Machine Learning in Clinical Trials: A Primer with Applications to Neurology

Miller, Matthew; Shih, Ludy C.; Kolachalama, Vijaya B.

doi:10.1007/s13311-023-01384-2

Cited by 10 publications

(3 citation statements)

References 157 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike traditional medical interventions that undergo rigorous clinical trials before receiving regulatory approval, AI and ML algorithms pose unique challenges in terms of validation and regulation. The iterative nature of algorithmic development coupled with the dynamic nature of healthcare data complicates the assessment of the clinical validity and reliability of AI-driven technologies [ 40 ]. Clinical validation is a critical step in the deployment of AI and ML algorithms in health care to ensure that these technologies deliver accurate, reliable, and clinically relevant results.…”

Section: Reviewmentioning

confidence: 99%

Ethical Considerations in the Use of Artificial Intelligence and Machine Learning in Health Care: A Comprehensive Review

Harishbhai Tilala,

Kumar Chenchala,

Choppadandi

et al. 2024

Cureus

View full text Add to dashboard Cite

Artificial intelligence (AI) and machine learning (ML) technologies are revolutionizing health care by offering unprecedented opportunities to enhance patient care, optimize clinical workflows, and advance medical research. However, the integration of AI and ML into healthcare systems raises significant ethical considerations that must be carefully addressed to ensure responsible and equitable deployment. This comprehensive review explored the multifaceted ethical considerations surrounding the use of AI and ML in health care, including privacy and data security, algorithmic bias, transparency, clinical validation, and professional responsibility. By critically examining these ethical dimensions, stakeholders can navigate the ethical complexities of AI and ML integration in health care, while safeguarding patient welfare and upholding ethical principles. By embracing ethical best practices and fostering collaboration across interdisciplinary teams, the healthcare community can harness the full potential of AI and ML technologies to usher in a new era of personalized data-driven health care that prioritizes patient well-being and equity.

show abstract

Section: Reviewmentioning

confidence: 99%

Ethical Considerations in the Use of Artificial Intelligence and Machine Learning in Health Care: A Comprehensive Review

Harishbhai Tilala,

Kumar Chenchala,

Choppadandi

et al. 2024

Cureus

View full text Add to dashboard Cite

show abstract

“…These designs include Sequential Multiphase Adaptive Trials (SMART) and Multiphase Optimization Strategy Trials (MOST; Collins et al, 2007) which leverage the power of factorial designs and Q-learning techniques to estimate outcomes for sequences of intervention based on decision rules (e.g., adding DBT should affective lability fail to otherwise decrease during Phase I of CBT-E) or comparing treatment responses to specific elements of treatment (i.e., self-monitoring, cognitive restructuring, motivational interviewing, etc.). Extended further, the search for an algorithm that can alter study designs and probe intervention effects now includes options like machine learning and causal algorithm developments as part of their workflow (Miller et al, 2023) with ambitious pursuit of tailoring treatments more effectively through within-subject responses to clinical intervention.…”

Section: Sequences Mechanisms and Targetsmentioning

confidence: 99%

Adapting dose–response methodology to improve clinical trial design for psychotherapies

Sysko,

Holland,

Hildebrandt

2023

Intl J Eating Disorders

View full text Add to dashboard Cite

ObjectiveConventional randomized controlled trials (RCTs) have long served as the foundation of research in clinical psychology; however, most treatments for eating disorders show only modest effects on reduction of symptoms and maintenance of long‐term remission. New options for psychotherapy treatment development research, beyond continuing to pursue additive or subpopulation approaches, are needed.MethodsOne option is to apply dose–response designs, which are commonplace in studies of pharmacology, toxicology, and medical research, and characterized by the evaluation of the amount of exposure (dose) to an intervention, and the resulting changes in body function or health (response).ResultsEating disorder interventions are particularly well‐suited for dose–response treatment designs. The deadly nature of eating disorders makes it imperative that patients are not turned away for not being “ready” to engage with treatment. By identifying optimal doses, research will likely yield a more parsimonious course of treatment, which will lend itself to reduced costs, greater uptake, and reduced drop‐out.DiscussionLimited use of within‐subject designs in trials for patients with eating disorders has produced fast‐track efficacy studies and omitted key elements in the treatment development pathway. To decrease reliance on RCT's, dose–response methods should be applied as an alternative study design.Public SignificanceEating disorders are associated with medical and psychiatric comorbidities, poor quality of life, and high mortality. Access to evidence‐based services for patients with eating disorders is limited, and identifying additional effective treatment options can be difficult because of challenges inherent to randomized‐controlled trials. This manuscript describes an alternative trial methodology to maximize the information that can be gathered prior to utilizing a standard large‐scale efficacy design.

show abstract

“…Machine learning (ML) is a branch of artificial intelligence (AI) and computer science that uses large amounts of data to create complex predictions and decision-making systems that would otherwise be difficult to achieve. Decision-making systems based on ML are increasingly being used in decisions about bank loans (Karthiban et al, 2019), employment (Imam & Ananda, 2022), clinical trials (Miller et al, 2023) and in many other areas. The success of ML-enabled systems depends on the properties of the ML solutions (like performance, transparency, maintainability, interoperability, etc.…”

Section: Introductionmentioning

confidence: 99%

The Efficiency of Machine Learning Algorithms in Classifying Non-Functional Requirements

Maciejauskaitė,

Miliauskaitė

2024

New Trends in Computer Sciences

View full text Add to dashboard Cite

Machine learning (ML) algorithms are more and more widely applied in various types of systems, so the research related to them is also increasing. One of the areas of research under consideration is the classification of non-functional requirements (NFRs) using ML algorithms. This area of research is important because the automatic classification of NFRs using high-performance ML algorithms and corresponding features helps requirements engineers classify non-functional requirements more accurately. This paper examines ML algorithms suitable for solving classification problems and their effectiveness in classifying non-functional requirements. Based on the described stages of the research methodology ML algorithms models were compared using the accuracy, precision, recall, and F-score metrics. A majority voting classifier model was created using Support Vector Machine, Naïve Bayes and K Nearest Neighbor Algorithm algorithms. After K-Fold cross validation were obtained these results: accuracy – 0.710 (scale from 0 to 1), precision – 0.845, recall – 0.814 and F-score – 0.815.

show abstract

Machine Learning in Clinical Trials: A Primer with Applications to Neurology

Cited by 10 publications

References 157 publications

Ethical Considerations in the Use of Artificial Intelligence and Machine Learning in Health Care: A Comprehensive Review

Ethical Considerations in the Use of Artificial Intelligence and Machine Learning in Health Care: A Comprehensive Review

Adapting dose–response methodology to improve clinical trial design for psychotherapies

The Efficiency of Machine Learning Algorithms in Classifying Non-Functional Requirements

Contact Info

Product

Resources

About