scholarly journals Evaluating artificial intelligence in medicine: phases of clinical research

JAMIA Open ◽  
2020 ◽  
Vol 3 (3) ◽  
pp. 326-331 ◽  
Author(s):  
Yoonyoung Park ◽  
Gretchen Purcell Jackson ◽  
Morgan A Foreman ◽  
Daniel Gruen ◽  
Jianying Hu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Clinical Trial ◽  
Clinical Research ◽  
Study Design ◽  
Medical Devices ◽  
Real World ◽  
In Silico ◽  
Unintended Consequences ◽  
Multifaceted Approach ◽  
Research Framework

Abstract Increased scrutiny of artificial intelligence (AI) applications in healthcare highlights the need for real-world evaluations for effectiveness and unintended consequences. The complexity of healthcare, compounded by the user- and context-dependent nature of AI applications, calls for a multifaceted approach beyond traditional in silico evaluation of AI. We propose an interdisciplinary, phased research framework for evaluation of AI implementations in healthcare. We draw analogies to and highlight differences from the clinical trial phases for drugs and medical devices, and we present study design and methodological guidance for each stage.

scholarly journals In silico imaging clinical trials: cheaper, faster, better, safer, and more scalable

Trials ◽  
2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Aldo Badano
Keyword(s):  
Clinical Trial ◽  
Clinical Trials ◽  
Medical Devices ◽  
In Silico ◽  
Lessons Learned ◽  
Patient Access ◽  
High Quality ◽  
Virtual Imaging ◽  
Regulatory Evaluation

AbstractImaging clinical trials can be burdensome and often delay patient access to novel, high-quality medical devices. Tools for in silico imaging trials have significantly improved in sophistication and availability. Here, I describe some of the principal advantages of in silico imaging trials and enumerate five lessons learned during the design and execution of the first all-in silico virtual imaging clinical trial for regulatory evaluation (the VICTRE study).

scholarly journals POS1497-PARE POST-TRIAL SURVEY OF PARTICIPANTS OF A PHASE 3 CLINICAL TRIAL IN SSC-ILD

2021 ◽  
Vol 80 (Suppl 1) ◽  
pp. 1033.1-1033
Author(s):  
I. Galetti ◽  
E. Brown ◽  
A. Kennedy ◽  
R. J. Riggs ◽  
A. Roennow ◽  
...  
Keyword(s):  
Clinical Trial ◽  
Clinical Trials ◽  
Clinical Research ◽  
Real World ◽  
Advisory Board ◽  
Patient Organisations ◽  
Post Trial ◽  
To Receive ◽  
Trial Participants ◽  
Patient Centric

Background:The SENSCIS® trial (2015–18) was a large clinical trial (n=576) investigating the efficacy and safety of nintedanib in patients with systemic sclerosis-associated interstitial lung disease.1 The clinical research sponsors (CRS) collaborated with the scleroderma patient community advisory board (CAB) regarding the design, implementation and conduct of the trial.2 As part of this collaboration, the CRS and CAB developed a post-trial survey for SENSCIS® participants. The use of the developed patient-centric materials was optional for the sites.Objectives:The objectives of the SENSCIS® post-trial survey were to gain experience in collecting real-world information and trial satisfaction data from patients to inform and improve future patient centric clinical research.Methods:SENSCIS® trial participants who were involved in the extension trial SENSCIS®-ON completed a post-trial survey covering nine multiple-choice questions about three main topics:[1]Recruitment – Where do patients usually search for clinical trials and how did they become aware of SENSCIS®?[2]Motivation & Retention – What motivated patients to start and continue participation in SENSCIS®?[3]Challenges & Wishes – What were the challenges during trial participation and how can future clinical trials be improved regarding patient centricity?Results:A total of 125 participants completed all survey questions. Participants could select more than one option. A total of 51 patients reported that they are usually not actively looking for trials. For those actively searching, the most common sources to learn about trials were specialists/general practitioners (GPs) (46 patients) and internet search engines (20 patients), followed by patient organisations (12 patients). Of note, 78 patients would pay attention to printed materials, such as a card/flyer/poster in a doctor’s office and get in touch with a trial/study site.Back in 2015–2017, during recruitment for the SENSCIS® trial, the majority of the patients who answered the survey were made aware via their specialist/GP (116 patients), whereas 5 were made aware via patient organisations and 4 via the internet.The most frequent motivations to join the trial were ‘hope to receive an improved therapy’ (98 patients), to help other patients (64 patients), and on the recommendation of their specialist/GP (81 patients). Similarly, the most liked aspects of the trial were the ‘opportunity to receive an improved therapy’ (92 patients) and ‘to support the development of an improved therapy for my illness’ (90 patients). More than half of patients reported ‘continuous observation of general health’ (72 patients) and ‘advice from GPs/specialists’ (71 patients) as motivation to stay in the trial (Figure 1).‘Concerns about side effects’ (72 patients) and ‘not knowing whether the trial medication will work for me’ (63 patients) were reported as the least liked aspects of the trial. Travel to the site was reported as a challenge by 21 patients.To improve clinical trials, patients requested more patient-friendly information (50 patients) and multiple formats of information material (46 patients). Finally, 48 patients expressed the desire to communicate with other trial participants.Conclusion:The SENSCIS® post-trial survey is a unique approach to receive real-world feedback from trial participants, and these pilot data will help improve future clinical trials and communication. The results highlight the importance of reaching patients who may not be actively looking for clinical trials.Figure 1.Motivation to stay in the SENSCIS® trial1,21More than one option could be selected.2Data collected on 9th January 2021References:[1]Distler O et al. N Engl J Med. 2019 Jun 27;380(26):2518-2528. doi: 10.1056/NEJMoa1903076.[2]Roennow A et al. BMJ Open. 2020 Dec 16;10(12):e039473. doi: 10.1136/bmjopen-2020-039473.Acknowledgements:Sue Farrington (Federation of European Scleroderma Associations [FESCA] Belgium), Luke Evnin (Scleroderma Research Foundation, United States), Beatriz Garcia (Asociacion Espanola de Esclerodermia, Spain), Catarina Leite (Associacao Portuguesa de Doentes com Esclerodermia, Portugal), Alison Zheng (Chinese Organisation for Scleroderma), Matea Perković Popović (Hrvatska udruga oboljelih od sklerodermije, Croatia), Tina Ampudia (Asociacion Mexicana de Orientacion Apoyo y Lucha Contra la Esclerodermia, AC, Mexico), Stephanie Munoz (Norsk Revmatikerforbund, Diagnosegruppen for Systemisk Sklerose, Norway), Monica Holmner (Reumatikerförbundet Riksföreningen för systemisk skleros, Sweden).Disclosure of Interests:Ilaria Galetti: None declared, EDITH BROWN: None declared, Ann Kennedy Consultant of: I have been a member of the CAB (Community Patient Advisory Board) described in the accompanying abstract under discussion. My patient organisation has been paid for its participation in the CAB., Grant/research support from: It is not myself personally, but FESCA (Federation of European Scleroderma Associations) aisbl., that has received project grants for awareness raising and education. I was President of this Federation., Robert J Riggs: None declared, Annelise Roennow: None declared, Maureen Sauvé: None declared, Joep Welling Speakers bureau: BI MIDI and BI International, Sanofi, Henrik Finnern Employee of: I am employee of Boehringer Ingelheim International GmbH, Annie Gilbert Consultant of: I am a paid consultant for Bohringer Ingelheim since 2016, Martina Gahlemann Employee of: I am employed by Boehringer Ingelheim (Schweiz) GmbH, Basel, Switzerland, Wiebke Sauter Employee of: I am employer of Boehringer-Ingelheim

The Use of CDISC Standards for Real-World Data (RWD): Expert Perspectives from a Qualitative Delphi Survey (Preprint)

2021 ◽  
Author(s):  
Rhonda Facile ◽  
Erin Elizabeth Muhlbradt ◽  
Mengchun Gong ◽  
Qing-Na Li ◽  
Vaishali B. Popat ◽  
...  
Keyword(s):  
Clinical Trial ◽  
Clinical Research ◽  
Real World ◽  
Data Science ◽  
Health Data ◽  
Delphi Survey ◽  
Data Standards ◽  
Real World Data ◽  
World Data

BACKGROUND Real World Data (RWD) and Real World Evidence (RWE) have an increasingly important role in clinical research and health care decision making in many countries. In order to leverage RWD and generate reliable RWE, a framework must be in place to ensure that the data is well-defined and structured in a way that is semantically interoperable and consistent across stakeholders. The adoption of data standards is one of the cornerstones supporting high-quality evidence for clinical medicine and therapeutics development. CDISC data standards are mature, globally recognized and heavily utilized by the pharmaceutical industry for regulatory submission in the US and Japan and are recommended in Europe and China. Against this backdrop, the CDISC RWD Connect Initiative was initiated to better understand the barriers to implementing CDISC standards for RWD and to identify the tools and guidance needed to more easily implement CDISC standards for this purpose. We believe that bridging the gap between RWD and clinical trial generated data will benefit all stakeholders. OBJECTIVE The aim of this project was to understand the barriers to implementing CDISC standards for Real World Data (RWD) and to identify what tools and guidance may be needed to more easily implement CDISC standards for this purpose. METHODS We conducted a qualitative Delphi survey involving an Expert Advisory Board (EAB) with multiple key stakeholders, with three rounds of input and review. RESULTS In total, 66 experts participated in round 1, 56 participated in round 2 and 49 participated in round 3 of the Delphi Survey. Their input was collected and analyzed culminating in group statements. It was widely agreed that the standardization of RWD is highly necessary, and the primary focus should be on its ability to improve data-sharing and the quality of RWE. The priorities for RWD standardization include electronic health records, such as data shared using HL7 FHIR, and data stemming from observational studies. With different standardization efforts already underway in these areas, a gap analysis should be performed to identify areas where synergies and efficiencies are possible and then collaborate with stakeholders to create, or extend existing, mappings between CDISC and other standards, controlled terminologies and models to represent data originating across different sources. CONCLUSIONS There are many ongoing data standardization efforts that span the spectrum of human health data related activities including, but not limited to, those related to healthcare, public health, product or disease registries and clinical research, each with different definitions, levels of granularity and purpose. Amongst these standardization efforts, CDISC has been successful in standardizing clinical trial-based data for regulation worldwide. However, the complexity of the CDISC standards, and the fact that they were developed for different purposes, combined with the lack of awareness and incentives to using a new standard, insufficient training and implementation support are significant barriers for setting up the use of CDISC standards for RWD. The collection and dissemination of use cases showing in detail how to effectively implement CDISC standards for RWD, developing tools and support systems specifically for the RWD community, and collaboration with other standards development organizations and initiatives are potential steps towards connecting RWD to research. The integrity of RWE is dependent on the quality of the RWD and the data standards utilized in its collection, integration, processing, exchange and reporting. Using CDISC as part of the database schema will help to link clinical trial data and RWD and promote innovation in health data science. The authors believe that CDISC standards, if adapted carefully and presented appropriately to the RWD community, can provide “FAIR” structure and semantics for common clinical concepts and domains and help to bridge the gap between RWD and clinical trial generated data. CLINICALTRIAL Not Applicable

Guidelines for Conducting Ethical Artificial Intelligence Research in Neurology: A Systematic Approach for Clinicians and Researchers

Neurology ◽  
2021 ◽  
pp. 10.1212/WNL.0000000000012570
Author(s):  
Sharon Chiang ◽  
Rosalind W. Picard ◽  
Winston Chiong ◽  
Robert Moss ◽  
Gregory A. Worrell ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Clinical Practice ◽  
Study Design ◽  
Clinical Care ◽  
Unintended Consequences ◽  
Multimodal Data ◽  
Ethical Implications ◽  
Methods Development ◽  
Clinical Scenarios ◽  
Long Timescales

Pre-emptive recognition of the ethical implications of study design and algorithm choices in artificial intelligence (AI) research is an important but challenging process. AI applications have begun to transition from a promising future to clinical reality in neurology. As the clinical management of neurology is often concerned with discrete, often unpredictable, and highly consequential events linked to multimodal data streams over long timescales, forthcoming advances in AI have great potential to transform care for patients. However, critical ethical questions have been raised with implementation of the first AI applications in clinical practice. Clearly, AI will have far-reaching potential to promote, but also to endanger, ethical clinical practice. This article employs an anticipatory ethics approach to scrutinize how researchers in neurology can methodically identify ethical ramifications of design choices early in the research and development process, with a goal of pre-empting unintended consequences that may violate principles of ethical clinical care. First, we discuss the use of a systematic framework for researchers to identify ethical ramifications of various study design and algorithm choices. Second, using epilepsy as a paradigmatic example, anticipatory clinical scenarios that illustrate unintended ethical consequences are discussed, and failure points in each scenario evaluated. Third, we provide practical recommendations for understanding and addressing ethical ramifications early in methods development stages. Awareness of the ethical implications of study design and algorithm choices that may unintentionally enter AI is crucial to ensuring that incorporation of AI into neurology care leads to patient benefit rather than harm.

scholarly journals Applied Artificial Intelligence – Making AI Work for Consumers as a Core Business Component

2020 ◽  
pp. 39-72
Author(s):  
Mikael Wiberg ◽  
Keyword(s):  
Artificial Intelligence ◽  
Study Design ◽  
Real World ◽  
Design Development ◽  
The Past ◽  
Growing Body ◽  
Business Component ◽  
Online Business ◽  
Societal Level ◽  
Applied Artificial Intelligence

Artificial Intelligence (AI) is now rapidly being applied in our society. While the breakthrough of AI in terms of its use and its applicability on a societal level has in fact been repeatedly announced since the mid 1950s, is now truer than ever. As recently acknowledged, AI has now, after three waves of developments, finally left the research labs and entered real-world contexts. Accordingly, and as AI is now increasingly and widely applied, we suggest that it is now time to address issues related to “Applied Artificial Intelligence” (AAI). In this paper we propose this term, and we define it as the study, design, development, implementation and use of Artificial Intelligence technologies to address real-world problems. In this article we present how AI has developed over the past few decades, and across three waves of developments, and we illustrated Applied Artificial Intelligence by presenting our e-Biz corp case where a global actor is now using AI as a core component of their online business. We conclude this article with a set of recommendations for moving forward with Applied Artificial Intelligence, and we present the main contributions offered by our work to the growing body of research on how to make use of AI.

The Power of Matrix Factorization: Methods for Deconvoluting Genetic Heterogeneous Data at Expression Level

2021 ◽  
Vol 15 (8) ◽  
pp. 841-853
Author(s):  
Yuan Liu ◽  
Zhining Wen ◽  
Menglong Li
Keyword(s):  
Artificial Intelligence ◽  
Matrix Factorization ◽  
In Silico ◽  
Genetic Data ◽  
Heterogeneous Data ◽  
Expression Level ◽  
Mathematical Methods ◽  
Challenges And Opportunities ◽  
Factorization Methods ◽  
Genetic Profiles

Background:: The utilization of genetic data to investigate biological problems has recently become a vital approach. However, it is undeniable that the heterogeneity of original samples at the biological level is usually ignored when utilizing genetic data. Different cell-constitutions of a sample could differentiate the expression profile, and set considerable biases for downstream research. Matrix factorization (MF) which originated as a set of mathematical methods, has contributed massively to deconvoluting genetic profiles in silico, especially at the expression level. Objective: With the development of artificial intelligence algorithms and machine learning, the number of computational methods for solving heterogeneous problems is also rapidly abundant. However, a structural view from the angle of using MF to deconvolute genetic data is quite limited. This study was conducted to review the usages of MF methods on heterogeneous problems of genetic data on expression level. Methods: MF methods involved in deconvolution were reviewed according to their individual strengths. The demonstration is presented separately into three sections: application scenarios, method categories and summarization for tools. Specifically, application scenarios defined deconvoluting problem with applying scenarios. Method categories summarized MF algorithms contributed to different scenarios. Summarization for tools listed functions and developed web-servers over the latest decade. Additionally, challenges and opportunities of relative fields are discussed. Results and Conclusion: Based on the investigation, this study aims to present a relatively global picture to assist researchers to achieve a quicker access of deconvoluting genetic data in silico, further to help researchers in selecting suitable MF methods based on the different scenarios.

The Use of Digital Clinical Trial Methods in the Evaluation of Digital Therapeutics: A Scoping Review (Preprint)

2019 ◽  
Author(s):  
Allison Hirsch ◽  
Mahip Grewal ◽  
Anthony James Martorell ◽  
Brian Michael Iacoviello
Keyword(s):  
Clinical Trial ◽  
Clinical Trials ◽  
Clinical Research ◽  
Scoping Review ◽  
Digital Technologies ◽  
Good Clinical Practice ◽  
The United States ◽  
Clinical Trial Research ◽  
Digital Methods ◽  
Clinical Trial Methods

BACKGROUND Digital Therapeutics (DTx) provide evidence based therapeutic health interventions that have been clinically validated to deliver therapeutic outcomes, such that the software is the treatment. Digital methodologies are increasingly adopted to conduct clinical trials due to advantages they provide including increases in efficiency and decreases in trial costs. Digital therapeutics are digital by design and can leverage the potential of digital and remote clinical trial methods. OBJECTIVE The principal purpose of this scoping review is to review the literature to determine whether digital technologies are being used in DTx clinical research, which type are being used and whether publications are noting any advantages to their use. As DTx development is an emerging field there are likely gaps in the knowledge base regarding DTx and clinical trials, and the purpose of this review is to illuminate those gaps. A secondary purpose is to consider questions which emerged during the review process including whether fully remote digital clinical research is appropriate for all health conditions and whether digital clinical trial methods are inline with the principles of Good Clinical Practice. METHODS 1,326 records were identified by searching research databases and 1,227 reviewed at the full-article level in order to determine if they were appropriate for inclusion. Confirmation of clinical trial status, use of digital clinical research methods and digital therapeutic status as well as inclusion and exclusion criteria were applied in order to determine relevant articles. Digital methods employed in DTx research were extracted from each article and these data were synthesized in order to determine which digital methods are currently used in clinical trial research. RESULTS After applying our criteria for scoping review inclusion, 11 articles were identified. All articles used at least one form of digital clinical research methodology enabling an element of remote research. The most commonly used digital methods are those related to recruitment, enrollment and the assessment of outcomes. A small number of articles reported using other methods such as online compensation (n = 3), or digital reminders for participants (n = 5). The majority of digital therapeutics clinical research using digital methods is conducted in the United States and increasing number of articles using digital methods are published each year. CONCLUSIONS Digital methods are used in clinical trial research evaluating DTx, though not frequently as evidenced by the low proportion of articles included in this review. Fully remote clinical trial research is not yet the standard, more frequently authors are using partially remote methods. Additionally, there is tremendous variability in the level of detail describing digital methods within the literature. As digital technologies continue to advance and the clinical research DTx literature matures, digital methods which facilitate remote research may be used more frequently.

scholarly journals Tuberculosis and viral hepatitis in patients treated with certolizumab pegol in Asia-Pacific countries and worldwide: real-world and clinical trial data

2020 ◽  
Author(s):  
Chak Sing Lau ◽  
Yi-Hsing Chen ◽  
Keith Lim ◽  
Marc de Longueville ◽  
Catherine Arendt ◽  
...  
Keyword(s):  
Clinical Trial ◽  
Clinical Trials ◽  
Viral Hepatitis ◽  
Central Europe ◽  
Real World ◽  
Certolizumab Pegol ◽  
Safety Data ◽  
Asia Pacific ◽  
Hbv Reactivation ◽  
Post Marketing

Abstract Introduction/objectives To evaluate the incidence rate (IR) of tuberculosis (TB) and viral hepatitis B and C (HBV/HCV) during certolizumab pegol (CZP) treatment, worldwide and in Asia-Pacific countries, across clinical trials and post-marketing reports (non-interventional studies and real-world practice). Method CZP safety data were pooled across 49 clinical trials from 1998 to June 2017. Post-marketing reports were from initial commercialization until March 2015 (TB)/February 2017 (HBV/HCV). All suspected TB and HBV/HCV cases underwent centralized retrospective review by external experts. Incidence rates (IRs) were calculated per 100 patient-years (PY) of CZP exposure. Results Among 11,317 clinical trial patients (21,695 PY), 62 TB cases were confirmed (IR 0.29/100 PY) including 2 in Japan (0.10/100 PY) and 3 in other Asia-Pacific countries (0.58/100 PY). From > 238,000 PY estimated post-marketing CZP exposure, there were 31 confirmed TB cases (0.01/100 PY): 5 in Japan (0.05/100 PY), 1 in other Asia-Pacific countries (0.03/100 PY). Reported regional TB IRs were highest in eastern Europe (0.17/100 PY), central Europe (0.09/100 PY), and Mexico (0.16/100 PY). Across clinical trials, there was 1 confirmed HBV reactivation and no HCV cases. From > 420,000 PY estimated post-marketing CZP exposure, 5 HBV/HCV cases were confirmed (0.001/100 PY): 2 HCV reactivations; 1 new HCV; plus 2 HBV reactivations in Japan (0.008/100 PY). Conclusions CZP TB risk is aligned with nationwide TB rates, being slightly higher in Asia-Pacific countries excluding Japan. Overall, TB and HBV/HCV risk with CZP treatment is currently relatively low, as risk can be minimized with patient/physician education, screening, and vigilant treatment, according to international guidelines. Key Points:• TB rates were highest in eastern/central Europe, Mexico, and Asia-Pacific regions.• With the implementation of stricter TB screening and risk evaluations in 2007, especially in high TB incidence countries, there was a notable reduction TB occurrence.• Safety profile of biologics in real-world settings complements controlled studies.• TB and hepatitis (HBV/HCV) risk with certolizumab pegol (CZP) treatment is low.

Sign in / Sign up

Export Citation Format

Share Document