A machine learning-based, decision support, mobile phone application for diagnosis of common dermatological diseases.

BACKGROUND: The integration of machine learning algorithms in decision support tools for physicians is gaining popularity. These tools can tackle the disparities in healthcare access as the technology can be implemented on smartphones. We present the first, large-scale study on patients with skin of colour, in which the feasibility of a novel mobile health application (mHealth app) was investigated in actual clinical workflows. OBJECTIVE: To develop a mHealth app to diagnose 40 common skin diseases and test it in clinical settings. METHODS: A convolutional neural network-based algorithm was trained with clinical images of 40 skin diseases. A smartphone app was generated and validated on 5014 patients, attending rural and urban outpatient dermatology departments in India. The results of this mHealth app were compared against the dermatologists' diagnoses. RESULTS: The machine-learning model, in an in silico validation study, demonstrated an overall top-1 accuracy of 76.93 ± 0.88% and mean area-under-curve of 0.95 ± 0.02 on a set of clinical images. In the clinical study, on patients with skin of colour, the app achieved an overall top-1 accuracy of 75.07% (95% CI = 73.75-76.36), top-3 accuracy of 89.62% (95% CI = 88.67-90.52) and mean area-under-curve of 0.90 ± 0.07. CONCLUSION: This study underscores the utility of artificial intelligence-driven smartphone applications as a point-of-care, clinical decision support tool for dermatological diagnosis for a wide spectrum of skin diseases in patients of the skin of colour.

Dysplasia epiphysealis hemimelica of the talus: two case reports.

Trevor's disease, also known as dysplasia epiphysealis hemimelica, is an uncommon skeletal developmental disorder representing an osteochondroma occurring in one or more epiphyses. We present 2 cases of dysplasia epiphysealis hemimelica in an 8-year-old female and a 12-year-old male who suffered from a hard swelling of the ankle joint. The female patient was treated by surgical excision and the male patient conservatively.

Silastic replacement of metacarpal after resection of giant cell tumour. A case report.

Giant cell tumours are aggressive lesions, albeit benign. Lesions in the hand, especially those arising from metacarpals require resection with adequate margins and definitive structural reconstructions to ensure preservation of hand architecture, function and cosmesis. Almost all the described reconstructive procedures require a stump of tumour free metacarpal base after resection, for reconstruction of the metacarpal. This report describes replacement of the entire metacarpal with a silastic prosthesis, in a case of giant cell tumour involving the entire metacarpal head and shaft to within 7 mm of the base.

An age- and sex-controlled matched pair analysis of T scores in ethnic Indians with hip fractures.

OBJECTIVE: The first study to predict peritrochanteric fractures by the use of T scores amongst the Indian population was performed. This study aimed to assess the risk of fracture around the hip in peri-menopausal and postmenopausal women, and in men over the age of 35 years using dual energy X-ray absorptiometry, and to analyse whether the result, i.e. the T score, can predict an impending hip fracture. METHODS: T scores of the unaffected hip in 30 patients with peritrochanteric fractures were determined, and matched pair analysis was done using a control group without fracture. All patients were from a single centre and were evaluated using the same scanner. RESULTS: The mean T score of the 30 patients in the fracture group was -3.34 (range, -1.2 to -5.1; standard deviation [SD], 1.032), compared with the mean T score of the 30 control subjects which was -2.41 (range, 0.6 to -5.0; SD, 1.378). T scores of patients from the fracture group were significantly lower than those in the control group. CONCLUSION: We infer that T scores are the best predictors for fracture risk. A score of -2.5 or lower effectively defines patients at risk and is useful for predicting fracture risk in the Indian population. In patients with osteoporosis, whether a fall precedes the fracture or the fracture precedes a fall may not be an issue of debate, but can serve as a basis for prevention of additional fractures by instituting appropriate measures in patients at risk.