Insulin resistance (IR) is considered the precursor and the key pathophysiological mechanism of type 2 diabetes (T2D) and metabolic syndrome (MetS). However, the pathways that IR shares with T2D are not clearly understood. Meta-analysis of multiple DNA microarray datasets could provide a robust set of metagenes identified across multiple studies. These metagenes would likely include a subset of genes (key metagenes) shared by both IR and T2D, and possibly responsible for the transition between them. In this study, we attempted to find these key metagenes using a feature selection method, LASSO, and then used the expression profiles of these genes to train five machine learning models: LASSO, SVM, XGBoost, Random Forest, and ANN. Among them, ANN performed well, with an area under the curve (AUC) > 95%. It also demonstrated fairly good performance in differentiating diabetics from normal glucose tolerant (NGT) persons in the test dataset, with 73% accuracy across 64 human adipose tissue samples. Furthermore, these core metagenes were also enriched in diabetes-associated terms and were found in previous genome-wide association studies of T2D and its associated glycemic traits HOMA-IR and HOMA-B. Therefore, this metagenome deserves further investigation with regard to the cardinal molecular pathological defects/pathways underlying both IR and T2D.

Machine Learning Model Based on Insulin Resistance Metagenes Underpins Genetic Basis of Type 2 Diabetes.

Paracetamol/acetaminophen (single administration) for perineal pain in the early postpartum period.

Artificial intelligence (AI) has potential uses in healthcare including the detection of health conditions and prediction of health outcomes. Past systematic reviews had reviewed the accuracy of artificial neural networks (ANN) on Electrocardiogram (ECG) readings but that of other AI models on other Acute Coronary Syndrome (ACS) detection tools remains unclear.
Nine electronic databases were searched from 2012 to 31 August 2022 including grey literature search and hand searching of references of included articles. Risk of bias was assessed by two independent reviewers using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). Test characteristics namely true positives, false positives, true negatives, and false negatives were extracted from all included articles into a 2x2 table. Study-specific estimates of sensitivity and specificity were pooled using hierarchical summary receiver operating characteristic (HSROC) model and displayed using a forest plot and HSROC curve.
66 studies were included in the review. A total of 518,931 patients were included whose mean ages varied from 32.62 to 70 years old. In 66 studies, the sensitivity and specificity of AI-based detection for ACS screening ranged from 64 % to 100 % and 65 %-100 %, respectively. The overall quality of evidence was low due to the inclusion of case-control studies.
Results of the study inform the potential of using AI-assisted ACS detection for accurate diagnosis and prompt treatment for ACS. Adherence to the Standards for Reporting of Diagnostic Accuracy (STARD) guideline and having more cohort studies for future Diagnostic Test Accuracy (DTA) studies are necessary to improve the quality of evidence of AI-based detection of ACS.

Diagnostic Test Accuracy of artificial intelligence-assisted detection of acute coronary syndrome: A systematic review and meta-analysis.

Oral cancer can show heterogenous patterns of behavior. For proper and effective management of oral cancer, early diagnosis and accurate prediction of prognosis are important. To achieve this, artificial intelligence (AI) or its subfield, machine learning, has been touted for its potential to revolutionize cancer management through improved diagnostic precision and prediction of outcomes. Yet, to date, it has made only few contributions to actual medical practice or patient care.
This study provides a systematic review of diagnostic and prognostic application of machine learning in oral squamous cell carcinoma (OSCC) and also highlights some of the limitations and concerns of clinicians towards the implementation of machine learning-based models for daily clinical practice.
We searched OvidMedline, PubMed, Scopus, Web of Science, and Institute of Electrical and Electronics Engineers (IEEE) databases from inception until February 2020 for articles that used machine learning for diagnostic or prognostic purposes of OSCC.
Only original studies that examined the application of machine learning models for prognostic and/or diagnostic purposes were considered.
Independent extraction of articles was done by two researchers (A.R. & O.Y) using predefine study selection criteria. We used the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) in the searching and screening processes. We also used Prediction model Risk of Bias Assessment Tool (PROBAST) for assessing the risk of bias (ROB) and quality of included studies.
A total of 41 studies were published to have used machine learning to aid in the diagnosis/or prognosis of OSCC. The majority of these studies used the support vector machine (SVM) and artificial neural network (ANN) algorithms as machine learning techniques. Their specificity ranged from 0.57 to 1.00, sensitivity from 0.70 to 1.00, and accuracy from 63.4 % to 100.0 % in these studies. The main limitations and concerns can be grouped as either the challenges inherent to the science of machine learning or relating to the clinical implementations.
Machine learning models have been reported to show promising performances for diagnostic and prognostic analyses in studies of oral cancer. These models should be developed to further enhance explainability, interpretability, and externally validated for generalizability in order to be safely integrated into daily clinical practices. Also, regulatory frameworks for the adoption of these models in clinical practices are necessary.

Machine learning in oral squamous cell carcinoma: Current status, clinical concerns and prospects for future-A systematic review.

Blood transfusions are frequently administered in cardiac surgery. Despite a large number of published studies comparing a "restrictive" strategy with a "liberal" strategy, no clear consensus has emerged to guide blood transfusion practice in cardiac surgery patients. The purpose of this study was to identify, critically appraise, and summarize the evidence on the overall effect of restrictive transfusion strategies compared with liberal transfusion strategies on mortality, other clinical outcomes, and transfusion-related outcomes in adult patients undergoing cardiac surgery.
We searched MEDLINE (OvidSP), EMBASE (OvidSP) and Cochrane CENTRAL (Wiley) from inception to 1 December 2017 and queried clinical trial registries and conference proceedings for randomized-controlled trials of liberal vs restrictive transfusion strategies in cardiac surgery.
From 7,908 citations, we included ten trials (9,101 patients) and eight companion publications. Overall, we found no significant difference in mortality between restrictive and liberal transfusion strategies (risk ratio [RR], 1.08; 95% confidence interval [CI], 0.76 to 1.54; I
In adult patients undergoing cardiac surgery, a restrictive transfusion strategy reduces RBC transfusion without impacting mortality rate or the incidence of other perioperative complications. Nevertheless, further large trials in subgroups of patients, potentially of differing age, are needed to establish firm evidence to guide transfusion in cardiac surgery.
PROSPERO (CRD42017071440); registered 20 April, 2018.
RéSUMé: OBJECTIF: Les transfusions sanguines sont fréquentes après une chirurgie cardiaque. Malgré le nombre important d’études publiées comparant une stratégie « restrictive » à une stratégie « libérale », aucun consensus clair n’est apparu pour guider la pratique de la transfusion sanguine chez les patients de chirurgie cardiaque. L’objectif de cette étude était d’identifier, d’évaluer de façon critique et de résumer les données probantes sur l’effet global des stratégies de transfusion restrictives comparativement aux stratégies libérales sur la mortalité, les autres devenirs cliniques, et les devenirs liés à la transfusion chez des patients adultes subissant une chirurgie cardiaque.
Nous avons réalisé des recherches dans les bases de données MEDLINE (OvidSP), EMBASE (OvidSP) et Cochrane CENTRAL (Wiley) de leur création jusqu’au 1
Sur 7908 citations, nous avons inclus dix études (9101 patients) et huit publications connexes. Globalement, nous n’avons observé aucune différence significative en matière de mortalité entre les stratégies transfusionnelles restrictives et libérales (risque relatif [RR], 1,08; intervalle de confiance [IC] 95 %, 0,76 à 1,54; I
Dans une population de patients adultes subissant une chirurgie cardiaque, une stratégie transfusionnelle restrictive réduit la transfusion d’érythrocytes sans avoir d’impact sur le taux de mortalité ou sur l’incidence d’autres complications périopératoires. D’autres grandes études sur différents sous-groupes de patients, peut-être d’âges différents, sont toutefois nécessaires afin d’établir des données probantes concluantes pour guider les transfusions en chirurgie cardiaque. ENREGISTREMENT DE L’éTUDE: PROSPERO (CRD42017071440); enregistrée le 20 avril 2018.

The effect of restrictive versus liberal transfusion strategies on longer-term outcomes after cardiac surgery: a systematic review and meta-analysis with trial sequential analysis.

Around the world, the use of modern contraceptives has risen significantly, but the quality and reach of sexual and reproductive health services remains weak in the poorest countries. To address the high unmet need, an opportunity arises for mobile health technology (mHealth) to empower both clients and providers. However, evidence that mHealth is effective in increasing modern contraceptive use is limited and mixed, and we set out to assess its impact.
A systematic literature search from seven electronic databases was conducted using key search terms. Individually randomised controlled trials that compared modern contraceptive use in women and men using phone message interventions and those without the intervention were included. Stata was used to calculate pooled estimates of effect under the random-effects model, as well as produce the risk of bias using the Egger's regression method. GRADEpro GDT was used to assess the quality of individual studies.
A pooled estimate of all of the studies showed a positive association between phone messages and contraception use, but no clear evidence of benefit (OR 1.12; 95% CI 0.97-1.29). Notably, pooled results of studies that reported modern contraceptive use as the primary outcome showed that mobile phone messaging was associated with an increase in the use of modern contraception (OR 1.22; 95% CI 1.01-1.47).
The finding of this systematic review suggests that mobile phone message interventions utilising a behavioural change technique are an effective method of increasing modern contraceptive use among men and women of reproductive age in low- and middle-income countries though the effect is small.
Partout dans le monde, l'utilisation de contraceptifs modernes a considérablement augmenté, mais la qualité et la portée des services de santé sexuelle et reproductive restent faibles dans les pays les plus pauvres. Pour répondre à cet important besoin non satisfait, une opportunité se présente avec la technologie de la santé mobile (mHealth) permettant d'autonomiser à la fois les patients et les prestataires. Cependant, les preuves que mHealth est efficace pour augmenter l'utilisation de la contraception moderne sont limitées et mitigées, et nous avons entrepris d'évaluer son impact. MÉTHODES: Une recherche systématique de la littérature dans 7 bases de données électroniques a été menée à l'aide de termes de recherche clés. Des essais contrôlés randomisés individuels comparant l'utilisation de la contraception moderne chez les femmes et les hommes utilisant des interventions via des messages téléphoniques et ceux sans intervention ont été inclus. Stata a été utilisé pour calculer des estimations d'effet poolées selon le modèle à effets aléatoires, ainsi que pour produire le risque de biais à l'aide de la méthode de régression d'Egger. GRADEpro GDT a été utilisé pour évaluer la qualité des études individuelles. RÉSULTATS: Une estimation poolée de toutes les études a montré une association positive entre les messages téléphoniques et l'utilisation de la contraception, mais aucune preuve claire de bénéfice (OR 1,12; IC95%: 0,97–1,29). Notamment, les résultats poolés des études qui rapportaient sur l'utilisation de la contraception moderne comme critère principal ont montré que la messagerie par téléphone mobile était associée à une augmentation de l'utilisation de la contraception moderne (OR 1,22; IC95%: 1,01–1,47).
Les résultats de cette revue systématique suggèrent que les interventions de messagerie par téléphone mobile utilisant une technique de changement de comportement sont une méthode efficace pour augmenter l'utilisation de la contraception moderne chez les hommes et les femmes en âge de procréer dans les pays à revenu faible ou intermédiaire, bien que l'effet soit faible.

Impact of mHealth on contraceptive use among women and men of reproductive age in low- and middle-income countries: a systematic review and meta-analysis.

Papers