ota atsuhiko

Background and Objective: Excellent generalizability is the precondition for the widespread practical implementation of machine learning models. In our previous study, we developed the schizophrenia classification model (SZ classifier) to identify potential schizophrenia patients in the Japanese population. The SZ classifier has exhibited impressive performance during internal validation. However, ensuring the robustness and generalizability of the SZ classifier requires external validation across independent sample sets. In this study, we aimed to present an external validation of the SZ classifier using outpatient data. Methods: The SZ classifier was trained by using online survey data, which incorporate demographic, health-related, and social comorbidity features. External validation was conducted using an outpatient sample set which is independent from the sample set during the model development phase. The model performance was assessed based on the sensitivity and misclassification rates for schizophrenia, bipolar disorder, and major depression patients. Results: The SZ classifier demonstrated a sensitivity of 0.75 when applied to schizophrenia patients. The misclassification rates were 59% and 55% for bipolar disorder and major depression patients, respectively. Conclusions: The SZ classifier currently encounters challenges in accurately determining the presence or absence of schizophrenia at the individual level. Prior to widespread practical implementation, enhancements are necessary to bolster the accuracy and diminish the misclassification rates. Despite the current limitations of the model, such as poor specificity for certain psychiatric disorders, there is potential for improvement if including multiple types of psychiatric disorders during model development.

Nursery school workers are known for having a high prevalence of low back pain (LBP). The natural history of LBP and the determinants of persistent LBP remain unclear. We examined the prevalence of persistent LBP and whether pain intensity and disability in daily life due to LBP affected the persistence of LBP among these workers. A five-year panel study was conducted for 446 nursery school workers in Japan. LBP, pain intensity, and disability in daily life due to LBP were assessed with a self-administered questionnaire survey. Pain intensity was assessed using the numerical rating scale (NRS). The Roland–Morris Disability Questionnaire (RDQ) was used to assess disability in daily life due to LBP. At baseline, 270 nursery school workers (60.5%) suffered from LBP. The estimated prevalence of persistent LBP was 84.6% (80.3–88.9%), 82.2% (77.7–86.8%), and 82.0% (77.4–86.5%) at 1, 3, and 5 years after the initial study, respectively. NRS scores of 5 or greater predicted the persistence of LBP at 1 and 3 years after the initial survey (adjusted odds ratios: 4.01 (1.27–12.6) and 8.51 (1.87–38.7), respectively), while RDQ scores did not. In conclusion, LBP highly persisted for a long time and pain intensity predicted persistent LBP among nursery school workers in Japan.

Abstract Objectives This study aimed to develop an approach to enhance the model precision by artificial images. Materials and Methods Given an epidemiological study designed to predict 1 response using f features with M samples, each feature was converted into a pixel with certain value. Permutated these pixels into F orders, resulting in F distinct artificial image sample sets. Based on the experience of image recognition techniques, appropriate training images results in higher precision model. In the preliminary experiment, a binary response was predicted by 76 features, the sample set included 223 patients and 1776 healthy controls. Results We randomly selected 10 000 artificial sample sets to train the model. Models’ performance (area under the receiver operating characteristic curve values) depicted a bell-shaped distribution. Conclusion The model construction strategy developed in the research has potential to capture feature order related information and enhance model predictability.