BACKGROUND:In recent years,deep learning technologies have been increasingly applied in the field of oral medicine,enhancing the efficiency and accuracy of oral imaging analysis and promoting the rapid development of intelligent oral medicine. OBJECTIVE:To elaborate the current research status,advantages,and limitations of deep learning based on oral imaging in the diagnosis and treatment decision-making of oral diseases,as well as future prospects,exploring new directions for the transformation of oral medicine under the backdrop of deep learning technology. METHODS:PubMed was searched for literature related to deep learning in oral medical imaging published from January 2017 to January 2024 with the search terms"deep learning,artificial intelligence,stomatology,oral medical imaging."According to the inclusion criteria,80 papers were finally included for review. RESULTS AND CONCLUSION:(1)Classic deep learning models include artificial neural networks,convolutional neural networks,recurrent neural networks,and generative adversarial networks.Scholars have used these models in competitive or cooperative forms to achieve more efficient interpretation of oral medical images.(2)In the field of oral medicine,the diagnosis of diseases and the formulation of treatment plans largely depend on the interpretation of medical imaging data.Deep learning technology,with its strong image processing capabilities,aids in the diagnosis of diseases such as dental caries,periapical periodontitis,vertical root fractures,periodontal disease,and jaw cysts,as well as preoperative assessments for procedures such as third molar extraction and cervical lymph node dissection,helping clinicians improve the accuracy and efficiency of decision-making.(3)Although deep learning is promising as an important auxiliary tool for the diagnosis and treatment of oral diseases,it still has certain limitations in model technology,safety ethics,and legal regulation.Future research should focus on demonstrating the scalability,robustness,and clinical practicality of deep learning,and finding the best way to integrate automated deep learning decision support systems into routine clinical workflows.

BACKGROUND: The available evidence regarding the benefits of percutaneous coronary intervention (PCI) on patients receiving dialysis with coronary artery disease (CAD) is limited and inconsistent. This study aimed to evaluate the association between PCI and clinical outcomes as compared with medical therapy alone in patients undergoing dialysis with CAD in China. METHODS: This multicenter, retrospective study was conducted in 30 tertiary medical centers across 12 provinces in China from January 2015 to June 2021 to include patients on dialysis with CAD. The primary outcome was major adverse cardiovascular events (MACE), defined as a composite of cardiovascular death, non-fatal myocardial infarction, and non-fatal stroke. Secondary outcomes included all-cause death, the individual components of MACE, and Bleeding Academic Research Consortium criteria types 2, 3, or 5 bleeding. Multivariable Cox proportional hazard models were used to assess the association between PCI and outcomes. Inverse probability of treatment weighting (IPTW) and propensity score matching (PSM) were performed to account for potential between-group differences. RESULTS: Of the 1146 patients on dialysis with significant CAD, 821 (71.6%) underwent PCI. After a median follow-up of 23.0 months, PCI was associated with a 43.0% significantly lower risk for MACE (33.9% [ n  = 278] vs . 43.7% [ n  = 142]; adjusted hazards ratio 0.57, 95% confidence interval 0.45-0.71), along with a slightly increased risk for bleeding outcomes that did not reach statistical significance (11.1% vs . 8.3%; adjusted hazards ratio 1.31, 95% confidence interval, 0.82-2.11). Furthermore, PCI was associated with a significant reduction in all-cause and cardiovascular mortalities. Subgroup analysis did not modify the association of PCI with patient outcomes. These primary findings were consistent across IPTW, PSM, and competing risk analyses. CONCLUSION This study indicated that PCI in patients on dialysis with CAD was significantly associated with lower MACE and mortality when comparing with those with medical therapy alone, albeit with a slightly increased risk for bleeding events that did not reach statistical significance.
Humans ; Percutaneous Coronary Intervention/methods* ; Male ; Female ; Coronary Artery Disease/drug therapy* ; Retrospective Studies ; Renal Dialysis/methods* ; Middle Aged ; Aged ; China ; Proportional Hazards Models ; Treatment Outcome

Objective:To explore the clinical, biochemical and genetic characteristics of three children with Isoleucine metabolic disorders due to variants of HSD17B10 and ACAT1 genes. Methods:Two children with 17β hydroxysteroid dehydrogenase 10 (HSD17B10) deficiency and a child with β-ketothiolase deficiency (BKD) diagnosed at Shanghai Children′s Hospital between 2014 and 2021 were selected as the study subjects. Clinical data of the children were collected. The children were subjected to blood acylcarnitine, urinary organic acid and genetic testing, and candidate variants were analyzed with bioinformatic tools.Results:The main symptoms of the three children had included epilepsy, developmental delay, hypotonia and acidosis. Their blood acylcarnitine methylcrotonyl carnitine (C5: 1), 3-hydroxyisovalerylcarnitine (C5-OH) and 3-hydroxybutylcarnitine (C4OH) were increased to various extents, and urine organic acids including methyl crotonylglycine and 2-methyl-3-hydroxybutyric acid were significantly increased. Child 1 and child 2 were respectively found to harbor a c. 347G>A (p.R116Q) variant and a c. 274G>A (p.A92T) variant of the HSD17B10 gene, and child 3 was found to harbor compound heterozygous variants of the ACAT1 gene, namely c. 547G>A (p.G183R) and a c. 331G>C (p.A111P). Among these, the c. 274G>A (p.A92T) and c. 331G>C (p.A111P) variants were unreported previously. Based on the guidelines from the American College of Medical Genetics and Genomics (ACMG), they were respectively classified as variant of unknown significance (PP3_Strong+ PM2_supporting) and likely pathogenic (PM3+ PM2_Supporting+ PP3_Moderate+ PP4). Conclusion:Both the HSD17B10 deficiency and BKD can lead to Isoleucine metabolism disorders, which may be difficult to distinguish clinically. Genetic testing can further confirm the diagnosis. Discoveries of the HSD17B10: c. 274G>A (p.A92T) variant and the ACAT1: c. 331G>C (p.A111P) variant have enriched the mutational spectrum of the two diseases.

Objective:To explore the genetic etiology and clinical phenotype of a child with Triadin knockout syndrome (TKOS), and to review the relevant literature of TKOS patients due to variants of TRDN gene. Methods:A child who was admitted to the Children′s Hospital of Xi′an Jiaotong University on March 19, 2023 due to sudden cardiac arrest 3 days earlier was selected as the study subject. Peripheral blood samples (2 to 3 mL) were collected from the child and her parents for the extraction of genomic DNA and whole exome sequencing (WES). Pathogenic variants were searched from databases such as the Genome Aggregation Database (gnomAD) and Online Mendelian Inheritance in Man (OMIM), and were assessed based on the guidelines from the American College of Medical Genetics and Genomics (ACMG). Sanger sequencing was carried out for family validation of the pathogenic variants. Using keywords such as " arrhythmias" " TRDN" and " Triadin" both in Chinese and English, relevant literature on TKOS patients due to variants of the TRDN gene was retrieved from the CNKI, Wanfang Data Knowledge Service Platform, and PubMed databases, and the time of literature retrieval was set from January 1, 2012 to December 1, 2023. This study has been approved by the Ethics Committee of the Affiliated Children′s Hospital of Xi′an Jiaotong University (No. 20230097), and informed consent was obtained from the parents of the child. Results:The child had experienced syncope and cardiac arrest after exercise. Electrocardiographic examination revealed QTc interval prolongation, T-wave inversion in precordial leads V1-V3, polymorphic ventricular premature beat (VPB), and ventricular tachycardia (VT) along with increased heart rate. WES and Sanger sequencing revealed that the child has harbored a homozygous c.463del(p.E155Kfs*20) variant of the TRDN gene, for which both of the parents were heterozygous. Based on the guidelines from the ACMG, the variant was classified as pathogenic (PVS1+ PM2+ PM3). The child was ultimately diagnosed with TKOS. In total 12 publications on TOKS cases caused by TRDN gene variants were retrieved, which involved 30 patients and 28 carriers of single heterozygous variant of the TRDN gene. Among the 30 TKOS patients, 20 had carried homozygous variants of the TRDN gene, and 10 had carried compound heterozygous variants, and all had exhibited significant clinical phenotype of arrhythmia, with most cases had experienced malignant arrhythmia induced by exercise and/or excitement during infancy or early childhood, leading to recurrent syncope and cardiac arrest. Of note, none of the 28 carriers of single heterozygous variant had abnormal clinical phenotype. Conclusion:The homozygous c.463del(p.E155Kfs20) variant of the TRDN gene probably underlay the pathogenesis of cardiac arrest in this child. Above discovery has enriched the mutational spectrum of the TRDN gene.This mutation may represent a genetic cause for cardiac arrest in children with TKOS.

Objective To detect the expression level of 4-aminobutyrate aminotransferase(ABAT)in bone marrow of patients with myelodysplastic syndrome(MDS),and analyze its influence on clinicopathological features and prognosis of patients.Methods From January 2016 to March 2020,92 patients with MDS and 30 patients with acute myeloid leukemia(AML)from the First Affiliated Hospital of Xingtai Medical College were retrospectively collected.Meanwhile,30 patients with immunothrombocytopenia who did not develop MDS or other clonal diseases of the blood system during a 3-year follow-up were collected as control group.Real-time quantitative fluorescent PCR(qRT-PCR)was used to detect the relative expression level and methylation level of ABAT mRNA of all patients,and the relative expression level and methylation level of ABAT mRNA among different clinical characteristics of MDS patients were compared.Multivariate logistic regression analysis was used to analyze the risk factors affecting the adverse prognosis of MDS.The clinical value of detecting ABAT methylation level in predicting poor prognosis of MDS patients was analyzed by receiver operating characteristic(ROC)curve.Kaplan-Meier method was used to calculate the 3-year survival rate between groups with different ABAT mRNA relative expression levels and methylation levels,and log-rank test was used for their comparison.Results The expression level of ABAT mRNA in MDS group(0.42±0.08)was lower than that in control group(0.56±0.15)and AML group(0.52±0.10),while the methylation level of ABAT(32.51±5.32)was higher than that of AML group(26.21±4.58)and control group(10.25±4.31),and the differences were significant(t=4.251,4.562;10.415,8.326,all P<0.001).The methylation level of ABAT in high-risk patients(42.65±5.32)was higher than that in low-risk patients(25.63±4.16),intermediate-risk-1 patients(30.59±2.51)and intermediate-risk-2 patients(33.25±3.69)by IPSS risk grade,and the differences were significant(t=8.329,7.077,15.874,all P<0.001).Poor Karyotype analysis result[OR(95%CI):4.973(1.524～8.581),P=0.004],high IPSS risk grade[OR(95%CI):8.542(2.365～14.521),P<0.001]and ABAT hypermethylation level[OR(95%CI):6.178(1.589～13.021),P<0.001]were the risk factors affecting the poor prognosis of MDS.The cut-offvalue of ABAT methylation level to predict the poor prognosis of MDS were 30.54,and the area under the curve(AUC),the sensitivity and specificity were 0.92,0.874 and 0.851,respectively.The 3-year survival rate of the high ABAT methylation group(>30.54)was 66.67%,which was lower than that of the low ABAT methylation group(≤30.54)was 93.18%,with significant difference(Log-rank x2=9.814,P=0.002).Conclusion The ABAT methylation levels in MDS bone marrow increase,which is a risk factor affecting the poor prognosis of patients.ABAT basal level>30.54 is expected to become a factors predicting the poor prognosis of patients.

Background::The conversion of adenosine (A) to inosine (I) through deamination is the prevailing form of RNA editing, impacting numerous nuclear and cytoplasmic transcripts across various eukaryotic species. Millions of high-confidence RNA editing sites have been identified and integrated into various RNA databases, providing a convenient platform for the rapid identification of key drivers of cancer and potential therapeutic targets. However, the available database for integration of RNA editing in hematopoietic cells and hematopoietic malignancies is still lacking.Methods::We downloaded RNA sequencing (RNA-seq) data of 29 leukemia patients and 19 healthy donors from National Center for Biotechnology Information (NCBI) Gene Expression Omnibus (GEO) database, and RNA-seq data of 12 mouse hematopoietic cell populations obtained from our previous research were also used. We performed sequence alignment, identified RNA editing sites, and obtained characteristic editing sites related to normal hematopoietic development and abnormal editing sites associated with hematologic diseases.Results::We established a new database, "REDH", represents RNA editome in hematopoietic differentiation and malignancy. REDH is a curated database of associations between RNA editome and hematopoiesis. REDH integrates 30,796 editing sites from 12 murine adult hematopoietic cell populations and systematically characterizes more than 400,000 edited events in malignant hematopoietic samples from 48 cohorts (human). Through the Differentiation, Disease, Enrichment, and knowledge modules, each A-to-I editing site is systematically integrated, including its distribution throughout the genome, its clinical information (human sample), and functional editing sites under physiological and pathological conditions. Furthermore, REDH compares the similarities and differences of editing sites between different hematologic malignancies and healthy control.Conclusions::REDH is accessible at http://www.redhdatabase.com/. This user-friendly database would aid in understanding the mechanisms of RNA editing in hematopoietic differentiation and malignancies. It provides a set of data related to the maintenance of hematopoietic homeostasis and identifying potential therapeutic targets in malignancies.

Objective:To evaluate the efficacy and prognostic factors of allogeneic hematopoietic stem cell transplantation (allo-HSCT) in patients with secondary acute myeloid leukemia (sAML) .Methods:In this multicenter, retrospective clinical study, adult patients aged ≥18 years who underwent allo-HSCT for sAML at four centers of the Zhejiang Hematopoietic Stem Cell Transplantation Collaborative Group from January 2014 to November 2022 were included, and the efficacy and prognostic factors of allo-HSCT were analyzed.Results:A total of 95 patients were enrolled; 66 (69.5%) had myelodysplastic syndrome-acute myeloid leukemia (MDS-AML) , 4 (4.2%) had MDS/MPN-AML, and 25 (26.3%) had therapy-related AML (tAML) . The 3-year CIR, LFS, and overall survival (OS) rates were 18.6% (95% CI 10.2%-27.0%) , 70.6% (95% CI 60.8%-80.4%) , and 73.3% (95% CI 63.9%-82.7%) , respectively. The 3-year CIRs of the M-AML group (including MDS-AML and MDS/MPN-AML) and the tAML group were 20.0% and 16.4%, respectively ( P=0.430) . The 3-year LFSs were 68.3% and 75.4%, respectively ( P=0.176) . The 3-year OS rates were 69.7% and 75.4%, respectively ( P=0.233) . The 3-year CIRs of the groups with and without TP53 mutations were 60.0% and 13.7%, respectively ( P=0.003) ; the 3-year LFSs were 20.0% and 76.5%, respectively ( P=0.002) ; and the 3-year OS rates were 40.0% and 77.6%, respectively ( P=0.002) . According to European LeukmiaNet 2022 (ELN2022) risk stratification, the 3-year CIRs of patients in the low-, intermediate-, and high-risk groups were 8.3%, 17.8%, and 22.6%, respectively ( P=0.639) . The three-year LFSs were 91.7%, 69.5%, and 65.6%, respectively ( P=0.268) . The 3-year OS rates were 91.7%, 71.4%, and 70.1%, respectively ( P=0.314) . Multivariate analysis revealed that advanced disease at allo-HSCT and TP53 mutations were independent risk factors for CIR, LFS, and OS. Conclusion:There was no significant difference in the prognosis of patients who underwent allo-HSCT among the MDS-AML, MDS/MPN-AML, and tAML groups. Advanced disease at transplantation and TP53 mutations were poor prognostic factors. ELN2022 risk stratification had limited value for predicting the prognosis of patients with sAML following allo-HSCT.

The standardized workflow of computer-aided static guided implant surgery includes preoperative exami-nation,data acquisition,guide design,guide fabrication and surgery.Errors may occur at each step,leading to irrevers-ible cumulative effects and thus impacting the accuracy of implant placement.However,clinicians tend to focus on fac-tors causing errors in surgical operations,ignoring the possibility of irreversible errors in nonstandard guided surgery.Based on the clinical practice of domestic experts and research progress at home and abroad,this paper summarizes the sources of errors in guided implant surgery from the perspectives of preoperative inspection,data collection,guide de-signing and manufacturing and describes strategies to resolve errors so as to gain expert consensus.Consensus recom-mendation:1.Preoperative considerations:the appropriate implant guide type should be selected according to the pa-tient's oral condition before surgery,and a retaining screw-assisted support guide should be selected if necessary.2.Da-ta acquisition should be standardized as much as possible,including beam CT and extraoral scanning.CBCT performed with the patient's head fixed and with a small field of view is recommended.For patients with metal prostheses inside the mouth,a registration marker guide should be used,and the ambient temperature and light of the external oral scan-ner should be reasonably controlled.3.Optimization of computer-aided design:it is recommended to select a handle-guided planting system and a closed metal sleeve and to register images by overlapping markers.Properly designing the retaining screws,extending the support structure of the guide plate and increasing the length of the guide section are methods to feasibly reduce the incidence of surgical errors.4.Improving computer-aided production:it is also crucial to set the best printing parameters according to different printing technologies and to choose the most appropriate postpro-cessing procedures.

Introduction::Observational studies have revealed an association between waist circumference (WC) and atrial fibrillation (AF). However, it is difficult to infer a causal relationship from observational studies because the observed associations could be confounded by unknown risk factors. Therefore, the causal role of WC in AF is unclear. This study was designed to investigate the causal association between WC and AF using a two-sample Mendelian randomization (MR) analysis.Methods::In our two-sample MR analysis, the genetic variation used as an instrumental variable for MR was acquired from a genome-wide association study (GWAS) of WC (42 single nucleotide polymorphisms with a genetic significance of P <5 × 10 –8). The data of WC (from the Genetic Investigation of ANthropometric Traits consortium, containing 232,101 participants) and the data of AF (from the European Bioinformatics Institute database, containing 55,114 AF cases and 482,295 controls) were used to assess the causal role of WC on AF. Three different approaches (inverse variance weighted [IVW], MR–Egger, and weighted median regression) were used to ensure that our results more reliable. Results::All three MR analyses provided evidence of a positive causal association between high WC and AF. High WC was suggested to increase the risk of AF based on the IVW method (odds ratio [OR] = 1.43, 95% confidence interval [CI], 1.30–1.58, P = 2.51 × 10 -13). The results of MR–Egger and weighted median regression exhibited similar trends (MR–Egger OR = 1.40 [95% CI, 1.08–1.81], P = 1.61 × 10 -2; weighted median OR = 1.39 [95% CI, 1.21–1.61], P = 1.62 × 10 -6). MR–Egger intercepts and funnel plots showed no directional pleiotropic effects between high WC and AF. Conclusions::Our findings suggest that greater WC is associated with an increased risk of AF. Taking measures to reduce WC may help prevent the occurrence of AF.

Objective To analyze the clinical outcomes of early invasive fungal disease(IFD)in patients after allogenetic hematopoietic stem cell transplantation(allo-HCST)with metagenomic next-generation sequencing(mNGS).Methods A retrospective analysis was conducted on patients undergoing allo-HCST in our Bone Marrow Transplantation Center between July 2021 and October 2022.These patients experienced one of the following conditions within 100 d after transplantation:① Patients with persistent fever and negative blood culture after empiric antimicrobial therapy for 72 h or longer;② Hyperpyrexia of unknown origin occurred again after effective anti-infection in the past;③ Symptoms in lower respiratory tract associated with lung lesions on CT scan,and empiric anti-infective therapy was ineffective.Peripheral blood or bronchoscopic alveolar lavage fluid were tested with mNGS,and overall survival(OS)and non-relapse mortality(NRM)were analyzed.Results There were 60 patients enrolled in this study.For the peripheral blood samples of 47 cases and bronchoalveolar lavage fluid samples of 13 cases,mNGS found that 19 cases were negative to pathogens,30 cases were non-fungal positive,and 11 case were fungal positive,including 3 cases of aspergillus,5 cases of mucor,2 cases of Candida tropicalis,and 1 case of Trichosporon asahii.Of the 11 patients with fungal positive,8 achieved complete remission after antifungal therapy according to the mNGS results.The 1-year OS and NRM of the 60 patients were 70.0％(95％CI:64.1％～75.9％)and 20.0％(95％CI:11.9％～32.5％),respectively,while those of the fungal infection patients were 54.5％(95％CI:49.5％～69.5％)and 36.4％(95％ CI:15.5％～70.3％),respectively.No significant differences were seen in 1-year OS(P=0.487)and 1-year NRM(P=0.358)among the negative,fungal infection and non-fungal infection patients,neither OS(P=0.238)and NRM(P=0.154)between the fungal infection and the non-fungal infection patients.Conclusion mNGS can rapidly diagnose the early IFD after allo-HSCT,which is helpful for timely and effective treatment and improves the prognosis of patients.