Artificial intelligence

Artificial Intelligence in Colonoscopy: A Systematic Review of Adenoma Versus Polyp Detection Rates (2025)

Posted on by

Type of publication:

Systematic Review

Author(s):

Rabba, Waseem; *Asif, Fatima; Younis, Muhammad Y; Nasrullah, Haris; Fatima, Laraib; Arif, Muhammad A.

Citation:

Cureus. 17(12):e98528, 2025 Dec.

Abstract:

Colonoscopy is the gold standard in the prevention of colorectal cancer, but the miss rates of adenoma are high, which restricts its efficacy. To improve lesion recognition, artificial intelligence (AI), especially computer-aided detection (CADe) systems, has been introduced. The aim of this systematic review was to compare AI-assisted colonoscopy in terms of its ability to improve adenoma detection rate (ADR) and polyp detection rate (PDR). An extensive search was performed on PubMed, Embase, and Cochrane Library from 2015 to 2025. There were 17 randomized controlled trials (RCTs) comparing the use of AI-assisted colonoscopy with normal colonoscopy. The methodological quality measure of the included RCTs was Cochrane Risk of Bias 2.0 (RoB 2.0), which subdivided the studies based on low risk, some concerns, or high risk of bias based on whether they were biased in this or that domain. The robVis tool was used to produce the visual summaries. AI-aided colonoscopy effectively enhanced both adenoma detection rate (ADR) and polyp detection rate (PDR) in all of the included studies over conventional colonoscopy. In adenoma detection, accuracy was more than 85%, and in polyp detection, more than 90%. The advantage was also found especially in the detection of small and flat adenomas, which are very often missed in routine practice. The use of AI in colonoscopy is strongly associated with an increase in the detection rate of adenoma and polyps, minimizing the risk of underdiagnosis. The results highlight the clinical promise of AI in the form of a decision-support tool across gastroenterologists and suggest that AI can be applied to enhance the outcomes of preventive and screening colorectal cancer. Future research should be cost-efficient and practical, and combined with some clinical activities.

DOI: 10.7759/cureus.98528

Link to full-text [open access - no password required]

Artificial Intelligence and Digital Therapy for Adolescent Mental Health in the UK; Opportunities, Barriers, and Ethical Consideration (2025)

Posted on by

Type of publication:

Journal article

Author(s):

Adindu K.N.; Akubue N.; Jude N.O.; Onakoya A.; Chukwunonye C.; Odion O.; *Okengwu C.G.; Uchechukwu N.; Osita-Obasi P.Z.; Ezike A.; Bello I.; Olenloa E.; Eruteya O.O.; Oyewole S.A.

Citation:

SSRN. (no pagination), 2025. Date of Publication: 20 May 2025. [preprint]

Abstract:

Background: Adolescence constitutes a critical developmental stage marked by the onset of mental health difficulties, yet timely access to effective mental health care remains a significant challenge for many adolescents in the United Kingdom (UK). Artificial intelligence (AI)-enabled digital therapies present innovative opportunities to address these gaps. Objective(s): This systematic review critically assesses current evidence on AI-driven digital interventions for adolescent mental health within the UK, highlighting their potential opportunities, barriers to implementation, and pertinent ethical considerations. Method(s): Employing a mixed-methods design, a systematic literature review adhering to PRISMA guidelines was combined with thematic analysis of semi-structured interviews. Comprehensive database searches (MEDLINE, PsycINFO, Web of Science; 2013-2023) targeted studies involving UK adolescents (ages 11-19) using AI-based mental health technologies. Included studies underwent rigorous quality appraisal (Cochrane RoB 2.0, ROBINS-I, CASP). Additional insights were gathered through stakeholder interviews (clinicians, AI developers, adolescent users). Result(s): Twenty-seven studies met inclusion criteria, investigating interventions such as AI chatbots, predictive analytics, mobile apps, and virtual environments targeting anxiety and depression. Key opportunities identified include enhanced accessibility for underserved populations, personalization through adaptive algorithms, proactive early-risk detection, scalability, cost-efficiency, and improved engagement via interactive interfaces. Significant implementation barriers encompassed technical infrastructure limitations, data security concerns, insufficient longitudinal efficacy data, socioeconomic disparities, and clinician scepticism. Ethical challenges emphasized informed consent, algorithm transparency, potential biases, unclear accountability, and clinician deskilling risks. Conclusion(s): AI-driven digital interventions offer substantial promise for augmenting adolescent mental health services in the UK. However, realizing their full potential necessitates addressing infrastructural, ethical, and evidentiary challenges through robust governance frameworks and continued rigorous research.

DOI: 10.2139/ssrn.5253224

Link to full-text [open access - no password required]

Interpretable Machine Learning for Predicting Multiple Sclerosis Conversion from Clinically Isolated Syndrome (2024)

Posted on by

Type of publication:
Journal article

Author(s):
Daniel E.C.; Tirunagari S.; Batth K.; Windridge D.; *Balla Y.

Citation:
medRxiv. (no pagination), 2024. Date of Publication: 19 Jul 2024. [preprint]

Abstract:
Background: Machine learning (ML) prediction of clinically isolated syndrome (CIS) conversion to multiple sclerosis (MS) could be used as a remote, preliminary tool by clinicians to identify high-risk patients that would benefit from early treatment. Objective(s): This study evaluates ML models to predict CIS to MS conversion and identifies key predictors. Method(s): Five supervised learning techniques (Naive Bayes, Logistic Regression, Decision Trees, Random Forests and Support Vector Machines) were applied to clinical data from 138 Lithuanian and 273 Mexican CIS patients. Seven different feature combinations were evaluated to determine the most effective models and predictors. Result(s): Key predictors common to both datasets included sex, presence of oligoclonal bands in CSF, MRI spinal lesions, abnormal visual evoked potentials and brainstem auditory evoked potentials. The Lithuanian dataset confirmed predictors identified by previous clinical research, while the Mexican dataset partially validated them. The highest F1 score of 1.0 was achieved using Random Forests on all features for the Mexican dataset and Logistic Regression with SMOTE Upsampling on all features for the Lithuanian dataset. Conclusion(s): Applying the identified high-performing ML models to the CIS patient datasets shows potential in assisting clinicians to identify high-risk patients.

Link to full-text [open access - no password required]

The Impact of Artificial Intelligence on Optimizing Diagnosis and Treatment Plans for Rare Genetic Disorders (2023)

Posted on by

Type of publication:Journal article

Author(s):Abdallah, Shenouda; Sharifa, Mouhammad; I Kh Almadhoun, Mohammed Khaleel; Khawar, Muhammad Muneeb Sr; Shaikh, Unzla; Balabel, Khaled M; Saleh, Inam; Manzoor, Amima; Mandal, Arun Kumar; *Ekomwereren, Osatohanmwen; Khine, Wai Mon; Oyelaja, Oluwaseyi T.

Citation:Cureus. 15(10):e46860, 2023 Oct.

Abstract:Rare genetic disorders (RDs), characterized by their low prevalence and diagnostic complexities, present significant challenges to healthcare systems. This article explores the transformative impact of artificial intelligence (AI) and machine learning (ML) in addressing these challenges. It emphasizes the need for accurate and early diagnosis of RDs, often hindered by genetic and clinical heterogeneity. This article discusses how AI and ML are reshaping healthcare, providing examples of their effectiveness in disease diagnosis, prognosis, image analysis, and drug repurposing. It highlights AI's ability to efficiently analyze extensive datasets and expedite diagnosis, showcasing case studies like Face2Gene. Furthermore, the article explores how AI tailors treatment plans for RDs, leveraging ML and deep learning (DL) to create personalized therapeutic regimens. It emphasizes AI's role in drug discovery, including the identification of potential candidates for rare disease treatments. Challenges and limitations related to AI in healthcare, including ethical, legal, technical, and human aspects, are addressed. This article underscores the importance of data ethics, privacy, and algorithmic fairness, as well as the need for standardized evaluation techniques and transparency in AI research. It highlights second-generation AI systems that prioritize patient-centric care, efficient patient recruitment for clinical trials, and the significance of high-quality data. The integration of AI with telemedicine, the growth of health databases, and the potential for personalized therapeutic recommendations are identified as promising directions for the field. In summary, this article provides a comprehensive exploration of how AI and ML are revolutionizing the diagnosis and treatment of RDs, addressing challenges while considering ethical implications in this rapidly evolving healthcare landscape.

Link to full-text [open access - no password required]

Altmetrics: