Risk prediction platform for pancreatic fistula after pancreatoduodenectomy using artificial intelligence

BACKGROUND Despite advancements in operative technique and improvements in postoperative managements,postoperative pancreatic fistula(POPF) is a life-threatening complication following pancreatoduodenectomy(PD).There are some reports to predict POPF preoperatively or intraoperatively,but the accuracy of those is questionable.Artificial intelligence(AI) technology is being actively used in the medical field,but few studies have reported applying it to outcomes after PD.AIM To develop a risk prediction platform for POPF using an AI model.METHODS Medical records were reviewed from 1769 patients at Samsung Medical Center who underwent PD from 2007 to 2016.A total of 38 variables were inserted into AI-driven algorithms.The algorithms tested to make the risk prediction platform were random forest(RF) and a neural network(NN) with or without recursive feature elimination(RFE).The median imputation method was used for missing values.The area under the curve(AUC) was calculated to examine the discriminative power of algorithm for POPF prediction.RESULTS The number of POPFs was 221(12.5%) according to the International Study Group of Pancreatic Fistula definition 2016.After median imputation,AUCs using 38 variables were 0.68 ± 0.02 with RF and 0.71 ± 0.02 with NN.The maximal AUC using NN with RFE was 0.74.Sixteen risk factors for POPF were identified by AI algorithm:Pancreatic duct diameter,body mass index,preoperative serum albumin,lipase level,amount of intraoperative fluid infusion,age,platelet count,extrapancreatic location of tumor,combined venous resection,co-existing pancreatitis,neoadjuvant radiotherapy,American Society of Anesthesiologists' score,sex,soft texture of the pancreas,underlying heart disease,and preoperative endoscopic biliary decompression.We developed a web-based POPF prediction platform,and this application is freely available at http://popfrisk.smchbp.org.CONCLUSION This study is the first to predict POPF with multiple risk factors using AI.This platform is reliable(AUC 0.74),so it could be used to select patients who need especially intense therapy and to preoperatively establish an effective treatment strategy.     

Nonsurgical and nonprosthetic camouflage treatment of skeletal Class II open bite with bilaterally missing lower first molars

This report illustrates the successful nonsurgical and nonprosthetic camouflage treatment of a skeletal Class II open bite malocclusion combined with missing mandibular first molars bilaterally. In the mandible, the second and third molars were uprighted and protracted, substituting for the missing first molars. In the maxilla, anterior bodily retraction and full-arch intrusion were achieved following premolar and second molar extraction, which also induced autorotation of the mandible. The treatment outcome and prognosis were confirmed with three-dimensional superimposition techniques, along with long-term stability.     

Association Between PAX9 Single-Nucleotide Polymorphisms and Nonsyndromic Cleft Lip With or Without Cleft Palate

ABSTRACT: The purpose of this study was to investigate the contribution of PAX9 gene to the risk of nonsyndromic cleft lip with or without cleft palate (NS-CL/P). The samples consisted of 142 Korean NS-CL/P families (90 males and 52 females; 9 cleft lip, 26 cleft lip and alveolus, and 107 cleft lip and palate; 76 trios and 66 dyads). A total of 10 single-nucleotide polymorphisms (SNPs) were tested for association with Korean CL/P case-parent trios using transmission disequilibrium test (TDT) and conditional logistic regression models. The minor allele frequency, heterozygosity, and a χ test for Hardy-Weinberg equilibrium at each SNP were computed between parents. Pairwise linkage disequilibrium was computed as both D' and r for all SNPs. Both allelic and genotypic TDTs were performed for individual SNPs using family-based association test program. Sliding windows of haplotypes consisting of 2 to 8 SNPs were tested using haplotype-based association test program. Genotypic odd ratios were obtained from conditional logistic regression models using STATA software. The family-based TDT using individual SNPs and 2- to 8-SNP haplotypes of the gene indicated a significant association at rs17104928 (P = 0.014). The haplotype analysis revealed that the association was most significant for the haplotype consisting of 3 SNPs (rs2073247, rs17104928, and rs17176643; P = 0.007). G/A heterozygote at rs17104928 had a significantly increased association with NS-CL/P (genotypic odd ratio, 2.88; 95% confidence interval, 1.42-5.84; P = 0.0014, dominant model). The high-risk SNP and genotype may provide a better understanding of the etiologic role of PAX9 gene in NS-CL/P and potential options for genetic counseling.     

Co-development of autoimmune hepatitis and Sj?gren's syndrome triggered by the administration of herbal medicines

Autoimmune hepatitis (AIH) has been reported in association with Sjögren''s syndrome (SS). Drug-induced AIH has been rarely reported. A rare case of the co-development of AIH and SS in a 53-year-old woman after the consumption of herbal medicines is described. After admission, the patient complained of dryness in her mouth, and she was subsequently diagnosed with SS, which had not been detected previously. The patient''s bilirubin and aminotransferase levels initially decreased following conservative management; however, they later began to progressively increase. A diagnosis of AIH was made based on the scoring system proposed by the International Autoimmune Hepatitis Group. The patient was administered a combination of prednisolone and azathioprine, and the results of follow-up liver-function tests were found to be within the normal range. This is an unusual case of AIH and SS triggered simultaneously by the administration of herbal medicines.