Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension

Nature Medicine, Journal Year: 2020, Volume and Issue: 26(9), P. 1364 - 1374

Published: Sept. 1, 2020

Abstract The CONSORT 2010 statement provides minimum guidelines for reporting randomized trials. Its widespread use has been instrumental in ensuring transparency the evaluation of new interventions. More recently, there a growing recognition that interventions involving artificial intelligence (AI) need to undergo rigorous, prospective demonstrate impact on health outcomes. CONSORT-AI (Consolidated Standards Reporting Trials–Artificial Intelligence) extension is guideline clinical trials evaluating with an AI component. It was developed parallel its companion trial protocols: SPIRIT-AI (Standard Protocol Items: Recommendations Interventional Intelligence). Both were through staged consensus process literature review and expert consultation generate 29 candidate items, which assessed by international multi-stakeholder group two-stage Delphi survey (103 stakeholders), agreed upon two-day meeting (31 stakeholders) refined checklist pilot (34 participants). includes 14 items considered sufficiently important they should be routinely reported addition core items. recommends investigators provide clear descriptions intervention, including instructions skills required use, setting intervention integrated, handling inputs outputs human–AI interaction provision analysis error cases. will help promote completeness assist editors peer reviewers, as well general readership, understand, interpret critically appraise quality design risk bias

Language: Английский

---

Deep learning in histopathology: the path to the clinic

Nature Medicine, Journal Year: 2021, Volume and Issue: 27(5), P. 775 - 784

Published: May 1, 2021

Language: Английский

---

Recent advances and clinical applications of deep learning in medical image analysis

Medical Image Analysis, Journal Year: 2022, Volume and Issue: 79, P. 102444 - 102444

Published: April 4, 2022

Language: Английский

---

The imperative for regulatory oversight of large language models (or generative AI) in healthcare

npj Digital Medicine, Journal Year: 2023, Volume and Issue: 6(1)

Published: July 6, 2023

The rapid advancements in artificial intelligence (AI) have led to the development of sophisticated large language models (LLMs) such as GPT-4 and Bard. potential implementation LLMs healthcare settings has already garnered considerable attention because their diverse applications that include facilitating clinical documentation, obtaining insurance pre-authorization, summarizing research papers, or working a chatbot answer questions for patients about specific data concerns. While offering transformative potential, warrant very cautious approach since these are trained differently from AI-based medical technologies regulated already, especially within critical context caring patients. newest version, GPT-4, was released March, 2023, brings potentials this technology support multiple tasks; risks mishandling results it provides varying reliability new level. Besides being an advanced LLM, will be able read texts on images analyze those images. regulation generative AI medicine without damaging exciting is timely challenge ensure safety, maintain ethical standards, protect patient privacy. We argue regulatory oversight should assure professionals can use causing harm compromising This paper summarizes our practical recommendations what we expect regulators bring vision reality.

Language: Английский

---

Mapping the landscape of Artificial Intelligence applications against COVID-19

Journal of Artificial Intelligence Research, Journal Year: 2020, Volume and Issue: 69, P. 807 - 845

Published: Nov. 19, 2020

COVID-19, the disease caused by SARS-CoV-2 virus, has been declared a pandemic World Health Organization, which reported over 18 million confirmed cases as of August 5, 2020. In this review, we present an overview recent studies using Machine Learning and, more broadly, Artificial Intelligence, to tackle many aspects COVID-19 crisis. We have identified applications that address challenges posed at different scales, including: molecular, identifying new or existing drugs for treatment; clinical, supporting diagnosis and evaluating prognosis based on medical imaging non-invasive measures; societal, tracking both epidemic accompanying infodemic multiple data sources. also review datasets, tools, resources needed facilitate Intelligence research, discuss strategic considerations related operational implementation multidisciplinary partnerships open science. highlight need international cooperation maximize potential AI in future pandemics.

Language: Английский

---

On evaluation metrics for medical applications of artificial intelligence

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: April 8, 2022

Clinicians and software developers need to understand how proposed machine learning (ML) models could improve patient care. No single metric captures all the desirable properties of a model, which is why several metrics are typically reported summarize model's performance. Unfortunately, these measures not easily understandable by many clinicians. Moreover, comparison across studies in an objective manner challenging, no tool exists compare using same performance metrics. This paper looks at previous ML done gastroenterology, provides explanation what different mean context binary classification presented studies, gives thorough should be interpreted. We also release open source web-based that may used aid calculating most relevant this so other researchers clinicians incorporate them into their research.

Language: Английский

---

Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension

Nature Medicine, Journal Year: 2020, Volume and Issue: 26(9), P. 1351 - 1363

Published: Sept. 1, 2020

The SPIRIT 2013 statement aims to improve the completeness of clinical trial protocol reporting by providing evidence-based recommendations for minimum set items be addressed. This guidance has been instrumental in promoting transparent evaluation new interventions. More recently, there a growing recognition that interventions involving artificial intelligence (AI) need undergo rigorous, prospective demonstrate their impact on health outcomes. SPIRIT-AI (Standard Protocol Items: Recommendations Interventional Trials-Artificial Intelligence) extension is guideline protocols evaluating with an AI component. It was developed parallel its companion reports: CONSORT-AI (Consolidated Standards Reporting Intelligence). Both guidelines were through staged consensus process literature review and expert consultation generate 26 candidate items, which consulted upon international multi-stakeholder group two-stage Delphi survey (103 stakeholders), agreed meeting (31 stakeholders) refined checklist pilot (34 participants). includes 15 considered sufficiently important These should routinely reported addition core items. recommends investigators provide clear descriptions intervention, including instructions skills required use, setting intervention will integrated, considerations handling input output data, human-AI interaction analysis error cases. help promote transparency Its use assist editors peer reviewers, as well general readership, understand, interpret critically appraise design risk bias planned trial.

Language: Английский

---

Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge

Nature Medicine, Journal Year: 2022, Volume and Issue: 28(1), P. 154 - 163

Published: Jan. 1, 2022

Abstract Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation multinational settings. Competitions be accelerators medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this mind, we organized the PANDA challenge—the largest histopathology competition date, joined 1,290 developers—to catalyze development reproducible AI algorithms Gleason grading using 10,616 digitized We validated that a diverse set submitted reached pathologist-level performance on cross-continental cohorts, fully blinded algorithm developers. On United States European external sets, achieved agreements 0.862 (quadratically weighted κ, 95% confidence interval (CI), 0.840–0.884) 0.868 (95% CI, 0.835–0.900) with expert uropathologists. Successful generalization across different patient populations, laboratories reference standards, variety algorithmic approaches, warrants evaluating AI-based prospective clinical trials.

Language: Английский

---

The myth of generalisability in clinical research and machine learning in health care

The Lancet Digital Health, Journal Year: 2020, Volume and Issue: 2(9), P. e489 - e492

Published: Aug. 24, 2020

An emphasis on overly broad notions of generalisability as it pertains to applications machine learning in health care can overlook situations which might provide clinical utility. We believe that this narrow focus should be replaced with wider considerations for the ultimate goal building systems are useful at bedside.

Language: Английский

---

Artificial intelligence in radiology: 100 commercially available products and their scientific evidence

European Radiology, Journal Year: 2021, Volume and Issue: 31(6), P. 3797 - 3804

Published: April 15, 2021

Abstract Objectives Map the current landscape of commercially available artificial intelligence (AI) software for radiology and review availability their scientific evidence. Methods We created an online overview CE-marked AI products clinical based on vendor-supplied product specifications ( www.aiforradiology.com ). Characteristics such as modality, subspeciality, main task, regulatory information, deployment, pricing model were retrieved. conducted extensive literature search evidence these products. Articles classified according to a hierarchical efficacy. Results The included 100 from 54 different vendors. For 64/100 products, there was no peer-reviewed its observed large heterogeneity in deployment methods, models, classes. remaining 36/100 comprised 237 papers that predominantly (65%) focused diagnostic accuracy (efficacy level 2). From 18 had regarded 3 or higher, validating (potential) impact thinking, patient outcome, costs. Half (116/237) independent not (co-)funded (co-)authored by vendor. Conclusions Even though commercial supply already holds we conclude sector is still infancy. efficacy lacking. Only 18/100 have demonstrated impact. Key Points • Artificial infancy even are available. 36 out which most studies demonstrate lower levels There wide variety strategies, CE marking class radiology.

Language: Английский

---