Development of a prognostic prediction support system for cervical intraepithelial neoplasia using artificial intelligence-based diagnosis.

OBJECTIVE: Human papillomavirus subtypes are predictive indicators of cervical intraepithelial neoplasia (CIN) progression. While colposcopy is also an essential part of cervical cancer prevention, its accuracy and reproducibility are limited because of subjective evaluation. This study aimed to develop an artificial intelligence (AI) algorithm that can accurately detect the optimal lesion associated with prognosis using colposcopic images of CIN2 patients by utilizing objective AI diagnosis. METHODS: We identified colposcopic findings associated with the prognosis of patients with CIN2. We developed a convolutional neural network that can automatically detect the rate of high-grade lesions in the uterovaginal area in 12 segments. We finally evaluated the detection accuracy of our AI algorithm compared with the scores by multiple gynecologic oncologists. RESULTS: High-grade lesion occupancy in the uterovaginal area detected by senior colposcopists was significantly correlated with the prognosis of patients with CIN2. The detection rate for high-grade lesions in 12 segments of the uterovaginal area by the AI system was 62.1% for recall, and the overall correct response rate was 89.7%. Moreover, the percentage of high-grade lesions detected by the AI system was significantly correlated with the rate detected by multiple gynecologic senior oncologists (r=0.61). CONCLUSION: Our novel AI algorithm can accurately determine high-grade lesions associated with prognosis on colposcopic images, and these results provide an insight into the additional utility of colposcopy for the management of patients with CIN2.

Clustering by phenotype and genome-wide association study in autism.

Autism spectrum disorder (ASD) has phenotypically and genetically heterogeneous characteristics. A simulation study demonstrated that attempts to categorize patients with a complex disease into more homogeneous subgroups could have more power to elucidate hidden heritability. We conducted cluster analyses using the k-means algorithm with a cluster number of 15 based on phenotypic variables from the Simons Simplex Collection (SSC). As a preliminary study, we conducted a conventional genome-wide association study (GWAS) with a data set of 597 ASD cases and 370 controls. In the second step, we divided cases based on the clustering results and conducted GWAS in each of the subgroups vs controls (cluster-based GWAS). We also conducted cluster-based GWAS on another SSC data set of 712 probands and 354 controls in the replication stage. In the preliminary study, which was conducted in conventional GWAS design, we observed no significant associations. In the second step of cluster-based GWASs, we identified 65 chromosomal loci, which included 30 intragenic loci located in 21 genes and 35 intergenic loci that satisfied the threshold of P < 5.0 × 10-8. Some of these loci were located within or near previously reported candidate genes for ASD: CDH5, CNTN5, CNTNAP5, DNAH17, DPP10, DSCAM, FOXK1, GABBR2, GRIN2A5, ITPR1, NTM, SDK1, SNCA, and SRRM4. Of these 65 significant chromosomal loci, rs11064685 located within the SRRM4 gene had a significantly different distribution in the cases vs controls in the replication cohort. These findings suggest that clustering may successfully identify subgroups with relatively homogeneous disease etiologies. Further cluster validation and replication studies are warranted in larger cohorts.

Outlier detection for questionnaire data in biobanks.

BACKGROUND: Biobanks increasingly collect, process and store omics with more conventional epidemiologic information necessitating considerable effort in data cleaning. An efficient outlier detection method that reduces manual labour is highly desirable. METHOD: We develop an unsupervised machine-learning method for outlier detection, namely kurPCA, that uses principal component analysis combined with kurtosis to ascertain the existence of outliers. In addition, we propose a novel regression adjustment approach to improve detection, namely the regression adjustment for data by systematic missing patterns (RAMP). RESULT: Application to epidemiological record data in a large-scale biobank (Tohoku Medical Megabank Organization, Japan) shows that a combination of kurPCA and RAMP effectively detects known errors or inconsistent patterns. CONCLUSIONS: We confirm through the results of the simulation and the application that our methods showed good performance. The proposed methods are useful for many practical analysis scenarios.

Children's Eating Attitudes Test: Reliability and validation in Japanese adolescents.

Eating disorders (ED) are serious psychosomatic disorders that commonly occur in girls during adolescence. An increase in earlier onset ED has recently been suggested. Therefore, accurate assessment of eating attitudes in children is a necessary part of school mental health. The 26-item Children's Eating Attitudes Test (ChEAT-26) is widely used internationally to assess abnormal eating attitudes. The present study aimed to validate the Japanese version of the ChEAT-26. Participants were 7076 school children (aged 10-15years) from large, medium-sized, and small cities, and 44 children with anorexia nervosa. We examined the average ChEAT-26 score by participant attributes, including sex, age, geographical region, and school style. Factor analysis of the ChEAT-26 content was performed with varimax rotation. The optimal cut-off point was evaluated using receiver operating characteristic (ROC) analysis. The mean ChEAT-26 score was 7.94 for girls and 5.86 for boys. The mean score was significantly higher in children from larger cities than small cities, and was higher with increasing age, and private schools. Five factors explained 31.4% of the variance. The Cronbach's alpha was 0.81 for the scale. The area under the ROC curve was 0.83; sensitivity was 0.69 and specificity was 0.93 for a cut-off score of 18. The Japanese version of the ChEAT-26 is a reliable and valid psychometric tool that may be useful in the triage and assessment of children with anorexia nervosa.

Altered SPECT (123)I-iomazenil Binding in the Cingulate Cortex of Children with Anorexia Nervosa.

Several lines of evidence suggest that anxiety plays a key role in the development and maintenance of anorexia nervosa (AN) in children. The purpose of this study was to examine cortical GABA(A)-benzodiazepine receptor binding before and after treatment in children beginning intensive AN treatment. Brain single-photon emission computed tomography (SPECT) measurements using (123)I-iomazenil, which binds to GABA(A)-benzodiazepine receptors, was performed in 26 participants with AN who were enrolled in a multimodal treatment program. Sixteen of the 26 participants underwent a repeat SPECT scan immediately before discharge at conclusion of the intensive treatment program. Eating behavior and mood disturbances were assessed using Eating Attitudes Test with 26 items (EAT-26) and the short form of the Profile of Mood States (POMS). Clinical outcome scores were evaluated after a 1-year period. We examined association between relative iomazenil-binding activity in cortical regions of interest and psychometric profiles and determined which psychometric profiles show interaction effects with brain regions. Further, we determined if binding activity could predict clinical outcome and treatment changes. Higher EAT-26 scores were significantly associated with lower iomazenil-binding activity in the anterior and posterior cingulate cortex. Higher POMS subscale scores were significantly associated with lower iomazenil-binding activity in the left frontal, parietal cortex, and posterior cingulate cortex (PCC). "Depression-Dejection" and "Confusion" POMS subscale scores, and total POMS score showed interaction effects with brain regions in iomazenil-binding activity. Decreased binding in the anterior cingulate cortex and left parietal cortex was associated with poor clinical outcomes. Relative binding increases throughout the PCC and occipital gyrus were observed after weight gain in children with AN. These findings suggest that cortical GABAergic receptor binding is altered in children with AN. This may be a state-related change, which could be used to monitor and guide the treatment of eating disorders.