.03% (-0.210, 0.142) I2 0% (12 months). Few reported HrQoL with Hedges' g 0.183 (-0.039, 0.405), I2 0% (6 months), 0.153 (-0.060, 0.366), I2 0% (12 months) and diabetes knowledge with Hedges' g 1.003 (0.068, 1.938), I2 87% (3 months). CONCLUSION: Digital health-led DSMES are effective in improving HbA1c and diabetes knowledge, notably for T2DM. Research shows non-significant changes in HrQoL. Intervention effect on HbA1c was more impressive if delivered through mobile apps or patient portals. Further research is needed on the impact of DSMES on these outcomes, especially for newly diagnosed diabetes patients.

Deep Learning Classifier with Patient's Metadata of Dermoscopic Images in Malignant Melanoma Detection.

BACKGROUND: Incidence of skin cancer is one of the global burdens of malignancies that increase each year, with melanoma being the deadliest one. Imaging-based automated skin cancer detection still remains challenging owing to variability in the skin lesions and limited standard dataset availability. Recent research indicates the potential of deep convolutional neural networks (CNN) in predicting outcomes from simple as well as highly complicated images. However, its implementation requires high-class computational facility, that is not feasible in low resource and remote areas of health care. There is potential in combining image and patient's metadata, but the study is still lacking. OBJECTIVE: We want to develop malignant melanoma detection based on dermoscopic images and patient's metadata using an artificial intelligence (AI) model that will work on low-resource devices. METHODS: We used an open-access dermatology repository of International Skin Imaging Collaboration (ISIC) Archive dataset consist of 23,801 biopsy-proven dermoscopic images. We tested performance for binary classification malignant melanomas vs nonmalignant melanomas. From 1200 sample images, we split the data for training (72%), validation (18%), and testing (10%). We compared CNN with image data only (CNN model) vs CNN for image data combined with an artificial neural network (ANN) for patient's metadata (CNN+ANN model). RESULTS: The balanced accuracy for CNN+ANN model was higher (92.34%) than the CNN model (73.69%). Combination of the patient's metadata using ANN prevents the overfitting that occurs in the CNN model using dermoscopic images only. This small size (24 MB) of this model made it possible to run on a medium class computer without the need of cloud computing, suitable for deployment on devices with limited resources. CONCLUSION: The CNN+ANN model can increase the accuracy of classification in malignant melanoma detection even with limited data and is promising for development as a screening device in remote and low resources health care.