DESIGN: De-identified images were provided retrospectively or collected prospectively by IVF clinics using the artificial intelligence model in clinical practice. A total of 9359 images were provided by 18 IVF clinics across six countries, from 4709 women who underwent IVF between 2011 and 2021. Main outcome measures included clinical pregnancy outcome (fetal heartbeat at first ultrasound scan), embryo morphology score, and/or pre-implantation genetic testing for aneuploidy (PGT-A) results.
RESULTS: A positive linear correlation of artificial intelligence scores with pregnancy outcomes was found, and up to a 12.2% reduction in time to pregnancy (TTP) was observed when comparing the artificial intelligence model with standard morphological grading methods using a novel simulated cohort ranking method. Artificial intelligence scores were significantly correlated with known morphological features of embryo quality based on the Gardner score, and with previously unknown morphological features associated with embryo ploidy status, including chromosomal abnormalities indicative of severity when considering embryos for transfer during IVF.
CONCLUSION: Improved methods for evaluating artificial intelligence for embryo selection were developed, and advantages of the artificial intelligence model over current grading approaches were highlighted, strongly supporting the use of the artificial intelligence model in a clinical setting.
OBJECTIVE: Our objective was to create a framework that can guide future implementation and research on the use of eHealth tools to support patients with growth disorders who require growth hormone therapy.
METHODS: A total of 12 pediatric endocrinologists with experience in eHealth, from a wide geographical distribution, participated in a series of online discussions. We summarized the discussions of 3 workshops, conducted during 2020, on the use of eHealth in the management of growth disorders, which were structured to provide insights on existing challenges, opportunities, and solutions for the implementation of eHealth tools across the patient journey, from referral to the end of pediatric therapy.
RESULTS: A total of 815 responses were collected from 2 questionnaire-based activities covering referral and diagnosis of growth disorders, and subsequent growth hormone therapy stages of the patient pathway, relating to physicians, nurses, and patients, parents, or caregivers. We mapped the feedback from those discussions into a framework that we developed as a guide to integration of eHealth tools across the patient journey. Responses focused on improved clinical management, such as growth monitoring and automation of referral for early detection of growth disorders, which could trigger rapid evaluation and diagnosis. Patient support included the use of eHealth for enhanced patient and caregiver communication, better access to educational opportunities, and enhanced medical and psychological support during growth hormone therapy management. Given the potential availability of patient data from connected devices, artificial intelligence can be used to predict adherence and personalize patient support. Providing evidence to demonstrate the value and utility of eHealth tools will ensure that these tools are widely accepted, trusted, and used in clinical practice, but implementation issues (eg, adaptation to specific clinical settings) must be addressed.
CONCLUSIONS: The use of eHealth in growth hormone therapy has major potential to improve the management of growth disorders along the patient journey. Combining objective clinical information and patient adherence data is vital in supporting decision-making and the development of new eHealth tools. Involvement of clinicians and patients in the process of integrating such technologies into clinical practice is essential for implementation and developing evidence that eHealth tools can provide value across the patient pathway.
METHOD: Two large datasets, including 1110 3D CT images, were split into five segments of 20% each. Each dataset's first 20% segment was separated as a holdout test set. 3D-CNN training was performed with the remaining 80% from each dataset. Two small external datasets were also used to independently evaluate the trained models.
RESULTS: The total combination of 80% of each dataset has an accuracy of 91% on Iranmehr and 83% on Moscow holdout test datasets. Results indicated that 80% of the primary datasets are adequate for fully training a model. The additional fine-tuning using 40% of a secondary dataset helps the model generalize to a third, unseen dataset. The highest accuracy achieved through transfer learning was 85% on LDCT dataset and 83% on Iranmehr holdout test sets when retrained on 80% of Iranmehr dataset.
CONCLUSION: While the total combination of both datasets produced the best results, different combinations and transfer learning still produced generalizable results. Adopting the proposed methodology may help to obtain satisfactory results in the case of limited external datasets.
Method: Scopus, PubMed, and Web of Science (all databases) were searched by 2 reviewers until 29th October 2020. Articles were screened and narratively synthesized according to PRISMA-DTA guidelines based on predefined eligibility criteria. Articles that made direct reference test comparisons to human clinicians were evaluated using the MI-CLAIM checklist. The risk of bias was assessed by JBI-DTA critical appraisal, and certainty of the evidence was evaluated using the GRADE approach. Information regarding the quantification method of dental pain and disease, the conditional characteristics of both training and test data cohort in the machine learning, diagnostic outcomes, and diagnostic test comparisons with clinicians, where applicable, were extracted.
Results: 34 eligible articles were found for data synthesis, of which 8 articles made direct reference comparisons to human clinicians. 7 papers scored over 13 (out of the evaluated 15 points) in the MI-CLAIM approach with all papers scoring 5+ (out of 7) in JBI-DTA appraisals. GRADE approach revealed serious risks of bias and inconsistencies with most studies containing more positive cases than their true prevalence in order to facilitate machine learning. Patient-perceived symptoms and clinical history were generally found to be less reliable than radiographs or histology for training accurate machine learning models. A low agreement level between clinicians training the models was suggested to have a negative impact on the prediction accuracy. Reference comparisons found nonspecialized clinicians with less than 3 years of experience to be disadvantaged against trained models.
Conclusion: Machine learning in dental and orofacial healthcare has shown respectable results in diagnosing diseases with symptomatic pain and with improved future iterations and can be used as a diagnostic aid in the clinics. The current review did not internally analyze the machine learning models and their respective algorithms, nor consider the confounding variables and factors responsible for shaping the orofacial disorders responsible for eliciting pain.
METHODS: After 10 min of supine rest, the subject was tilted at a 70-degree angle on a tilt table for approximately a total of 35 min. 400 µg of glyceryl trinitrate (GTN) was administered sublingually after the first 20 min and monitoring continued for another 15 min. Mean imputation and K-nearest neighbors (KNN) imputation approaches to handle missing values. Next, feature selection techniques were implemented, including genetic algorithm, recursive feature elimination, and feature importance, to determine the crucial features. The Mann-Whitney U test was then performed to determine the statistical difference between two groups. Patients with VVS are categorized via machine learning models including Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), Multinomial Naïve Bayes (MNB), KNN, Logistic Regression (LR), and Random Forest (RF). The developed model is interpreted using an explainable artificial intelligence (XAI) model known as partial dependence plot.
RESULTS: A total of 137 subjects aged between 9 and 93 years were recruited for this study, 54 experienced clinical symptoms were considered positive tests, while the remaining 83 tested negative. Optimal results were obtained by combining the KNN imputation technique and three tilting features with SVM with 90.5% accuracy, 87.0% sensitivity, 92.7% specificity, 88.6% precision, 87.8% F1 score, and 95.4% ROC (receiver operating characteristics) AUC (area under curve).
CONCLUSIONS: The proposed algorithm effectively classifies VVS patients with over 90% accuracy. However, the study was confined to a small sample size. More clinical datasets are required to ensure that our approach is generalizable.