Diabetes & Metabolic Syndrome-Clinical Research & Reviews最新文献

{"title":"Corrigendum to “Cardiometabolic disease and multiple long-term condition healthcare provision in Sub-Saharan Africa: Opportunities for new models of care in the post-COVID era” [Diabetes Metabol Syndr: Clin Res Rev 17 1 (January 2023) 102681]","authors":"Patrick J. Highton , Shabana Cassambai , Neusa Jessen , George N. Agot , Michelle Hadjiconstantinou , Melanie Davies , Samuel Seidu , Peter K. Njoroge , Joyce Muhenge Olenja , Pamela Godia , Albertino Damasceno , Roberta Lamptey , Kamlesh Khunti","doi":"10.1016/j.dsx.2024.103061","DOIUrl":"10.1016/j.dsx.2024.103061","url":null,"abstract":"","PeriodicalId":48252,"journal":{"name":"Diabetes & Metabolic Syndrome-Clinical Research & Reviews","volume":"18 5","pages":"Article 103061"},"PeriodicalIF":4.3,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S187140212400122X/pdfft?md5=a9e484ebca6821cf844f3b98b42f7536&pid=1-s2.0-S187140212400122X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141332322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The effects of anti-TNF-α biologics on insulin resistance and insulin sensitivity in patients with rheumatoid arthritis: An update systematic review and meta-analysis","authors":"Wei Shyann Lim ,&nbsp;Seth En Teoh ,&nbsp;Ansel Shao Pin Tang ,&nbsp;Beatrice Jia Min Tan ,&nbsp;Jasmine Yiling Lee ,&nbsp;Chun En Yau ,&nbsp;Julian Thumboo ,&nbsp;Qin Xiang Ng","doi":"10.1016/j.dsx.2024.103001","DOIUrl":"https://doi.org/10.1016/j.dsx.2024.103001","url":null,"abstract":"<div><h3>Background and aim</h3><p>Increasing evidence demonstrates a link between the chronic inflammatory state in patients with rheumatoid arthritis (RA) and the development of insulin resistance. It is thought that <em>anti</em>-TNF-α biologic therapy may improve insulin sensitivity and ameliorate insulin resistance by the downregulation of inflammatory cytokines, however, pre-clinical and clinical studies have yielded conflicting results. A meta-analysis on this topic is necessary to summarize current evidence and generate hypotheses for future research.</p></div><div><h3>Methods</h3><p>Literature search was performed in four databases, namely PubMed, EMBASE, Scopus, and The Cochrane Library, from inception till April 9, 2023, querying studies reporting peripheral insulin resistance with and without <em>anti</em>-TNF-α use in patients with RA. Peripheral insulin resistance or sensitivity was quantified by the Homeostasis Model Assessment of Insulin Resistance (HOMA) index or the Quantitative Insulin Sensitivity Check Index (QUICKI) respectively. The difference in insulin resistance or sensitivity between the treatment and control group was calculated using standardized mean difference (SMD) for the purposes of the meta-analysis.</p></div><div><h3>Results</h3><p>Twelve articles were reviewed, with 10 longitudinal studies with a total of 297 patients included in the meta-analysis. The pooled standardized mean difference (SMD) from baseline HOMA was −0.82 (95% CI: −1.38 to −0.25) suggesting significant beneficial effects of <em>anti</em>-TNF-α therapy on insulin resistance.</p></div><div><h3>Conclusion</h3><p>Current evidence supports the significant clinical efficacy of <em>anti</em>-TNF-α biologics in alleviating insulin resistance and improving insulin sensitivity in patients with active RA.</p></div>","PeriodicalId":48252,"journal":{"name":"Diabetes & Metabolic Syndrome-Clinical Research & Reviews","volume":"18 4","pages":"Article 103001"},"PeriodicalIF":10.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140543179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A new era for food in health? The FDA announces a qualified health claim for yogurt intake and type II diabetes mellitus risk reduction","authors":"Ronan Lordan","doi":"10.1016/j.dsx.2024.103006","DOIUrl":"https://doi.org/10.1016/j.dsx.2024.103006","url":null,"abstract":"<div><h3>Introduction</h3><p>Over the last two decades research has grown regarding dairy intake and health. It has been reported by many that yogurt intake may be associated with reduced risk of type 2 diabetes mellitus (T2D). In this report, the United States Food and Drug Administration (FDA) decision to announce a qualified health claim for yogurt products regarding reduced risk of T2D in response to a Danone North America petition is discussed.</p></div><div><h3>Methods</h3><p>Relevant literature cited in the petition along with supporting evidence from PubMed and Google Scholar databases until April 1st, 2024 were used. Literature was found using relevant keywords.</p></div><div><h3>Results</h3><p>On March 1st, 2024, the United States Food and Drug Administration (FDA) announced the first ever qualified health claim, stating that there that eating yogurt regularly may reduce the risk of T2D according to limited scientific evidence. The enforcement discretion letter was critically reviewed and discussed regarding its future implications for people with T2M and public health.</p></div><div><h3>Conclusions</h3><p>It is unclear how this FDA decision will affect public health and nutrition in the long-term. Limited scientific evidence suggests that at least 3 servings of yogurt per week may reduce the risk of T2D incidence for the general population. Yogurt will not cure or treat people with T2D.</p></div>","PeriodicalId":48252,"journal":{"name":"Diabetes & Metabolic Syndrome-Clinical Research & Reviews","volume":"18 4","pages":"Article 103006"},"PeriodicalIF":10.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140550860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of a diabetes-designed meal delivery service on changes in hemoglobin A1c and quality of life in patients with diabetes","authors":"Bryan A. Farford ,&nbsp;Brian J. Eglinger ,&nbsp;Lindsey Kane ,&nbsp;James N. Gilbert ,&nbsp;Colleen T. Ball","doi":"10.1016/j.dsx.2024.103004","DOIUrl":"https://doi.org/10.1016/j.dsx.2024.103004","url":null,"abstract":"<div><h3>Background</h3><p>Over 34 million Americans have diabetes, and nutrition therapy is essential in self-management.</p></div><div><h3>Aims</h3><p>The primary aim of the study was to evaluate the impact of meals designed for patients with type 2 diabetes (T2D) through a meal delivery program. The primary outcome was a 3-month change in hemoglobin A_1c (HbA_1c). Secondary outcomes included a 3-month change in weight, blood pressure, high-density lipoprotein, low-density lipoprotein, and triglycerides. Furthermore, the study aimed to evaluate the impact of the meal delivery program on the participants' quality of life.</p></div><div><h3>Methods</h3><p>In this randomized crossover clinical trial, patients were allocated in a 1:1 fashion to treatment sequence AB or treatment sequence BA. In Phase 1, participants allocated to sequence AB received 10 meals per week for 3 months, followed by a 3-month washout period and a 3-month standard intervention period with no meals. Participants allocated to sequence BA received 3 months of standard intervention with no meals followed by a 3-month washout period and a 3-month period with 10 meals per week. A quality-of-life survey was obtained during weeks 0, 12, 24, and 36.</p></div><div><h3>Results</h3><p>The mean 3-month change in HbA_1c (primary outcome) was nearly a half point lower with meal delivery (−0.44% [95% CI: −0.85%, −0.03%]; <em>P</em> = 0.037). The estimated mean 3-month change in quality of life was approximately 2 points lower (better) with meal delivery (−2.2 points [95% CI: −4.2, −0.3]; <em>P</em> = .027). There were no statistically significant differences in secondary outcomes with meal delivery (all <em>P</em> ≥ 0.15).</p></div><div><h3>Conclusions</h3><p>A meal delivery system for patients with T2D improves glycemic control and quality of life.</p></div>","PeriodicalId":48252,"journal":{"name":"Diabetes & Metabolic Syndrome-Clinical Research & Reviews","volume":"18 4","pages":"Article 103004"},"PeriodicalIF":10.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140553897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Medical, pharmaceutical, and nutritional applications of 3D-printing technology in diabetes","authors":"Reza Amin ,&nbsp;Sayed Mahdi Hossaeini Marashi ,&nbsp;Seyyed Mohammad Reza Noori ,&nbsp;Zeinab Alavi ,&nbsp;Elaheh Dehghani ,&nbsp;Reyhaneh Maleki ,&nbsp;Mehdi Safdarian ,&nbsp;Arash Rocky ,&nbsp;Enayat Berizi ,&nbsp;Seyyed Mohammad Amin Alemohammad ,&nbsp;Setayesh Zamanpour ,&nbsp;Seyyed Mohammad Ali Noori","doi":"10.1016/j.dsx.2024.103002","DOIUrl":"https://doi.org/10.1016/j.dsx.2024.103002","url":null,"abstract":"<div><h3>Aims</h3><p>Despite numerous studies covering the various features of three-dimensional printing (3D printing) technology, and its applications in food science and disease treatment, no study has yet been conducted to investigate applying 3D printing in diabetes. Therefore, the present study centers on the utilization and impact of 3D printing technology in relation to the nutritional, pharmaceutical, and medicinal facets of diabetes management. It highlights the latest advancements, and challenges in this field.</p></div><div><h3>Methods</h3><p>In this review, the articles focusing on the application and effect of 3D printing technology on medical, pharmaceutical, and nutritional aspects of diabetes management were collected from different databases.</p></div><div><h3>Result</h3><p>High precision of 3D printing in the placement of cells led to accurate anatomic control, and the possibility of bio-printing pancreas and β-cells. Transdermal drug delivery via 3D-printed microneedle (MN) patches was beneficial for the management of diabetes disease. 3D printing supported personalized medicine for Diabetes Mellitus (DM). For instance, it made it possible for pharmaceutical companies to manufacture unique doses of medications for every diabetic patient. Moreover, 3D printing allowed the food industry to produce high-fiber and sugar-free products for the individuals with DM.</p></div><div><h3>Conclusions</h3><p>In summary, applying 3D printing technology for diabetes management is in its early stages, and needs to be matured and developed to be safely used for humans. However, its rapid progress in recent years showed a bright future for the treatment of diabetes.</p></div>","PeriodicalId":48252,"journal":{"name":"Diabetes & Metabolic Syndrome-Clinical Research & Reviews","volume":"18 4","pages":"Article 103002"},"PeriodicalIF":10.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140550862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance of European prediction models for classification of type 1 and type 2 diabetes in Indians","authors":"Ulagamadesan Venkatesan ,&nbsp;Anandakumar Amutha ,&nbsp;Angus G. Jones ,&nbsp;Beverley M. Shields ,&nbsp;Ranjit Mohan Anjana ,&nbsp;Ranjit Unnikrishnan ,&nbsp;Bagavandas Mappillairaju ,&nbsp;Viswanathan Mohan","doi":"10.1016/j.dsx.2024.103007","DOIUrl":"https://doi.org/10.1016/j.dsx.2024.103007","url":null,"abstract":"<div><h3>Aim</h3><p>We aimed to determine the performance of European prediction models in an Indian population to classify type 1 diabetes(T1D) and type 2 diabetes(T2D).</p></div><div><h3>Methods</h3><p>We assessed discrimination and calibration of published models of diabetes classification, using retrospective data from electronic medical records of 83309 participants aged 18–50 years living in India. Diabetes type was defined based on <em>C</em>-peptide measurement and early insulin requirement. Models assessed combinations of clinical measurements: age at diagnosis, body mass index(mean = 26.6 kg/m²), sex(male = 64.9 %), Glutamic acid decarboxylase(GAD) antibody, serum cholesterol, serum triglycerides, and high-density lipoprotein(HDL) cholesterol.</p></div><div><h3>Results</h3><p>67955 participants met inclusion criteria, of whom 0.8 % had T1D, which was markedly lower than model development cohorts. Model discrimination for clinical features was broadly similar in our Indian cohort compared to the European cohort: area under the receiver operating characteristic curve(AUC ROC) was 0.90 vs. 0.90 respectively, but was lower in the subset of young participants with measured GAD antibodies(n = 2404): and an AUC ROC of 0.87 when clinical features, sex, lipids and GAD antibodies were combined. All models substantially overestimated the likelihood of T1D, reflecting the lower prevalence of T1D in the Indian population. However, good model performance was achieved after recalibration by updating the model intercept and slope.</p></div><div><h3>Conclusion</h3><p>Models for diabetes classification maintain the discrimination of T1D and T2D in this Indian population, where T2D is far more common, but require recalibration to obtain appropriate model probabilities. External validation and recalibration are needed before these tools can be used in non-European populations.</p></div>","PeriodicalId":48252,"journal":{"name":"Diabetes & Metabolic Syndrome-Clinical Research & Reviews","volume":"18 4","pages":"Article 103007"},"PeriodicalIF":10.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140604715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing outcome prediction by applying the 2019 WHO DM classification to adults with hyperglycemic crises: A single-center cohort in Thailand","authors":"Chatchon Kaewkrasaesin ,&nbsp;Weerapat Kositanurit ,&nbsp;Phawinpon Chotwanvirat ,&nbsp;Nitchakarn Laichuthai","doi":"10.1016/j.dsx.2024.103012","DOIUrl":"https://doi.org/10.1016/j.dsx.2024.103012","url":null,"abstract":"<div><h3>Background and aims</h3><p>Hyperglycemic crisis is a metabolic catastrophe which can occur in any type of diabetes. In 2019, the World Health Organization (WHO) revised the classification of diabetes mellitus (DM) and established two new hybrid forms, latent autoimmune diabetes in adults (LADA) and ketosis-prone type 2 diabetes (T2D). This study aimed to determine clinical outcomes after a hyperglycemic crisis event in people with diabetes classified subtypes by 2019 WHO DM classification.</p></div><div><h3>Methods</h3><p>A five-year (2015–2019) retrospective study of adult patients admitted with hyperglycemic crises was conducted. Types of diabetes were recategorized based on the 2019 WHO DM classification. Clinical characteristics, in-admission treatment and complications, long-term follow-up outcomes, and mortality were collected, analyzed, and compared.</p></div><div><h3>Results</h3><p>A total of 185 admissions occurred in 136 patients. The mean age was 50.6 ± 18.4 years (49.3 % men). The annual average incidence of hyperglycemic crises was 5.2 events/1000 persons. The proportion of type 1 diabetes, T2D, LADA, ketosis-prone T2D, and pancreatic DM were 15.4 %, 69.1 %, 2.2 %, 11 %, and 2.2 %, respectively. In-hospital mortality was 3.7 % while cumulative mortality totaled 19.1 %. During the 24-month follow-up, ketosis-prone T2D had the highest success of insulin discontinuation (HR 6.59; 95 % CI 6.69–319.4; p &lt; 0.001), while T2D demonstrated the highest mortality compared to others (HR, 2.89; 95%CI 1.15–6.27; p = 0.02).</p></div><div><h3>Conclusion</h3><p>The reclassification of diabetes based on 2019 WHO DM classification helped elucidate differences in long-term outcomes and mortality among DM types. The new classification, which separates ketosis-prone T2D from standard T2D, should be encouraged in clinical practice for precise and individualized management.</p></div>","PeriodicalId":48252,"journal":{"name":"Diabetes & Metabolic Syndrome-Clinical Research & Reviews","volume":"18 4","pages":"Article 103012"},"PeriodicalIF":10.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140622269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incorporating polygenic risk into the Leicester Risk Assessment score for 10-year risk prediction of type 2 diabetes","authors":"Xiaonan Liu ,&nbsp;Thomas J. Littlejohns ,&nbsp;Jelena Bešević ,&nbsp;Fiona Bragg ,&nbsp;Lei Clifton ,&nbsp;Jennifer A. Collister ,&nbsp;Eirini Trichia ,&nbsp;Laura J. Gray ,&nbsp;Kamlesh Khunti ,&nbsp;David J. Hunter","doi":"10.1016/j.dsx.2024.102996","DOIUrl":"10.1016/j.dsx.2024.102996","url":null,"abstract":"<div><h3>Aims</h3><p>We evaluated whether incorporating information on ethnic background and polygenic risk enhanced the Leicester Risk Assessment (LRA<em>)</em> score for predicting 10-year risk of type 2 diabetes.</p></div><div><h3>Methods</h3><p>The sample included 202,529 UK Biobank participants aged 40–69 years. We computed the <em>LRA score</em>, and developed two new risk scores using training data (80% sample): <em>LRArev</em>, which incorporated additional information on ethnic background, and <em>LRAprs</em>, which incorporated polygenic risk for type 2 diabetes. We assessed discriminative and reclassification performance in a test set (20% sample). Type 2 diabetes was ascertained using primary care, hospital inpatient and death registry records.</p></div><div><h3>Results</h3><p>Over 10 years, 7,476 participants developed type 2 diabetes. The Harrell's C indexes were 0.796 (95% Confidence Interval [CI] 0.785, 0.806), 0.802 (95% CI 0.792, 0.813), and 0.829 (95% CI 0.820, 0.839) for the <em>LRA</em>, <em>LRArev</em> and <em>LRAprs</em> scores, respectively. The <em>LRAprs</em> score significantly improved the overall reclassification compared to the <em>LRA</em> (net reclassification index [NRI] = 0.033, 95% CI 0.015, 0.049) and <em>LRArev</em> (NRI = 0.040, 95% CI 0.024, 0.055) <em>scores</em>.</p></div><div><h3>Conclusions</h3><p>Polygenic risk moderately improved the performance of the existing <em>LRA score</em> for 10-year risk prediction of type 2 diabetes.</p></div>","PeriodicalId":48252,"journal":{"name":"Diabetes & Metabolic Syndrome-Clinical Research & Reviews","volume":"18 4","pages":"Article 102996"},"PeriodicalIF":10.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1871402124000572/pdfft?md5=9424f3ac9af33735a2cee24ff4916bd4&pid=1-s2.0-S1871402124000572-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140401081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using nephropathy as an outcome to determine the HbA1c diagnostic threshold for type 2 diabetes","authors":"Alexandra E. Butler ,&nbsp;Steven C. Hunt ,&nbsp;Eric S. Kilpatrick","doi":"10.1016/j.dsx.2024.103005","DOIUrl":"https://doi.org/10.1016/j.dsx.2024.103005","url":null,"abstract":"<div><h3>Objective</h3><p>The hemoglobin A1c (HbA1c) diagnostic threshold for type 2 diabetes (T2D) of 6.5 % (48 mmol/mol) was based on the prevalence of retinopathy found in populations not known to have T2D. It is unclear if nephropathy has a similar HbA1c threshold, partly because it is a rarer complication of early diabetes. This cohort study investigated a very high diabetes prevalence population to determine if a better diagnostic HbA1c value can be established for predicting nephropathy rather than retinopathy in subjects without T2D.</p></div><div><h3>Methods</h3><p>The urine albumin:creatinine ratios (UACRs) of 2920 healthy individuals from the Qatar Biobank who had an HbA1c ≥ 5.6 %. were studied. Nephropathy was defined as a UACR≥30 mg/g and its prediction by HbA1c was assessed using cut-points ranging from 5.7 to 7.0 % to dichotomize high from low HbA1c.</p></div><div><h3>Results</h3><p>Although there was a significant trend for an increased prevalence of abnormal UACR as the HbA1c threshold increased (p &lt; 0.01), significance was due mostly to subjects with HbA1c ≥ 7.0 % (53 mmol/mol). The odds ratios for abnormal UACR were similar over the 5.7–6.9 % HbA1c threshold range, with a narrow odds ratio range of 1.2–1.6. Utilizing area-under-receiver-operating characteristic curves, no HbA1c threshold &lt;7.0 % was identified as the best predictor of nephropathy.</p></div><div><h3>Conclusion</h3><p>Even in a population with a high prevalence of known and unknown diabetes, no HbA1c threshold &lt;7.0 % could be found predicting an increased prevalence of nephropathy. This means there is not a requirement to change the existing retinopathy-based HbA1c threshold of 6.5 % to also accommodate diabetes nephropathy risk.</p></div>","PeriodicalId":48252,"journal":{"name":"Diabetes & Metabolic Syndrome-Clinical Research & Reviews","volume":"18 4","pages":"Article 103005"},"PeriodicalIF":10.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140548083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence facial recognition system for diagnosis of endocrine and metabolic syndromes based on a facial image database","authors":"Danning Wu ,&nbsp;Jiaqi Qiang ,&nbsp;Weixin Hong ,&nbsp;Hanze Du ,&nbsp;Hongbo Yang ,&nbsp;Huijuan Zhu ,&nbsp;Hui Pan ,&nbsp;Zhen Shen ,&nbsp;Shi Chen","doi":"10.1016/j.dsx.2024.103003","DOIUrl":"https://doi.org/10.1016/j.dsx.2024.103003","url":null,"abstract":"<div><h3>Aim</h3><p>To build a facial image database and to explore the diagnostic efficacy and influencing factors of the artificial intelligence-based facial recognition (AI-FR) system for multiple endocrine and metabolic syndromes.</p></div><div><h3>Methods</h3><p>Individuals with multiple endocrine and metabolic syndromes and healthy controls were included from public literature and databases. In this facial image database, facial images and clinical data were collected for each participant and dFRI (disease facial recognition intensity) was calculated to quantify facial complexity of each syndrome. AI-FR diagnosis models were trained for each disease using three algorithms: support vector machine (SVM), principal component analysis k-nearest neighbor (PCA-KNN), and adaptive boosting (AdaBoost). Diagnostic performance was evaluated. Optimal efficacy was achieved as the best index among the three models. Effect factors of AI-FR diagnosis were explored with regression analysis.</p></div><div><h3>Results</h3><p>462 cases of 10 endocrine and metabolic syndromes and 2310 controls were included into the facial image database. The AI-FR diagnostic models showed diagnostic accuracies of 0.827–0.920 with SVM, 0.766–0.890 with PCA-KNN, and 0.818–0.935 with AdaBoost. Higher dFRI was associated with higher optimal area under the curve (AUC) (P = 0.035). No significant correlation was observed between the sample size of the training set and diagnostic performance.</p></div><div><h3>Conclusions</h3><p>A multi-ethnic, multi-regional, and multi-disease facial database for 10 endocrine and metabolic syndromes was built. AI-FR models displayed ideal diagnostic performance. dFRI proved associated with the diagnostic performance, suggesting inherent facial features might contribute to the performance of AI-FR models.</p></div>","PeriodicalId":48252,"journal":{"name":"Diabetes & Metabolic Syndrome-Clinical Research & Reviews","volume":"18 4","pages":"Article 103003"},"PeriodicalIF":10.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140550859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}