arXiv subjects

John Kelly

Publications and source records attributed to John Kelly.

10 recordsLinked to original sources

arXiv2026

AI-driven Optimisation of Quality of Recovery (QoR) in Remote Patient Monitoring

Remote patient monitoring depends on patient-reported data to capture the subjective dimension of recovery that devices cannot measure. The Quality of Recovery (QoR-15) survey is the gold-standard instrument for this purpose. It was designed and validated for occasional in-hospital assessment, yet remote monitoring now administers it to patients daily. In our own post-surgical deployment, only 55% of patients submitted the survey more than 14 days of 30 monitoring days. We developed QoR-compact, a five-item daily input for the RPM prediction pathway. Setting a deployment-driven target of one-third of the daily items, we exhaustively evaluated all 3,003 five-question subsets of the QoR-15 and tested whether the best of them matches the full instrument in predicting near-term postoperative recovery severity. QoR-compact achieves a mean AUC-ROC of 0.968 (95% CI 0.915-0.988), statistically comparable to the 0.964 baseline obtained with one-third of the items. Patient-level backtesting indicates that it tracks readmission events as faithfully as the full form. Its five items span the physical and psychological axes of recovery: Q3 (feeling rested), Q9 (feeling comfortable and in control), Q10 (general well-being), Q12 (severe pain), and Q14 (feeling worried or anxious). The QoR-15 remains the gold-standard measure of recovery; QoR-compact complements it as a shorter daily input designed for prediction. This parity provides the basis for a prospective study of whether a lighter daily input is, in turn, completed more consistently. External validation on larger cohorts is required before clinical use.

cs.AI↗

arXiv2025

Multi-Modal AI for Remote Patient Monitoring in Cancer Care

For patients undergoing systemic cancer therapy, the time between clinic visits is full of uncertainties and risks of unmonitored side effects. To bridge this gap in care, we developed and prospectively trialed a multi-modal AI framework for remote patient monitoring (RPM). This system integrates multi-modal data from the HALO-X platform, such as demographics, wearable sensors, daily surveys, and clinical events. Our observational trial is one of the largest of its kind and has collected over 2.1 million data points (6,080 patient-days) of monitoring from 84 patients. We developed and adapted a multi-modal AI model to handle the asynchronous and incomplete nature of real-world RPM data, forecasting a continuous risk of future adverse events. The model achieved an accuracy of 83.9% (AUROC=0.70). Notably, the model identified previous treatments, wellness check-ins, and daily maximum heart rate as key predictive features. A case study demonstrated the model's ability to provide early warnings by outputting escalating risk profiles prior to the event. This work establishes the feasibility of multi-modal AI RPM for cancer care and offers a path toward more proactive patient support.(Accepted at Europe NeurIPS 2025 Multimodal Representation Learning for Healthcare Workshop. Best Paper Poster Award.)

cs.LG↗

arXiv2025

Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment

Automated surgical skill assessment (SSA) is a central task in surgical computer vision. Developing robust SSA models is challenging due to the scarcity of skill annotations, which are time-consuming to produce and require expert consensus. Few-shot learning (FSL) offers a scalable alternative enabling model development with minimal supervision, though its success critically depends on effective pre-training. While widely studied for several surgical downstream tasks, pre-training has remained largely unexplored in SSA. In this work, we formulate SSA as a few-shot task and investigate how self-supervised pre-training strategies affect downstream few-shot SSA performance. We annotate a publicly available robotic surgery dataset with Objective Structured Assessment of Technical Skill (OSATS) scores, and evaluate various pre-training sources across three few-shot settings. We quantify domain similarity and analyze how domain gap and the inclusion of procedure-specific data into pre-training influence transferability. Our results show that small but domain-relevant datasets can outperform large scale, less aligned ones, achieving accuracies of 60.16%, 66.03%, and 73.65% in the 1-, 2-, and 5-shot settings, respectively. Moreover, incorporating procedure-specific data into pre-training with a domain-relevant external dataset significantly boosts downstream performance, with an average gain of +1.22% in accuracy and +2.28% in F1-score; however, applying the same strategy with less similar but large-scale sources can instead lead to performance degradation. Code and models are available at https://github.com/anastadimi/ssa-fsl.

cs.CV↗

arXiv2025

Fine-Tuning Federated Learning-Based Intrusion Detection Systems for Transportation IoT

The rapid advancement of machine learning (ML) and on-device computing has revolutionized various industries, including transportation, through the development of Connected and Autonomous Vehicles (CAVs) and Intelligent Transportation Systems (ITS). These technologies improve traffic management and vehicle safety, but also introduce significant security and privacy concerns, such as cyberattacks and data breaches. Traditional Intrusion Detection Systems (IDS) are increasingly inadequate in detecting modern threats, leading to the adoption of ML-based IDS solutions. Federated Learning (FL) has emerged as a promising method for enabling the decentralized training of IDS models on distributed edge devices without sharing sensitive data. However, deploying FL-based IDS in CAV networks poses unique challenges, including limited computational and memory resources on edge devices, competing demands from critical applications such as navigation and safety systems, and the need to scale across diverse hardware and connectivity conditions. To address these issues, we propose a hybrid server-edge FL framework that offloads pre-training to a central server while enabling lightweight fine-tuning on edge devices. This approach reduces memory usage by up to 42%, decreases training times by up to 75%, and achieves competitive IDS accuracy of up to 99.2%. Scalability analyses further demonstrates minimal performance degradation as the number of clients increase, highlighting the framework's feasibility for CAV networks and other IoT applications.

cs.LG↗

arXiv2021

Early Melanoma Diagnosis with Sequential Dermoscopic Images

Dermatologists often diagnose or rule out early melanoma by evaluating the follow-up dermoscopic images of skin lesions. However, existing algorithms for early melanoma diagnosis are developed using single time-point images of lesions. Ignoring the temporal, morphological changes of lesions can lead to misdiagnosis in borderline cases. In this study, we propose a framework for automated early melanoma diagnosis using sequential dermoscopic images. To this end, we construct our method in three steps. First, we align sequential dermoscopic images of skin lesions using estimated Euclidean transformations, extract the lesion growth region by computing image differences among the consecutive images, and then propose a spatio-temporal network to capture the dermoscopic changes from aligned lesion images and the corresponding difference images. Finally, we develop an early diagnosis module to compute probability scores of malignancy for lesion images over time. We collected 179 serial dermoscopic imaging data from 122 patients to verify our method. Extensive experiments show that the proposed model outperforms other commonly used sequence models. We also compared the diagnostic results of our model with those of seven experienced dermatologists and five registrars. Our model achieved higher diagnostic accuracy than clinicians (63.69% vs. 54.33%, respectively) and provided an earlier diagnosis of melanoma (60.7% vs. 32.7% of melanoma correctly diagnosed on the first follow-up images). These results demonstrate that our model can be used to identify melanocytic lesions that are at high-risk of malignant transformation earlier in the disease process and thereby redefine what is possible in the early detection of melanoma.

eess.IV↗

arXiv2020

Melanoma Diagnosis with Spatio-Temporal Feature Learning on Sequential Dermoscopic Images

Existing studies for automated melanoma diagnosis are based on single-time point images of lesions. However, melanocytic lesions de facto are progressively evolving and, moreover, benign lesions can progress into malignant melanoma. Ignoring cross-time morphological changes of lesions thus may lead to misdiagnosis in borderline cases. Based on the fact that dermatologists diagnose ambiguous skin lesions by evaluating the dermoscopic changes over time via follow-up examination, in this study, we propose an automated framework for melanoma diagnosis using sequential dermoscopic images. To capture the spatio-temporal characterization of dermoscopic evolution, we construct our model in a two-stream network architecture which capable of simultaneously learning appearance representations of individual lesions while performing temporal reasoning on both raw pixels difference and abstract features difference. We collect 184 cases of serial dermoscopic image data, which consists of histologically confirmed 92 benign lesions and 92 melanoma lesions, to evaluate the effectiveness of the proposed method. Our model achieved AUC of 74.34%, which is ~8% higher than that of only using single images and ~6% higher than the widely used sequence learning model based on LSTM.

cs.CV↗

arXiv2018

Higher Order of Motion Magnification for Vessel Localisation in Surgical Video

Locating vessels during surgery is critical for avoiding inadvertent damage, yet vasculature can be difficult to identify. Video motion magnification can potentially highlight vessels by exaggerating subtle motion embedded within the video to become perceivable to the surgeon. In this paper, we explore a physiological model of artery distension to extend motion magnification to incorporate higher orders of motion, leveraging the difference in acceleration over time (jerk) in pulsatile motion to highlight the vascular pulse wave. Our method is compared to first and second order motion based Eulerian video magnification algorithms. Using data from a surgical video retrieved during a robotic prostatectomy, we show that our method can accentuate cardio-physiological features and produce a more succinct and clearer video for motion magnification, with more similarities in areas without motion to the source video at large magnifications. We validate the approach with a Structure Similarity (SSIM) and Peak Signal to Noise Ratio (PSNR) assessment of three videos at an increasing working distance, using three different levels of optical magnification. Spatio-temporal cross sections are presented to show the effectiveness of our proposal and video samples are provided to demonstrates qualitatively our results.

cs.CV↗

arXiv2018

Polarization, Partisanship and Junk News Consumption over Social Media in the US

What kinds of social media users read junk news? We examine the distribution of the most significant sources of junk news in the three months before President Donald Trump first State of the Union Address. Drawing on a list of sources that consistently publish political news and information that is extremist, sensationalist, conspiratorial, masked commentary, fake news and other forms of junk news, we find that the distribution of such content is unevenly spread across the ideological spectrum. We demonstrate that (1) on Twitter, a network of Trump supporters shares the widest range of known junk news sources and circulates more junk news than all the other groups put together; (2) on Facebook, extreme hard right pages, distinct from Republican pages, share the widest range of known junk news sources and circulate more junk news than all the other audiences put together; (3) on average, the audiences for junk news on Twitter share a wider range of known junk news sources than audiences on Facebook public pages.

cs.SI↗

arXiv2018

Junk News on Military Affairs and National Security: Social Media Disinformation Campaigns Against US Military Personnel and Veterans

Social media provides political news and information for both active duty military personnel and veterans. We analyze the subgroups of Twitter and Facebook users who spend time consuming junk news from websites that target US military personnel and veterans with conspiracy theories, misinformation, and other forms of junk news about military affairs and national security issues. (1) Over Twitter we find that there are significant and persistent interactions between current and former military personnel and a broad network of extremist, Russia-focused, and international conspiracy subgroups. (2) Over Facebook, we find significant and persistent interactions between public pages for military and veterans and subgroups dedicated to political conspiracy, and both sides of the political spectrum. (3) Over Facebook, the users who are most interested in conspiracy theories and the political right seem to be distributing the most junk news, whereas users who are either in the military or are veterans are among the most sophisticated news consumers, and share very little junk news through the network.

cs.SI↗

arXiv2015

Nuclear Data Needs and Capabilities for Applications

The Workshop on Nuclear Data Needs and Capabilities for Applications (NDNCA) was held at Lawrence Berkeley National Laboratory (LBNL) on 27-29 May 2015. The goals of NDNCA were compile nuclear data needs across a wide spectrum of applied nuclear science, and to provide a summary of associated capabilities (accelerators, reactors, spectrometers, etc.) available for required measurements. This document represents the results of the workshop and a compilation of other recent documents assessing nuclear data needs for the above-mentioned applications.

nucl-ex↗