Nipun Kwatra

Dry Eye Disease (DED) is an eye condition characterized by abnormalities in tear film stability. Despite its high prevalence, screening for DED remains challenging, primarily due to the invasive nature of most diagnostic tests. The Fluorescein Break-Up Time (FBUT) test, which involves instilling fluorescein dye in the eye, is a widely used method for assessing tear film stability. In this work, we propose DEDector, a low-cost, smartphone-based automated Non-Invasive Break-Up Time (NIBUT) measurement for DED screening. Utilizing a 3D-printed Placido ring attachment on a smartphone's camera, DEDector projects concentric rings onto the cornea, capturing a video for subsequent analysis using our proposed video processing pipeline to identify tear film stability. We conducted a real-world evaluation on 46 eyes, comparing DEDector with the traditional FBUT method. DEDector achieved a sensitivity of 77.78% and specificity of 82.14%, outperforming FBUT.

Deep Learning training jobs process large amounts of training data using many GPU devices, often running for weeks or months. When hardware or software failures happen, these jobs need to restart, losing the memory state for the Deep Neural Network (DNN) model trained so far, unless checkpointing mechanisms are used to save training state periodically. However, for large models, periodic checkpointing incurs significant steady state overhead, and during recovery, a large number of GPUs need to redo work since the last checkpoint. This is especially problematic when failures are frequent for large DNN (such as Large Language Model) training jobs using many GPUs. In this paper, we present a novel approach of just-in-time checkpointing when failures happen, which enables recovery from failures with just a single minibatch iteration of work replayed by all GPUs. This reduces the cost of error recovery from several minutes to a few seconds per GPU, with nearly zero steady state overhead. This also avoids the guesswork of choosing a checkpointing frequency since failure rates usually have high variance. We discuss how just-in-time checkpointing can be enabled in training code, as well as design of key mechanisms for transparent just-in-time checkpointing without user code change. We analyze the wasted GPU work of just-in-time checkpointing and show that it is less than periodic checkpointing for large numbers of GPUs. We present results from our implementation in modern AI cluster infrastructure.

The growing platformization of health has spurred new avenues for healthcare access and reinvigorated telemedicine as a viable pathway to care. Telemedicine adoption during the COVID-19 pandemic has surfaced barriers to patient-centered care that call for attention. Our work extends current Human-Computer Interaction (HCI) research on telemedicine and the challenges to remote care, and investigates the scope for enhancing remote care seeking and provision through telemedicine workflows involving intermediation. Our study, focused on the urban Indian context, involved providing doctors with videos of remote clinical examinations to aid in telemedicine. We present a qualitative evaluation of this modified telemedicine experience, highlighting how workflows involving intermediation could bridge existing gaps in telemedicine, and how their acceptance among doctors could shift interaction dynamics between doctors and patients. We conclude by discussing the implications of such telemedicine workflows on patient-centered care and the future of care work.