Statistical considerations for testing an AI algorithm used for prescreening lung CT images

Automated decision-making by AI algorithms is increasingly likely to cause civil liability. However, AI algorithms based on machine learning techniques are less explainable due to technical inscrutability arising from the nature of the learning methods itself, legal opacity due to protection of trade secrets or intellectual property rights, or incomprehensibility of the general public or judges due to the complexity and counterintuitiveness of algorithms, thus making its judicial review difficult. When the mechanism of an AI algorithm is at issue in a lawsuit, the question is how an opaque AI algorithm can be evaluated by experts and reviewed by a court. This article first introduces ACCC v. Trivago decision made by the Federal Court of Australia in 2020, focusing on how the experts appointed by each party presented their opinions on the AI algorithm and how the court drew its conclusion based on their opinions. It then studies issues and solutions that may arise in examining opaque AI algorithms in the Korean civil litigation procedures, making comparison with the Trivago decision. It explains basic features of Explainable AI(XAI) methods including Ante hoc methods and post hoc methods. It then points out problems of the Civil Procedure Act and Intellectual Property laws of South Korea in disclosing data necessary for the experts’ analysis on the AI algorithms and in protecting the trade secrets contained in the produced data, and makes suggestions on how to solve those problems. Lastly, it recommends a more active use of party-appointed experts in the judicial review of the AI algorithms by allowing their active participations throughout the litigation procedure in order to clarify issues and deepen the court’s scientific understanding.

In the world of trading and complex market transactions, technology has greatly revolutionized and adapted to the fast-growing data and complexities of modern trading strategies. Computers and advanced algorithms have paved the way for a more digitalized world where virtual transactions are common place. Not only can people buy and sell products online, but can also do these transactions automatically. However, thanks to complex AI and ML algorithms; high-frequency trading or HFT strategies can be formulated for highly efficient and optimized automated trading. There are various HFT firms that uses complex ML and AI algorithms to identify and dynamically adjust buying or selling prices according to available market data to maximize profit and save time. Various businesses can take advantage of HFT strategies to optimize selling and buying frequencies. Relevant data is required for executing a HFT strategy properly, along with a sophisticated AI algorithm which is capable of handling vast amounts of data dynamically. The key features of HFT makes it a compelling route for optimized trading and buying. These key features include: lightning-fast transactions, dynamic market data analysis and execution of numerous transactions at once. This research paper aims to understand how AI and ML algorithms can dynamically optimize HFT strategies to further take leverage of available market data. The research paper discusses the implementation of Deep Reinforcement Learning or DLL framework for optimizing HFT strategies. In particular, the implementation discussed adopts a multi-time scale DRL for improved dynamic data processing. This research paper aims to shed light into the effectiveness of an AI-driven solution for improving HFT efficiency for better and faster trading using a simple deep reinforcement learning or DRL machine learning algorithm.

Bots can be broadly divided into two categories: chat bots and smart bots. Chat bots respond using a predefined set of rules and hence the responses are limited. For example, if you build a bot for reserving a table in a restaurant, the bot would always ask the basic questions of date and time, number of people, and seating preference (indoor/outdoor). If you throw a random request at the chat bot, it might not respond with a meaningful message or might just respond with a generic message. Smart bots are more intelligent. They work with a wide variety of information and generate more human-like responses. Smart bots are designed to learn from the conversation and provide more-useful answers as the conversation progresses, leaving the impression of a human-to-human conversation. Bots can be designed to create smarter responses by using cutting-edge artificial intelligence algorithms. Authoring AI algorithms is a complex task, requiring a varied skill set and lots of analysis to build an AI algorithm that can perform tasks like natural language processing and sentiment analysis or generate recommendations. Microsoft Cognitive Services provides a basket of AI algorithms that can be integrated into any application. These algorithms were developed by an expert team and cater across the fields of computer vision, speech, text analysis, natural language processing, knowledge extraction, and web search. In this chapter, we will learn to build smarter bots using Microsoft Cognitive Services and come to understand the capabilities of the evolving list of powerful AI algorithms.

Introduction: In digital pathology, large amounts of time and money are spent annotating whole slide images (WSIs). By using an AI algorithm trained on thousands of WSIs, it is possible to remove the process of annotating from the workflow whilst simultaneously finding potential imaging features that correlate with drug response, molecular phenotypes, histologic features (e.g. Tertiary Lymphoid Structures), inflammation at the tumor-stroma interface, artifacts, etc. Method: A pipeline was constructed for ingesting WSI from the set of diagnostic slides available in the cancer genome archive (TCGA). The WSIs were masked for tissue areas and divided into patches extracted at multiple magnification levels. These patches were used to train a U-Net (initialised with a pre-trained ResNet34) to complete a self-supervised in-painting task and evaluated with perceptual loss using VGG16. After training, embeddings were extracted from the bottleneck layer of the U-Net, and these were evaluated for their capacity to cluster according to tissue type and magnification level. Results: The trained embeddings showed strong clustering by tissue type, magnification level, and separation of artefacts. The results were qualitatively evaluated by pathologist with consensus and exceeded the performance of a baseline pre-trained ImageNet model. Conclusion: These results highlight a novel methodology for AI algorithm development that removes the need for numerous pathologists to annotate pathology images by hand and converts their role to reviewing and quality-checking images. AI algorithms based on this approach can have a significant impact in the pathologic evaluation of tissue for oncology clinical trials by extracting a richer set of features than glass microscopy alone would permit. Furthermore, self-supervised methods, such as in-painting allow for the training of embeddings that encapsulate a richer understanding of the data and are consequently more repurposable than supervised/labelled approaches. Citation Format: Jason Hipp, Mona Xu, Lucas Bordeaux, Feng Gu, Carlos Pedrinaci, Khan Baykaner. Unsupervised learning of image embeddings enables new opportunities to extract novel information from digital pathology H&E images [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-076.

In this study, we investigate the performance of computer vision AI algorithms in predicting patient disposition from the emergency department (ED) using short video clips. Clinicians often use “eye-balling” or clinical gestalt to aid in triage, based on brief observations. We hypothesize that AI can similarly use patient appearance for disposition prediction. Data were collected from adult patients at an academic ED, with mobile phone videos capturing patients performing simple tasks. Our AI algorithm, using video alone, showed better performance in predicting hospital admissions (AUROC = 0.693 [95% CI 0.689, 0.696]) compared to models using triage clinical data (AUROC = 0.678 [95% CI 0.668, 0.687]). Combining video and triage data achieved the highest predictive performance (AUROC = 0.714 [95% CI 0.709, 0.719]). This study demonstrates the potential of video AI algorithms to support ED triage and alleviate healthcare capacity strains during periods of high demand.

PD50-06 PERFORMANCE OF A PROSTATE CANCER DETECTION SYSTEM ON IHC-REQUESTED CASES

Despite the plethora of AI-based algorithms developed for anomaly detection in radiology, subsequent integration into clinical setting is rarely evaluated. In this work, we assess the applicability and utility of an AI-based model for brain aneurysm detection comparing the performance of two readers with different levels of experience (2 and 13years). We aim to answer the following questions: 1) Do the readers improve their performance when assisted by the AI algorithm? 2) How much does the AI algorithm impact routine clinical workflow? We reuse and enlarge our open-access, Time-Of-Flight Magnetic Resonance Angiography dataset (N=460). We use 360 subjects for training/validating our algorithm and 100 as unseen test set for the reading session. Even though our model reaches state-of-the-art results on the test set (sensitivity=74%, false positive rate=1.6), we show that neither the junior nor the senior reader significantly increase their sensitivity (p=0.59, p=1, respectively). In addition, we find that reading time for both readers is significantly higher in the "AI-assisted" setting than in the "Unassisted" (+15s, on average; p=3×10-4 junior, p=3×10-5 senior). The confidence reported by the readers is unchanged across the two settings, indicating that the AI assistance does not influence the certainty of the diagnosis. Our findings highlight the importance of clinical validation of AI algorithms in a clinical setting involving radiologists. This study should serve as a reminder to the community to always examine the real-word effectiveness and workflow impact of proposed algorithms.

Generating Rare Surgical Events Using CycleGAN: Addressing Lack of Data for Artificial Intelligence Event Recognition

The aim of this study was to develop a clinical application model for the rational use of caffeine. Caffeine is related to the incidence of neuro immune gastrointestinal diseases. Coffee consumption needs to be optimized in order to reduce the incidence rate. By using KEEG analysis to explore potential molecular signaling pathways involved in the progression of neurological immune gastrointestinal diseases, and analyzing the details of this signaling Pathway using molecular simulation results, which can support AI system for doctor. The research team designed a controlled experiment to analyze the differences in reward and reinforcement of Brain pleasure/addiction and dopamine related signaling pathways function between multiple groups of people with different coffee drinking habits and a blank control group. The study team used molecular dynamics methods to investigate the signaling route that links coffee with the binding of dopamine receptor D3.AI is used to predict the prevalence of gastric reflux disease. Human experiments have shown a correlation between caffeine intake and gastroesophageal reflux disease. AI algorithm results can provide clinical support, and molecular simulation results are consistent with human experimental results. Caffeine and DRD3 protein have a stable interaction system. The research team elucidated the intermolecular interaction between caffeine and DRD3, and AI algorithms can predict the likelihood of disease occurrence, providing a new strategy for clinical practice. This study has passed ethical approval at Chifeng Cancer Hospital, and the ethical documents for this study have been submitted to the World Health Organization for filing.

This paper’s structure is the literature review, which is about the critical comparison in the AI algorithm field. And its main purpose was to identify some problems to address with this research. In my paper, I discussed various aspects of AI for improved performance and efficiency. I emphasize the need for technologists and AI researchers to create reliable systems and highlight the importance of connecting key AI components to establish trust between AI and humans.

Glaucoma is a global disease that leads to blindness due to pathological loss of retinal ganglion cell axons in the optic nerve head (ONH). The presented project aims at improving a computational algorithm for estimating the thickness and surface area of the waist of the nerve fiber layer in the ONH. Our currently developed deep learning AI algorithm meets the need for a morphometric parameter that detects glaucomatous change earlier than current clinical follow-up methods. In 3D OCT image volumes, two different AI algorithms identify the Optic nerve head Pigment epithelium Central Limit (OPCL) and the Inner limit of the Retina Closest Point (IRCP) in a 3D grid. Our computational algorithm includes the undulating surface area of the waist of the ONH, as well as waist thickness. In 16 eyes of 16 non-glaucomatous subjects aged [20;30] years, the mean difference in minimal thickness of the waist of the nerve fiber layer between our previous and the current post-processing strategies was estimated as CI_μ(0.95) 0 ±1 μm (D.f. 15). The mean surface area of the waist of the nerve fiber layer in the optic nerve head was 1.97 ± 0.19 mm². Our computational algorithm results in slightly higher values for surface areas compared to published work, but as expected, this may be due to surface undulations of the waist being considered. Estimates of the thickness of the waist of the ONH yields estimates of the same order as our previous computational algorithm.

Study question Deep-learning algorithms are known to be non-robust: can the variability and inconsistency of AI algorithms be reduced in embryo selection? Summary answer We reduced the variability of algorithms (measured on different tasks like rotations and brightness changes) by 86% while preserving their quality. What is known already Deep-learning methods are generally known to be non-robust, i.e., decisions change with even slight modification of input data. Current solutions for embryo scoring are not robust - for example rotating the input image results in a different score in most solutions on the market. Despite this fact and expressed concerns of embryologists, there are no other publications focusing on the problem of variance in AI solutions used in IVF. Most of the publications measure accuracy, sensitivity, specificity, and ROC AUC; there are no variance metrics. Study design, size, duration The data-set was collected within multiple clinics using various devices. It contains 34,821 embryos (4,510 were transferred with known pregnancy results), represented by time-lapse videos or images. This gives 3,290,481 frames of embryos at various maturity levels. From the data-set 925 randomly selected embryos were chosen as a test set. The frames were modified by methods that are not supposed to change the results of the algorithm. We measured the variability of the scores given by our algorithm. Participants/materials, setting, methods We have considered seven different modifications of images that should not influence embryo scoring: • Rotations (10 different angles); • Brightness and Contrast modifications; • Substitutions of Frames (from time-lapse monitoring taken from a 2 hours interval); • Blur (Generalised Normal filter); • Gaussian Noise; • Gaussian Blur; • Sharpening. We used several techniques to reduce variance of our deep neural network model (architecture commonly used for embryo selection): • Ensemble (of different models in cross validation); • Test time augmentation (TTA); • Robust training. Main results and the role of chance In order to measure the variance we have used the following method. First, the scores are stretched to the standard uniform distribution. In other words we look in which percentile the score lies. This way the range of the scores are normalised thus the variance can be compared. Second, we train the EMBROAID model on the augmented data that includes all the above modifications. Third, we compute the variance of the normalised scores on the test set. The mean variance dropped by 86% (0.0055 to 0.0008) across all measured input modifications. The individual drops in the variance on measured input modifications: Rotations: 77% (0.009 -> 0.002), Brightness and Contrast: 81% (0.0036 -> 0.0007), Substitution of Frames: 76% (0.0076 -> 0.0019), Blur 94% (0.012 -> 0.0008), Gaussian Noise: 96% (0.0049 -> 0.0002), Gaussian Blur: 95% (0.0052 -> 0.0003), Sharpening: 77% (0.0015 -> 0.0003). The significance was tested with Wilcoxon Rank Sum Test giving the p-value < 0.01 on all input modifications. Finally, we stress that these results were obtained without any loss in the ROC AUC metric. We have tested the algorithm both on the original test-set. Both models achieved an ROC AUC of 0.66 (CI 0.63-0.69) on both test-sets. Limitations, reasons for caution Further work needs to be done to extend the set of possible augmentations of data. Wider implications of the findings Increased reliability of AI scoring algorithms for embryo selection. It is possible to obtain consistent results over a wide range of data modifications. Trial registration number not applicable

Detecting bias in data is crucial since it can pose serious problems when developing an AI algorithm. The research aims to propose a novel study design to detect bias in image classification data by using pretrained Convolutional Neural Network (CNN) layers as a feature extractor. There are three datasets used in the research with varying degrees of complexity, those are low, medium, and high complexity. There are Modified National Institute of Standards and Technology (MNIST) Digits, batik collections (Parang, Megamendung, and Kawung), and Canadian Institute for Advanced Research (CIFAR-10) datasets. Then, the researchers make a baseline workflow and substitute a step-in feature extraction with a convolution using the first pre-trained CNN layer and each of its kernels. Then, the researchers evaluate the effect of the experiments using accuracy. By observing the effect of the individual kernel, the research can better make sense of what happens inside a CNN layer. The research finds that color in the image is an essential factor when working with CNN. Furthermore, the proposed study design can detect bias in image classification data where it is related to the color of the image. Detecting this bias early is important in helping developers to improve AI algorithms.

With the development of edge computing, AI algorithms are deployed on edge computing servers to reduce latency and protect privacy. The advancement of AI technology and the enhancement of computing capabilities of edge computing servers enable their application in more industries. Currently, in the aspect of factory safety production control, there exist problems such as insufficient intelligence and waste of human resources. To address these issues, this article designs a factory safety production control system based on AI technology. The system consists of four layers: perception layer, data layer, AI algorithm application layer, and user display management layer. It supports safety helmet detection, safety belt detection, human body detection, hot work operation detection, and left-behind object detection, featuring high levels of intelligence, security, and ease of use. It realizes the automatic identification and alarm of various safety hazards in industrial production environments. The project is targeted at a scale of approximately 1,000 cameras in the enterprise's production base, and an AI server is added in the monitoring room to perform intelligent recognition functions related to safety.

Artificial Intelligence using algorithm is now capable to engage with humans through books. Will robot authors produce romantic books on cow hug day? Can it structure signs, symbols and narratives in literature as humans does, even with zero grammatical mistakes? What aspects of Romantic poetry and the Graphic novel can computer algorithms disclose that a human reader cannot? Can technology aid writers while they generate a book? The fourth industrial revolution totally made machine-generated language looked to have moved closer to reality with the recent unveiling of an artificial intelligence that could independently produce literary texts. Large volumes of data can now be processed and analysed by computers thanks to AI algorithms, which has produced novel findings and advancements in a number of industries. The capacity of AI to produce and alter text is one feature that has drawn a lot of interest. The evolution of AI-generated texts has been impacted by human language in many ways, and this paper will explore how current alphabets have shaped this development. This study investigates the connection between creativity and technology, with a particular emphasis on how AI-generated literature may change the legacy of human narratives. It will also explore how AI algorithms have changed over time. This research article delves into the captivating world of AI-generated texts, focusing on the novel Dinner Depression by Julia Roy Raffel, which was generated without human intervention through transhumanistic lens.