Subhrajit Roy
YOU?
Author Swipe
The Effect of Suggestive Cues in Influencing Human Perception Open
Suggestion is the medium through information of a perspective is shared. The act suggestion, conveyed through verbal, visual, or sensory cues, alters an individual’s behaviour or actions, defined as social influence. This research focuses …
Performance of machine learning models for predicting high-severity symptoms in multiple sclerosis Open
Current care in multiple sclerosis (MS) primarily relies on infrequently obtained data such as magnetic resonance imaging, clinical laboratory tests or clinical history, resulting in subtle changes that may occur between visits being misse…
Role of Cholesterol in Formation of Amyloid Plaques in Alzheimer’s Disease Open
Amyloid plaques are one of the key reasons in progression of Alzheimer’s disease (AD) being one of the leading causes of dementia. Recent studies have shown evidence to the levels of cholesterol playing an important role in the formation o…
Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering Open
Prompting and in-context learning (ICL) have become efficient learning paradigms for large language models (LLMs). However, LLMs suffer from prompt brittleness and various bias factors in the prompt, including but not limited to the format…
STUDY: Socially Aware Temporally Causal Decoder Recommender Systems Open
Recommender systems are widely used to help people find items that are tailored to their interests. These interests are often influenced by social networks, making it important to use social network information effectively in recommender s…
Benchmarking Continuous Time Models for Predicting Multiple Sclerosis Progression Open
Multiple sclerosis is a disease that affects the brain and spinal cord, it can lead to severe disability and has no known cure. The majority of prior work in machine learning for multiple sclerosis has been centered around using Magnetic R…
Performance of Machine Learning Models for Predicting High-Severity Symptoms in Multiple Sclerosis Open
Current care in multiple sclerosis (MS) primarily relies on infrequently obtained data such as magnetic resonance imaging (MRI), clinical laboratory tests or clinical history, resulting in subtle changes that may occur between visits being…
Developing robust benchmarks for driving forward AI innovation in healthcare Open
Machine learning technologies have seen increased application to the healthcare domain. The main drivers are openly available healthcare datasets, and a general interest from the community to use its powers for knowledge discovery and tech…
View article: Boosting the interpretability of clinical risk scores with intervention predictions
Boosting the interpretability of clinical risk scores with intervention predictions Open
Machine learning systems show significant promise for forecasting patient adverse events via risk scores. However, these risk scores implicitly encode assumptions about future interventions that the patient is likely to receive, based on t…
Healthsheet: Development of a Transparency Artifact for Health Datasets Open
Machine learning (ML) approaches have demonstrated promising results in a wide range of healthcare applications. Data plays a crucial role in developing ML-based healthcare systems that directly affect people's lives. Many of the ethical i…
A Research Paper on Biometric based ATM System Open
Biometrics-based authentication is a potential alternative to password-based authentication. Of all biometric methods, face-based identification is one of the most convenient one. In ATM systems, facial images are captured using a high res…
Disability prediction in multiple sclerosis using performance outcome measures and demographic data Open
Literature on machine learning for multiple sclerosis has primarily focused on the use of neuroimaging data such as magnetic resonance imaging and clinical laboratory tests for disease identification. However, studies have shown that these…
Biometric based ATM System: A Survey Open
Biometrics-based authentication is a potential alternative to password-based authentication. Of all biometric methods, face-based identification is one of the most convenient one. In ATM systems, facial images are captured using a high res…
Healthsheet: Development of a Transparency Artifact for Health Datasets Open
Machine learning (ML) approaches have demonstrated promising results in a wide range of healthcare applications. Data plays a crucial role in developing ML-based healthcare systems that directly affect people's lives. Many of the ethical i…
View article: Diagnosing failures of fairness transfer across distribution shift in real-world medical settings
Diagnosing failures of fairness transfer across distribution shift in real-world medical settings Open
Diagnosing and mitigating changes in model fairness under distribution shift is an important component of the safe deployment of machine learning in healthcare settings. Importantly, the success of any mitigation strategy strongly depends …
A collection of the accepted abstracts for the Machine Learning for Health (ML4H) symposium 2021 Open
A collection of the accepted abstracts for the Machine Learning for Health (ML4H) symposium 2021. This index is not complete, as some accepted abstracts chose to opt-out of inclusion.
Seizure detection using wearable sensors and machine learning: Setting a benchmark Open
Objective Tracking seizures is crucial for epilepsy monitoring and treatment evaluation. Current epilepsy care relies on caretaker seizure diaries, but clinical seizure monitoring may miss seizures. Wearable devices may be better tolerated…
Multitask prediction of organ dysfunction in the intensive care unit using sequential subnetwork routing Open
Objective Multitask learning (MTL) using electronic health records allows concurrent prediction of multiple endpoints. MTL has shown promise in improving model performance and training efficiency; however, it often suffers from negative tr…
Seizure Type Classification Using EEG Signals and Machine Learning: Setting a Benchmark Open
Accurate classification of seizure types plays a crucial role in the treatment and disease management of epileptic patients. Epileptic seizure types not only impact the choice of drugs but also the range of activities a patient can safely …
ML4H Abstract Track 2020 Open
A collection of the accepted abstracts for the Machine Learning for Health (ML4H) workshop at NeurIPS 2020. This index is not complete, as some accepted abstracts chose to opt-out of inclusion.
Type-Driven Automated Learning with Lale Open
Machine-learning automation tools, ranging from humble grid-search to hyperopt, auto-sklearn, and TPOT, help explore large search spaces of possible pipelines. Unfortunately, each of these tools has a different syntax for specifying its se…
A semi-supervised deep learning algorithm for abnormal EEG identification Open
Systems that can automatically analyze EEG signals can aid neurologists by reducing heavy workload and delays. However, such systems need to be first trained using a labeled dataset. While large corpuses of EEG data exist, a fraction of th…
Machine Learning for removing EEG artifacts: Setting the benchmark Open
Electroencephalograms (EEG) are often contaminated by artifacts which make interpreting them more challenging for clinicians. Hence, automated artifact recognition systems have the potential to aid the clinical workflow. In this abstract, …
Seizure Type Classification using EEG signals and Machine Learning:\n Setting a benchmark Open
Accurate classification of seizure types plays a crucial role in the\ntreatment and disease management of epileptic patients. Epileptic seizure types\nnot only impact the choice of drugs but also the range of activities a patient\ncan safe…
ChronoNet: A Deep Recurrent Neural Network for Abnormal EEG\n Identification Open
Brain-related disorders such as epilepsy can be diagnosed by analyzing\nelectroencephalograms (EEG). However, manual analysis of EEG data requires\nhighly trained clinicians, and is a procedure that is known to have relatively\nlow inter-r…