Artificial intelligence facial recognition system for diagnosis of endocrine and metabolic syndromes based on a facial image database.

AIM: 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. METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.

Clopidogrel as a Distinctive Cause of Insulin Autoimmune Syndrome: A Systematic Case Review.

The sulfhydryl group of clopidogrel metabolite could induce insulin autoimmune syndrome (IAS) with hypoglycemia as the major symptom. For patients with cardiovascular disease taking clopidogrel for vascular protection, this adverse event hypoglycemia increases the risk of cardiovascular events. However, discontinuing clopidogrel leaves patients without appropriate antiplatelet therapy. Treating IAS with glucocorticoids is also risky for these patients' primary cardiovascular diseases. Early recognition and appropriate treatment of clopidogrel-induced IAS (CIAS) would be beneficial for patients. This research aimed to discover the clinical features and investigate optimal therapeutic management of CIAS. We systematically searched for cases of CIAS in PubMed and Embase and performed data mining in Food and Drug Administration Adverse Event Reporting System (FAERS). In the CIAS series, clinical features were summarized and compared to 287 IAS cases, including demographic information, HLA alleles, onset, and symptoms. The therapeutic effect of glucocorticoids was compared between the receiving group and the not-receiving group. The possibilities of common antiplatelet drugs to induce hypoglycemia/IAS were investigated with chemical structure and FAERS reports. A CIAS series of 51 patients was established. CIAS had an onset age of 74.8±8.6 years old, 92.2% male, and a balanced proportion of East Asians and non-East Asians. Confusion occurred more frequently in CIAS than in IAS from various causes, while the other symptoms and hypoglycemia types were similar. The recovery time was approximately the same whether using glucocorticoids/immunotherapy in CIAS or not. Among common antiplatelet drugs, ticagrelor and rivaroxaban were unlikely to induce hypoglycemia/IAS. Clopidogrel is a distinctive cause of IAS featuring an elderly male presenting confusion as the symptom of hypoglycemia. Glucocorticoids/immunotherapy might not be necessary for the long-term recovery of CIAS. To balance the risks of hypoglycemia and cardiovascular events, substituting clopidogrel with ticagrelor and rivaroxaban might be considered.

Hypoglycemia as a potential risk for patients taking clopidogrel: A systematic review and meta-analysis.

Background: Clopidogrel is a cornerstone antiplatelet drug used in cardiovascular, cerebrovascular, and peripheral artery diseases. The sulfhydryl group of clopidogrel metabolite could induce insulin autoimmune syndrome (IAS) with hypoglycemia as the major symptom. Discontinuing clopidogrel and substituting it with ticagrelor has been revealed as an effective treatment in previous studies. Since hypoglycemia serves as a risk factor for cardiovascular and cerebrovascular events, we aimed to determine the association between hypoglycemia/IAS and clopidogrel and to investigate whether clopidogrel is a modifiable and causal risk factor of hypoglycemia/IAS. Methods: MEDLINE, Embase, Cochrane databases, and clinical trial registries were searched for randomized controlled trials (RCTs) of clopidogrel from inception to 28 February 2022. RCTs comparing clopidogrel with placebo or other antiplatelet drugs were eligible if meeting the inclusion criteria: 1) clopidogrel was administrated 75 mg qd orally as a long-term antiplatelet prescription at least for months, and 2) hypoglycemia-inducible drugs were not used in the control arm. One investigator abstracted articles and performed a quality assessment. Uncertainties were resolved by discussions with two investigators independently. Odds ratio (OR) and risk difference (RD) were calculated and performed with subgroup analyses. The pre-specified protocol was registered in PROSPERO (CRD42022299622). Results: Six trials with 61,399 participants in total fulfilled the criteria and were included in the meta-analysis. Clopidogrel might not be associated with higher hypoglycemia odds (OR 0.95, 95% CI 0.65 to 1.40). However, Asian participants (p = 0.0437) seemed more likely to develop clopidogrel-associated hypoglycemia. Clopidogrel-associated hypoglycemia occurred at the highest rate of 0.03% (RD -0.00023, 95% CI -0.00077 to 0.00031), and this increased to 0.91% (RD 0.00210, 95% CI -0.00494 to 0.00914) in an aging population and to 0.18% (RD 0.00040, 95% CI -0.00096 to 0.00177) when Asian ratio of the population was elevated. Conclusions: We raise the concern that clopidogrel might be a modifiable and causal risk factor of hypoglycemia. The Asian population might be more vulnerable and need additional care. Systematic review registration: https://www.crd.york.ac.uk/prospero, identifier CRD42022299622.

Review on Facial-Recognition-Based Applications in Disease Diagnosis.

Diseases not only manifest as internal structural and functional abnormalities, but also have facial characteristics and appearance deformities. Specific facial phenotypes are potential diagnostic markers, especially for endocrine and metabolic syndromes, genetic disorders, facial neuromuscular diseases, etc. The technology of facial recognition (FR) has been developed for more than a half century, but research in automated identification applied in clinical medicine has exploded only in the last decade. Artificial-intelligence-based FR has been found to have superior performance in diagnosis of diseases. This interdisciplinary field is promising for the optimization of the screening and diagnosis process and assisting in clinical evaluation and decision-making. However, only a few instances have been translated to practical use, and there is need of an overview for integration and future perspectives. This review mainly focuses on the leading edge of technology and applications in varieties of disease, and discusses implications for further exploration.

YTHDF1 Promotes Gastric Carcinogenesis by Controlling Translation of FZD7.

N6-methyladenosine (m6A) is the most prevalent internal RNA modification in mammals that regulates homeostasis and function of modified RNA transcripts. Here, we aimed to investigate the role of YTH m6A RNA-binding protein 1 (YTHDF1), a key regulator of m6A methylation in gastric cancer tumorigenesis. Multiple bioinformatic analyses of different human cancer databases identified key m6A-associated genetic mutations that regulated gastric tumorigenesis. YTHDF1 was mutated in about 7% of patients with gastric cancer, and high expression of YTHDF1 was associated with more aggressive tumor progression and poor overall survival. Inhibition of YTHDF1 attenuated gastric cancer cell proliferation and tumorigenesis in vitro and in vivo. Mechanistically, YTHDF1 promoted the translation of a key Wnt receptor frizzled7 (FZD7) in an m6A-dependent manner, and mutated YTHDF1 enhanced expression of FZD7, leading to hyperactivation of the Wnt/ß-catenin pathway and promotion of gastric carcinogenesis. Our results demonstrate the oncogenic role of YTHDF1 and its m6A-mediated regulation of Wnt/ß-catenin signaling in gastric cancer, providing a novel approach of targeting such epigenetic regulators in this disease. SIGNIFICANCE: This study provides a rationale for controlling translation of key oncogenic drivers in cancer by manipulating epigenetic regulators, representing a novel and efficient strategy for anticancer treatment. GRAPHICAL ABSTRACT: http://cancerres.aacrjournals.org/content/canres/81/10/2651/F1.large.jpg.

α1,6-Fucosyltransferase (FUT8) regulates the cancer-promoting capacity of cancer-associated fibroblasts (CAFs) by modifying EGFR core fucosylation (CF) in non-small cell lung cancer (NSCLC).

Cancer-associated fibroblasts (CAFs) are the main cancer-promoting component in the tumor microenvironment (TME) of non-small cell lung cancer (NSCLC). α1,6-Fucosyltransferase (FUT8), the key enzyme catalyzing core α1,6-fucosylation (CF), plays a promoting role in multiple malignancies. In the current study, we investigated the function of FUT8 in CAFs and elucidated the mechanism through which FUT8 regulates the cancer-promoting capacity of CAFs in NSCLC. A bioinformatics analysis was performed to reveal the relationship between FUT8 and CAFs. Resected specimens from NSCLC patients were analyzed to assess the expression of FUT8 in CAFs. Primary CAFs and normal lung fibroblasts (NLFs) were extracted from NSCLC patient specimens and were co-cultured with NSCLC cell lines in a novel 3D-printed non-contact co-culture device. An In vivo CAF/NSCLC co-injection tumorigenesis assay was performed using nude mice to study the function of FUT8/CF in TME formation. The current study revealed that FUT8-mediated CF in CAFs plays a positive role in the cancer-promoting capacity of these cells. FUT8 overexpression was observed in CAFs isolated from some lung adenocarcinoma cases. Further investigation showed that FUT8/CF in CAFs promoted the formation of an invasive and malignant TME in vivo and in vitro, and the resulting NSCLC cells exhibited faster proliferation and increased invasiveness. EGFR signaling exerts a catalytic effect on the cancer-promoting capacity of CAFs and is regulated by the CF modification of the EGFR protein.