arXiv subjects

Karandeep Singh

Publications and source records attributed to Karandeep Singh.

12 recordsLinked to original sources

arXiv2026

A global log for medical AI

Modern computer systems rely on syslog, a universal protocol that records critical events across heterogeneous infrastructure. Medicine's rapidly growing AI stack has no equivalent. As medicine deploys AI tools at scale, there is no standard way to record how, when, by whom, and for whom these models are used. Without such records, it is difficult to measure real-world performance and outcomes, detect adverse events, or identify bias and dataset drift. Here we introduce MedLog, a protocol for event-level logging of medical AI. Each time an AI model interacts with a human, another algorithm, or an automated workflow, MedLog creates a record. Each record contains nine core fields: header, model, user, target, inputs, artifacts, outputs, outcomes, and feedback. We apply MedLog across four deployments in the US, Switzerland, and Vietnam: ICU deterioration prediction, tetanus progression monitoring from wearable signals, automated sepsis quality reporting, and patient attendance prediction. MedLog records capture model behavior, workflow interactions, and downstream outcomes, including AI performance degradation during severe weather events in patient attendance prediction and increased laboratory testing after ICU deterioration alerts. MedLog limits the data footprint through risk-based sampling, lifecycle-aware retention policies, and write-behind caching, enabling deployment in low-resource settings. It also supports detailed traces for complex, agentic, or multi-stage workflows, creating a foundation for continuous monitoring, auditing, and improvement of medical AI.

cs.AI↗

arXiv2026

Temporal Coverage over Density: Parsimonious Training-Set Design for ML Climate Downscaling

High-resolution regional climate simulations provide critical information for climate impacts assessments but remain computationally expensive, motivating the development of machine-learning downscalers and emulators. A key challenge is determining how limited high-resolution simulations should be distributed across a changing climate trajectory to capture both forced climate response and internal variability. Using the CESM2 Large Ensemble over the western United States, we compare three training-year selection strategies under fixed data budgets: a contiguous block of historical years, years drawn from both the beginning and end of the simulation period, and years distributed throughout the full climate trajectory. Including both historical and future years consistently outperforms training on historical years alone, demonstrating the importance of exposing downscaling models to climate states outside the historical record and highlighting limitations of stationarity assumptions common in statistical downscaling. Training on years distributed throughout the full climate trajectory performs best overall, indicating that broad sampling of internal variability provides additional information beyond exposure to the forced climate response alone. Models trained on temporally distributed subsets more successfully reproduce variability in unseen ensemble members while retaining strong performance across a wide range of climate diagnostics. Even when trained on only one-tenth of the available high-resolution years, temporally distributed models remain highly competitive with full-data training. These results suggest that, under fixed computational budgets, broad sampling of climate states is more valuable than temporal continuity when allocating scarce high-resolution simulations. The findings provide practical guidance for regional climate downscaling and large-ensemble projection workflows.

cs.LG↗

arXiv2025

Learning optimal treatment strategies for intraoperative hypotension using deep reinforcement learning

Traditional methods of surgical decision making heavily rely on human experience and prompt actions, which are variable. A data-driven system generating treatment recommendations based on patient states can be a substantial asset in perioperative decision-making, as in cases of intraoperative hypotension, for which suboptimal management is associated with acute kidney injury (AKI), a common and morbid postoperative complication. We developed a Reinforcement Learning (RL) model to recommend optimum dose of intravenous (IV) fluid and vasopressors during surgery to avoid intraoperative hypotension and postoperative AKI. We retrospectively analyzed 50,021 surgeries from 42,547 adult patients who underwent major surgery at a quaternary care hospital between June 2014 and September 2020. Of these, 34,186 surgeries were used for model training and 15,835 surgeries were reserved for testing. We developed a Deep Q-Networks based RL model using 16 variables including intraoperative physiologic time series, total dose of IV fluid and vasopressors extracted for every 15-minute epoch. The model replicated 69% of physician's decisions for the dosage of vasopressors and proposed higher or lower dosage of vasopressors than received in 10% and 21% of the treatments, respectively. In terms of IV fluids, the model's recommendations were within 0.05 ml/kg/15 min of the actual dose in 41% of the cases, with higher or lower doses recommended for 27% and 32% of the treatments, respectively. The model resulted in a higher estimated policy value compared to the physicians' actual treatments, as well as random and zero-drug policies. AKI prevalence was the lowest in patients receiving medication dosages that aligned with model's decisions. Our findings suggest that implementation of the model's policy has the potential to reduce postoperative AKI and improve other outcomes driven by intraoperative hypotension.

q-bio.QM↗

arXiv2024

Performance evaluation of predictive AI models to support medical decisions: Overview and guidance

A myriad of measures to illustrate performance of predictive artificial intelligence (AI) models have been proposed in the literature. Selecting appropriate performance measures is essential for predictive AI models that are developed to be used in medical practice, because poorly performing models may harm patients and lead to increased costs. We aim to assess the merits of classic and contemporary performance measures when validating predictive AI models for use in medical practice. We focus on models with a binary outcome. We discuss 32 performance measures covering five performance domains (discrimination, calibration, overall, classification, and clinical utility) along with accompanying graphical assessments. The first four domains cover statistical performance, the fifth domain covers decision-analytic performance. We explain why two key characteristics are important when selecting which performance measures to assess: (1) whether the measure's expected value is optimized when it is calculated using the correct probabilities (i.e., a "proper" measure), and (2) whether they reflect either purely statistical performance or decision-analytic performance by properly considering misclassification costs. Seventeen measures exhibit both characteristics, fourteen measures exhibited one characteristic, and one measure possessed neither characteristic (the F1 measure). All classification measures (such as classification accuracy and F1) are improper for clinically relevant decision thresholds other than 0.5 or the prevalence. We recommend the following measures and plots as essential to report: AUROC, calibration plot, a clinical utility measure such as net benefit with decision curve analysis, and a plot with probability distributions per outcome category.

cs.LG↗

arXiv2024

Self Supervised Vision for Climate Downscaling

Climate change is one of the most critical challenges that our planet is facing today. Rising global temperatures are already bringing noticeable changes to Earth's weather and climate patterns with an increased frequency of unpredictable and extreme weather events. Future projections for climate change research are based on Earth System Models (ESMs), the computer models that simulate the Earth's climate system. ESMs provide a framework to integrate various physical systems, but their output is bound by the enormous computational resources required for running and archiving higher-resolution simulations. For a given resource budget, the ESMs are generally run on a coarser grid, followed by a computationally lighter $downscaling$ process to obtain a finer-resolution output. In this work, we present a deep-learning model for downscaling ESM simulation data that does not require high-resolution ground truth data for model optimization. This is realized by leveraging salient data distribution patterns and the hidden dependencies between weather variables for an $\textit{individual}$ data point at $\textit{runtime}$. Extensive evaluation with $2$x, $3$x, and $4$x scaling factors demonstrates that the proposed model consistently obtains superior performance over that of various baselines. The improved downscaling performance and no dependence on high-resolution ground truth data make the proposed method a valuable tool for climate research and mark it as a promising direction for future research.

physics.ao-ph↗

arXiv2023

Generating High-Resolution Regional Precipitation Using Conditional Diffusion Model

Climate downscaling is a crucial technique within climate research, serving to project low-resolution (LR) climate data to higher resolutions (HR). Previous research has demonstrated the effectiveness of deep learning for downscaling tasks. However, most deep learning models for climate downscaling may not perform optimally for high scaling factors (i.e., 4x, 8x) due to their limited ability to capture the intricate details required for generating HR climate data. Furthermore, climate data behaves differently from image data, necessitating a nuanced approach when employing deep generative models. In response to these challenges, this paper presents a deep generative model for downscaling climate data, specifically precipitation on a regional scale. We employ a denoising diffusion probabilistic model (DDPM) conditioned on multiple LR climate variables. The proposed model is evaluated using precipitation data from the Community Earth System Model (CESM) v1.2.2 simulation. Our results demonstrate significant improvements over existing baselines, underscoring the effectiveness of the conditional diffusion model in downscaling climate data.

cs.LG↗

arXiv2023

An AI-Guided Data Centric Strategy to Detect and Mitigate Biases in Healthcare Datasets

The adoption of diagnosis and prognostic algorithms in healthcare has led to concerns about the perpetuation of bias against disadvantaged groups of individuals. Deep learning methods to detect and mitigate bias have revolved around modifying models, optimization strategies, and threshold calibration with varying levels of success. Here, we generate a data-centric, model-agnostic, task-agnostic approach to evaluate dataset bias by investigating the relationship between how easily different groups are learned at small sample sizes (AEquity). We then apply a systematic analysis of AEq values across subpopulations to identify and mitigate manifestations of racial bias in two known cases in healthcare - Chest X-rays diagnosis with deep convolutional neural networks and healthcare utilization prediction with multivariate logistic regression. AEq is a novel and broadly applicable metric that can be applied to advance equity by diagnosing and remediating bias in healthcare datasets.

cs.LG↗

arXiv2023

GraphFC: Customs Fraud Detection with Label Scarcity

Custom officials across the world encounter huge volumes of transactions. With increased connectivity and globalization, the customs transactions continue to grow every year. Associated with customs transactions is the customs fraud - the intentional manipulation of goods declarations to avoid the taxes and duties. With limited manpower, the custom offices can only undertake manual inspection of a limited number of declarations. This necessitates the need for automating the customs fraud detection by machine learning (ML) techniques. Due the limited manual inspection for labeling the new-incoming declarations, the ML approach should have robust performance subject to the scarcity of labeled data. However, current approaches for customs fraud detection are not well suited and designed for this real-world setting. In this work, we propose $\textbf{GraphFC}$ ($\textbf{Graph}$ neural networks for $\textbf{C}$ustoms $\textbf{F}$raud), a model-agnostic, domain-specific, semi-supervised graph neural network based customs fraud detection algorithm that has strong semi-supervised and inductive capabilities. With upto 252% relative increase in recall over the present state-of-the-art, extensive experimentation on real customs data from customs administrations of three different countries demonstrate that GraphFC consistently outperforms various baselines and the present state-of-art by a large margin.

cs.LG↗

arXiv2022

Active Learning for Human-in-the-Loop Customs Inspection

We study the human-in-the-loop customs inspection scenario, where an AI-assisted algorithm supports customs officers by recommending a set of imported goods to be inspected. If the inspected items are fraudulent, the officers can levy extra duties. Th formed logs are then used as additional training data for successive iterations. Choosing to inspect suspicious items first leads to an immediate gain in customs revenue, yet such inspections may not bring new insights for learning dynamic traffic patterns. On the other hand, inspecting uncertain items can help acquire new knowledge, which will be used as a supplementary training resource to update the selection systems. Based on multiyear customs datasets obtained from three countries, we demonstrate that some degree of exploration is necessary to cope with domain shifts in trade data. The results show that a hybrid strategy of selecting likely fraudulent and uncertain items will eventually outperform the exploitation-only strategy.

cs.LG↗

arXiv2021

The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning

The Internet of Things (IoT) is on the verge of a major paradigm shift. In the IoT system of the future, IoFT, the cloud will be substituted by the crowd where model training is brought to the edge, allowing IoT devices to collaboratively extract knowledge and build smart analytics/models while keeping their personal data stored locally. This paradigm shift was set into motion by the tremendous increase in computational power on IoT devices and the recent advances in decentralized and privacy-preserving model training, coined as federated learning (FL). This article provides a vision for IoFT and a systematic overview of current efforts towards realizing this vision. Specifically, we first introduce the defining characteristics of IoFT and discuss FL data-driven approaches, opportunities, and challenges that allow decentralized inference within three dimensions: (i) a global model that maximizes utility across all IoT devices, (ii) a personalized model that borrows strengths across all devices yet retains its own model, (iii) a meta-learning model that quickly adapts to new devices or learning tasks. We end by describing the vision and challenges of IoFT in reshaping different industries through the lens of domain experts. Those industries include manufacturing, transportation, energy, healthcare, quality & reliability, business, and computing.

cs.LG↗

arXiv2021

Misinformation, Believability, and Vaccine Acceptance Over 40 Countries: Takeaways From the Initial Phase of The COVID-19 Infodemic

The COVID-19 pandemic has been damaging to the lives of people all around the world. Accompanied by the pandemic is an infodemic, an abundant and uncontrolled spreading of potentially harmful misinformation. The infodemic may severely change the pandemic's course by interfering with public health interventions such as wearing masks, social distancing, and vaccination. In particular, the impact of the infodemic on vaccination is critical because it holds the key to reverting to pre-pandemic normalcy. This paper presents findings from a global survey on the extent of worldwide exposure to the COVID-19 infodemic, assesses different populations' susceptibility to false claims, and analyzes its association with vaccine acceptance. Based on responses gathered from over 18,400 individuals from 40 countries, we find a strong association between perceived believability of misinformation and vaccination hesitancy. Additionally, our study shows that only half of the online users exposed to rumors might have seen the fact-checked information. Moreover, depending on the country, between 6% and 37% of individuals considered these rumors believable. Our survey also shows that poorer regions are more susceptible to encountering and believing COVID-19 misinformation. We discuss implications of our findings on public campaigns that proactively spread accurate information to countries that are more susceptible to the infodemic. We also highlight fact-checking platforms' role in better identifying and prioritizing claims that are perceived to be believable and have wide exposure. Our findings give insights into better handling of risk communication during the initial phase of a future pandemic.

cs.SI↗

arXiv2020

Risk Communication in Asian Countries: COVID-19 Discourse on Twitter

COVID-19 has become one of the most widely talked about topics on social media. This research characterizes risk communication patterns by analyzing the public discourse on the novel coronavirus from four Asian countries: South Korea, Iran, Vietnam, and India, which suffered the outbreak to different degrees. The temporal analysis shows that the official epidemic phases issued by governments do not match well with the online attention on COVID-19. This finding calls for a need to analyze the public discourse by new measures, such as topical dynamics. Here, we propose an automatic method to detect topical phase transitions and compare similarities in major topics across these countries over time. We examine the time lag difference between social media attention and confirmed patient counts. For dynamics, we find an inverse relationship between the tweet count and topical diversity.

cs.SI↗