Gastroenterology Meets Machine Learning: Status Quo and Quo Vadis.
TL;DR: This work presents the results gleaned through a systematic review of prominent gastroenterology literature using machine learning techniques, and delimit the scope of application, discuss current limitations including bias, lack of transparency, accountability, and data availability, and put forward future avenues.
Abstract: Machine learning has undergone a transition phase from being a pure statistical tool to being one of the main drivers of modern medicine. In gastroenterology, this technology is motivating a growing number of studies that rely on these innovative methods to deal with critical issues related to this practice. Hence, in the light of the burgeoning research on the use of machine learning in gastroenterology, a systematic review of the literature is timely. In this work, we present the results gleaned through a systematic review of prominent gastroenterology literature using machine learning techniques. Based on the analysis of 88 journal articles, we delimit the scope of application, we discuss current limitations including bias, lack of transparency, accountability, and data availability, and we put forward future avenues.
Citations
More filters
TL;DR: Five frequently applied techniques for generating molecular data, which are micro array, RNA sequencing, quantitative polymerase chain reaction, NanoString and tissue microarray, are introduced and standardized methods should be established to help identify intrinsic subgroup signatures and build robust classifiers that pave the way toward stratified treatment of cancer patients.
Abstract: Cancer is a collection of genetic diseases, with large phenotypic differences and genetic heterogeneity between different types of cancers and even within the same cancer type. Recent advances in genome-wide profiling provide an opportunity to investigate global molecular changes during the development and progression of cancer. Meanwhile, numerous statistical and machine learning algorithms have been designed for the processing and interpretation of high-throughput molecular data. Molecular subtyping studies have allowed the allocation of cancer into homogeneous groups that are considered to harbor similar molecular and clinical characteristics. Furthermore, this has helped researchers to identify both actionable targets for drug design as well as biomarkers for response prediction. In this review, we introduce five frequently applied techniques for generating molecular data, which are microarray, RNA sequencing, quantitative polymerase chain reaction, NanoString and tissue microarray. Commonly used molecular data for cancer subtyping and clinical applications are discussed. Next, we summarize a workflow for molecular subtyping of cancer, including data preprocessing, cluster analysis, supervised classification and subtype characterizations. Finally, we identify and describe four major challenges in the molecular subtyping of cancer that may preclude clinical implementation. We suggest that standardized methods should be established to help identify intrinsic subgroup signatures and build robust classifiers that pave the way toward stratified treatment of cancer patients.
72 citations
TL;DR: The aim of this article is to provide an overview of the current status of MHA and MA use in the field of gastroenterology, describe the future perspectives in this field and point out some of the challenges that need to be addressed.
Abstract: Mobile health apps (MHAs) and medical apps (MAs) are becoming increasingly popular as digital interventions in a wide range of health-related applications in almost all sectors of healthcare. The surge in demand for digital medical solutions has been accelerated by the need for new diagnostic and therapeutic methods in the current coronavirus disease 2019 pandemic. This also applies to clinical practice in gastroenterology, which has, in many respects, undergone a recent digital transformation with numerous consequences that will impact patients and health care professionals in the near future. MHAs and MAs are considered to have great potential, especially for chronic diseases, as they can support the self-management of patients in many ways. Despite the great potential associated with the application of MHAs and MAs in gastroenterology and health care in general, there are numerous challenges to be met in the future, including both the ethical and legal aspects of applying this technology. The aim of this article is to provide an overview of the current status of MHA and MA use in the field of gastroenterology, describe the future perspectives in this field and point out some of the challenges that need to be addressed.
28 citations
30 Jun 2021
TL;DR: In this article, the authors provide some general information about AI and capsule endoscopy, and outline recent advances in AI and CE, issues around implementation of AI in medical practice and potential future applications of AI-aided CE.
Abstract: Capsule endoscopy (CE) has been increasingly utilised in recent years as a minimally invasive tool to investigate the whole gastrointestinal (GI) tract and a range of capsules are currently available for evaluation of upper GI, small bowel, and lower GI pathology. Although CE is undoubtedly an invaluable test for the investigation of small bowel pathology, it presents considerable challenges and limitations, such as long and laborious reading times, risk of missing lesions, lack of bowel cleansing score and lack of locomotion. Artificial intelligence (AI) seems to be a promising tool that may help improve the performance metrics of CE, and consequently translate to better patient care. In the last decade, significant progress has been made to apply AI in the field of endoscopy, including CE. Although it is certain that AI will find soon its place in day-to-day endoscopy clinical practice, there are still some open questions and barriers limiting its widespread application. In this review, we provide some general information about AI, and outline recent advances in AI and CE, issues around implementation of AI in medical practice and potential future applications of AI-aided CE.
11 citations
TL;DR: A systematic review of the use of Artificial Intelligence (AI) in dental specialties is presented in this article , where 28 studies were evaluated using the Probabilistic Study Risk of Bias Assessment Tool (PROBAST).
Abstract: Artificial intelligence (AI) has received enormous attention and has gone through a transition stage from being a pure statistical tool to being one of the main drivers of modern medicine. The purpose of this systematic review was to determine the use of this technology in dental specialties. This systematic review was conducted according to the PRISMA protocol and the Cochrane Handbook for Systematic Reviews of Interventions. Online databases (PubMed, Ovid via Medline, and web of Science) and manual retrieval of cross references were searched. The selection process yielded 28 studies investigating the acceptability, effectiveness, or feasibility of AI models in various dental subspecialties. The methodological quality and risk of bias of the included studies were analyzed and appraised using the Prediction Study Risk of Bias Assessment Tool (PROBAST). The authors included 28 studies that investigated the use of AI in the dental fields. Six studies in periodontics reported 480 training data sets and 171 test data sets. Eight studies in orthodontics reported 1336 training and 80 test data sets. Five studies in prosthodontics reported 4659 training and 1759 test data sets. Five studies in oral medicine and pathology reported 1151 training and 68 test data sets. Two studies in maxillofacial surgery reported 47 training data sets. Three studies in endodontics reported 142 training and 103 test data sets. AI represents an effective approach to analyze clinical dental data. Further studies, including randomized clinical trials, are needed to confirm the value of this concept in dental practice with the goal of providing data-driven, high performance dental care that can rapidly improve the science, economics, and delivery of optimum treatment options for patients.
10 citations
26 Apr 2020
TL;DR: Fosil yakitlar ile calisan tasitlar, cevrede zarli gazlarin artmasina ve petrol rezervlerinin azalmasina neden olmaktadir as discussed by the authors.
Abstract: Fosil yakitlar ile calisan tasitlar, cevrede zararli gazlarin artmasina ve petrol rezervlerinin azalmasina neden olmaktadir. Bu zararlarin minimize edilmesi icin pek cok arastirmaci, buji ateslemeli motorlarda istenilen performansi elde edebilen ve cevreye az oranda egzoz emisyonu birakabilen alternatif yakitlardan birinin de alkollerin oldugunu ileri surmusler ve pek cok deneysel calismalar gerceklestirmislerdir. Bu arastirma calismasinda; buji ateslemeli motorlarda alkol yakit kullanilmasi durumunda motor performansinda, emisyonlarda ve yanma karakteristiklerinde ne gibi degisikliklerin oldugu uzerine gerceklestirilmis calismalar detayli bir sekilde incelenerek tablolar olusturulmus ve bu degisikliklerin nedenleri aciklanmistir. Arastirma ile alkol kullanilmasiyla motor performansinda ve yanma karakteristiklerinde artis oldugu ve egzoz emisyonlarinda ise azalmalarin gerceklestigi sonucuna varilmistir.
5 citations
Cites background from "Gastroenterology Meets Machine Lear..."
...The WFD promotes integrated management of water resources to reduce problems associated with excessive water abstraction, pollution, floods and droughts [7]....
[...]
...As Turkey is a candidate country to the EU, there are several obligations we need to comply such as the WFD [7] and the Nitrate Directive [27]....
[...]
...Motor strokunun uzunluğuna, şarj durumuna ve ortalama efektif silindir basıncına bağlıdır [7]....
[...]
...Isı salınım hızı, bir çevrim sırasında termodinamiğin birinci yasasından hesaplanır ve dışına akış ve sızıntılardan elde edilen sonuçlara bağlı olan krank açısı ile değişmektedir [7]....
[...]
...Katı Atık depolama alanının seçimi ve değerlendirilmesi için çeşitli yöntemler ve yaklaşımlar geliştirilmiştir [3-8]....
[...]
References
More filters
TL;DR: Moher et al. as mentioned in this paper introduce PRISMA, an update of the QUOROM guidelines for reporting systematic reviews and meta-analyses, which is used in this paper.
Abstract: David Moher and colleagues introduce PRISMA, an update of the QUOROM guidelines for reporting systematic reviews and meta-analyses
62,157 citations
TL;DR: This work demonstrates an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists, trained end-to-end from images directly, using only pixels and disease labels as inputs.
Abstract: Skin cancer, the most common human malignancy, is primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy and histopathological examination. Automated classification of skin lesions using images is a challenging task owing to the fine-grained variability in the appearance of skin lesions. Deep convolutional neural networks (CNNs) show potential for general and highly variable tasks across many fine-grained object categories. Here we demonstrate classification of skin lesions using a single CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs. We train a CNN using a dataset of 129,450 clinical images-two orders of magnitude larger than previous datasets-consisting of 2,032 different diseases. We test its performance against 21 board-certified dermatologists on biopsy-proven clinical images with two critical binary classification use cases: keratinocyte carcinomas versus benign seborrheic keratoses; and malignant melanomas versus benign nevi. The first case represents the identification of the most common cancers, the second represents the identification of the deadliest skin cancer. The CNN achieves performance on par with all tested experts across both tasks, demonstrating an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists. Outfitted with deep neural networks, mobile devices can potentially extend the reach of dermatologists outside of the clinic. It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021 (ref. 13) and can therefore potentially provide low-cost universal access to vital diagnostic care.
8,424 citations
28 May 2006
TL;DR: This tutorial is designed to provide an introduction to the role, form and processes involved in performing Systematic Literature Reviews, and to gain the knowledge needed to conduct systematic reviews of their own.
Abstract: Context: Making best use of the growing number of empirical studies in Software Engineering, for making decisions and formulating research questions, requires the ability to construct an objective summary of available research evidence. Adopting a systematic approach to assessing and aggregating the outcomes from a set of empirical studies is also particularly important in Software Engineering, given that such studies may employ very different experimental forms and be undertaken in very different experimental contexts.Objectives: To provide an introduction to the role, form and processes involved in performing Systematic Literature Reviews. After the tutorial, participants should be able to read and use such reviews, and have gained the knowledge needed to conduct systematic reviews of their own.Method: We will use a blend of information presentation (including some experiences of the problems that can arise in the Software Engineering domain), and also of interactive working, using review material prepared in advance.
4,352 citations
TL;DR: In this article, two machine learning procedures have been investigated in some detail using the game of checkers, and enough work has been done to verify the fact that a computer can be programmed so that it will lear...
Abstract: Two machine-learning procedures have been investigated in some detail using the game of checkers. Enough work has been done to verify the fact that a computer can be programmed so that it will lear...
2,845 citations
SIDI1
TL;DR: This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI, and review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.
Abstract: At the dawn of the fourth industrial revolution, we are witnessing a fast and widespread adoption of artificial intelligence (AI) in our daily life, which contributes to accelerating the shift towards a more algorithmic society. However, even with such unprecedented advancements, a key impediment to the use of AI-based systems is that they often lack transparency. Indeed, the black-box nature of these systems allows powerful predictions, but it cannot be directly explained. This issue has triggered a new debate on explainable AI (XAI). A research field holds substantial promise for improving trust and transparency of AI-based systems. It is recognized as the sine qua non for AI to continue making steady progress without disruption. This survey provides an entry point for interested researchers and practitioners to learn key aspects of the young and rapidly growing body of research related to XAI. Through the lens of the literature, we review the existing approaches regarding the topic, discuss trends surrounding its sphere, and present major research trajectories.
2,258 citations