Search

The rising prevalence of type 2 diabetes mellitus (T2DM) necessitates the development of predictive models for T2DM risk assessment. Artificial intelligence (AI) models are being extensively used for this purpose, but a comprehensive review of their advancements and challenges is lacking. This scoping review analyzes existing literature on AI-based models for T2DM risk prediction. Forty studies were included, mainly published in the past four years. Traditional machine learning models were more prevalent than deep learning models. Electronic health records were the most commonly used data source. Unimodal AI models relying on EHR data were prominent, while only a few utilized multimodal models. Both unimodal and multimodal models showed promising performance, with the latter outperforming the former. Internal validation was common, while external validation was limited. Interpretability methods were reported in half of the studies. Few studies reported novel biomarkers, and open-source code availability was limited. This review provides insights into the current state and limitations of AI-based T2DM risk prediction models and highlights challenges for their development and clinical implementation.

Artificial Intelligence (AI)-based models can help in diagnosing COVID-19 from lung CT scans and X-ray images; however, these models require large amounts of data for training and validation. Many researchers studied Generative Adversarial Networks (GANs) for producing synthetic lung CT scans and X-Ray images to improve the performance of AI-based models. It is not well explored how good GAN-based methods performed to generate reliable synthetic data. This work analyzes 43 published studies that reported GANs for synthetic data generation. Many of these studies suffered data bias, lack of reproducibility, and lack of feedback from the radiologists or other domain experts. A common issue in these studies is the unavailability of the source code, hindering reproducibility. The included studies reported rescaling of the input images to train the existing GANs architecture without providing clinical insights on how the rescaling was motivated. Finally, even though GAN-based methods have the potential for data augmentation and improving the training of AI-based models, these methods fall short in terms of their use in clinical practice. This paper highlights research hotspots in countering the data scarcity problem, identifies various issues as well as potentials, and provides recommendations to guide future research. These recommendations might be useful to improve acceptability for the GAN-based approaches for data augmentation as GANs for data augmentation are increasingly becoming popular in the AI and medical imaging research community., Comment: submitted to 2023 CVPR workshop on Generative Models for Computer Vision

Generative models are becoming popular for the synthesis of medical images. Recently, neural diffusion models have demonstrated the potential to generate photo-realistic images of objects. However, their potential to generate medical images is not explored yet. In this work, we explore the possibilities of synthesis of medical images using neural diffusion models. First, we use a pre-trained DALLE2 model to generate lungs X-Ray and CT images from an input text prompt. Second, we train a stable diffusion model with 3165 X-Ray images and generate synthetic images. We evaluate the synthetic image data through a qualitative analysis where two independent radiologists label randomly chosen samples from the generated data as real, fake, or unsure. Results demonstrate that images generated with the diffusion model can translate characteristics that are otherwise very specific to certain medical conditions in chest X-Ray or CT images. Careful tuning of the model can be very promising. To the best of our knowledge, this is the first attempt to generate lungs X-Ray and CT images using neural diffusion models. This work aims to introduce a new dimension in artificial intelligence for medical imaging. Given that this is a new topic, the paper will serve as an introduction and motivation for the research community to explore the potential of diffusion models for medical image synthesis. We have released the synthetic images on https://www.kaggle.com/datasets/hazrat/awesomelungs., Comment: 8 pages. Submitted to AICS 2022 conference

Supplemental material, sj-pdf-1-vas-10.1177_17085381211011357 for Nationwide study of six-month readmissions in critical limb ischemia: Predictors and impact of revascularization strategies by Prakash Acharya, Prince Sethi, Sagar Ranka, Adam Alli, Kirk Hance, Anand Prasad, Zubair Shah and Kamal Gupta in Vascular

Supplemental material, sj-pdf-1-vas-10.1177_17085381211011357 for Nationwide study of six-month readmissions in critical limb ischemia: Predictors and impact of revascularization strategies by Prakash Acharya, Prince Sethi, Sagar Ranka, Adam Alli, Kirk Hance, Anand Prasad, Zubair Shah and Kamal Gupta in Vascular

Contact tracing apps are powerful software tools that can help control the spread of COVID-19. In this article, we evaluated 53 COVID-19 contact tracing apps found on the Google Play Store in terms of their usage, rating, access permission, and user privacy. For each app included in the study, we identified the country of origin, number of downloads, and access permissions to further understand the attributes and ratings of the apps. Our results show that contact tracing apps had low overall ratings and nearly 40% of the included apps were requesting dangerous access permission including access to storage, media files, and camera permissions. We also found that user adoption rates were inversely correlated to access permission requirements. To the best of our knowledge, our article summarizes the most extensive collection of contact tracing apps for COVID-19. We recommend that future contact tracing apps should be more transparent in permission requirements and should provide justification for permissions requested to preserve the app users privacy., Comment: Contact Tracing Apps for COVID-19

Background: Tools used to appraise the credibility of health information are time-consuming to apply and require context-specific expertise, limiting their use for quickly identifying and mitigating the spread of misinformation as it emerges. Our aim was to estimate the proportion of vaccination-related posts on Twitter are likely to be misinformation, and how unevenly exposure to misinformation was distributed among Twitter users. Methods: Sampling from 144,878 vaccination-related web pages shared on Twitter between January 2017 and March 2018, we used a seven-point checklist adapted from two validated tools to appraise the credibility of a small subset of 474. These were used to train several classifiers (random forest, support vector machines, and a recurrent neural network with transfer learning), using the text from a web page to predict whether the information satisfies each of the seven criteria. Results: Applying the best performing classifier to the 144,878 web pages, we found that 14.4% of relevant posts to text-based communications were linked to webpages of low credibility and made up 9.2% of all potential vaccination-related exposures. However, the 100 most popular links to misinformation were potentially seen by between 2 million and 80 million Twitter users, and for a substantial sub-population of Twitter users engaging with vaccination-related information, links to misinformation appear to dominate the vaccination-related information to which they were exposed. Conclusions: We proposed a new method for automatically appraising the credibility of webpages based on a combination of validated checklist tools. The results suggest that an automatic credibility appraisal tool can be used to find populations at higher risk of exposure to misinformation or applied proactively to add friction to the sharing of low credibility vaccination information., Comment: 8 Pages, 5 Figures

Many data stream applications have hierarchical data; containing time, geographic locations, product information, clickstreams, server logs, IP addresses. A hierarchical summary of such volumous data offers multiple advantages including compactness, quick understanding, and abstraction. The goal of this thesis is to design algorithmic approaches for summarizing hierarchical data streams. First, this thesis provides a theoretical analysis of the benchmark hierarchical heavy hitters' algorithms and uncovers their shortcomings such as requiring high theoretical memory, updates and coverage problem. To address these shortcomings, this thesis proposes efficient algorithms which offer deterministic estimation accuracy using O(η/ε) worst-case memory and O(η) worst-case time complexity per item, where ε ∈ [0,1] is a user defined parameter and η is a small constant derived from the data. The proposed hierarchical heavy hitters' algorithms are shown to have improved significantly over existing algorithms both theoretically as well as empirically. Next, this thesis introduces a new concept called hierarchically correlated heavy hitters, which is different from existing hierarchical summarization techniques. The thesis provides a formal definition of the proposed concept and compares it with existing hierarchical summarization approaches both at definition level and empirically. It also proposes an efficient hierarchy-aware algorithm for computing hierarchically correlated heavy hitters. The proposed algorithm offers deterministic estimation accuracy using O(η / (ε_p * ε_s )) worst-case memory and O(η) worst-case time complexity per item, where η is as defined previously, and ε_p ∈ [0,1], ε_s ∈ [0,1] are other user defined parameters. Finally, the thesis proposes a special hierarchical data structure and algorithm to summarize spatiotemporal data. It can be used to extract interesting and useful patterns from high-speed spatiotemporal data streams at multiple spatial and temporal granularities. Theoretical and empirical analysis are provided, which show that the proposed data structure is very efficient concerning data storage and response to queries. It updates a single item in O(1) time and responds to a point query in O(1) time. Importantly, the memory requirement of the proposed data structure is independent of the size of the data and only depends on user-supplied parameters ψ ⃗ and φ ⃗. In summary, this thesis provides a general framework consisting of a set of algorithms and data structures to compute hierarchical summaries of the big data streams. All of the proposed algorithms exploit a lattice structure built from the hierarchical attributes of the data to compute different hierarchical summaries, which can be used to address various data analytic issues in many emerging applications.