Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review.

INTRODUCTION: Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia. METHODS: We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases. RESULTS: A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort. DISCUSSION: The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice. HIGHLIGHTS: There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias.

Evaluation of compliance with isotretinoin PPP recommendations and exploration of reasons for non-compliance: Survey among French-speaking health care professionals and patients in Belgium.

PURPOSE: To evaluate awareness of and compliance in Belgium by French-speaking health care professionals and patients with the isotretinoin safety recommendations regarding its teratogenic risk. METHOD: Survey using online questionnaires, delivered from December 2014 to March 2015 for patients, pharmacists, dermatologists, and GPs and delivered again from September 2015 to October 2015 for GPs. RESULTS: Questionnaires were completed by 24 dermatologists, 24 GPs, 58 pharmacists, and 33 female patients. The pregnancy prevention programme was poorly known by health care professionals (23.6%) and patients (15.2%). Health care professionals informed women of childbearing age in depth about the teratogenic risk (98.3% of pharmacists and 100.0% of GPs and dermatologists) and the importance of an effective contraceptive method (87.9% and 100.0%, respectively). Patients were less informed about the pregnancy test (25.9% and 14.6%) and the need to use a second contraceptive method (29.3% and 27.1%). The low compliance with the last 2 recommendations was due to a lack of adoption by health care professionals regarding the need for these recommendations if female patients have an effective contraceptive method and the pregnancy risk is discussed in detail with them. CONCLUSION: The effectiveness of the pregnancy prevention programme recommendations should be reconsidered by an expert committee. Justifications should be added to effective recommendations to increase their adoption by health care professionals and patients.