Preoperative prediction for periprosthetic bone loss and individual evaluation of bisphosphonate effect after total hip arthroplasty using artificial intelligence

Aims

This study was designed to develop a model for predicting bone mineral density (BMD) loss of the femur after total hip arthroplasty (THA) using artificial intelligence (AI), and to identify factors that influence the prediction. Additionally, we virtually examined the efficacy of administration of bisphosphonate for cases with severe BMD loss based on the predictive model.

Methods

The study included 538 joints that underwent primary THA. The patients were divided into groups using unsupervised time series clustering for five-year BMD loss of Gruen zone 7 postoperatively, and a machine-learning model to predict the BMD loss was developed. Additionally, the predictor for BMD loss was extracted using SHapley Additive exPlanations (SHAP). The patient-specific efficacy of bisphosphonate, which is the most important categorical predictor for BMD loss, was examined by calculating the change in predictive probability when hypothetically switching between the inclusion and exclusion of bisphosphonate.

Results

Time series clustering allowed us to divide the patients into two groups, and the predictive factors were identified including patient- and operation-related factors. The area under the receiver operating characteristic (ROC) curve (AUC) for the BMD loss prediction averaged 0.734. Virtual administration of bisphosphonate showed on average 14% efficacy in preventing BMD loss of zone 7. Additionally, stem types and preoperative triglyceride (TG), creatinine (Cr), estimated glomerular filtration rate (eGFR), and creatine kinase (CK) showed significant association with the estimated patient-specific efficacy of bisphosphonate.

Conclusion

Periprosthetic BMD loss after THA is predictable based on patient- and operation-related factors, and optimal prescription of bisphosphonate based on the prediction may prevent BMD loss.

Dimension reduction of microbiome data linked Bifidobacterium and Prevotella to allergic rhinitis

Dimension reduction has been used to visualise the distribution of multidimensional microbiome data, but the composite variables calculated by the dimension reduction methods have not been widely used to investigate the relationship of the human gut microbiome with lifestyle and disease. In the present study, we applied several dimension reduction methods, including principal component analysis, principal coordinate analysis (PCoA), non-metric multidimensional scaling (NMDS), and non-negative matrix factorization, to a microbiome dataset from 186 subjects with symptoms of  allergic rhinitis (AR) and 106 controls. All the dimension reduction methods supported that the distribution of microbial data points appeared to be continuous rather than discrete. Comparison of the composite variables calculated from the different dimension reduction methods showed that the characteristics of the composite variables differed depending on the distance matrices and the dimension reduction methods. The first composite variables calculated from PCoA and NMDS with the UniFrac distance were strongly associated with AR (FDR adjusted P = 2.4 × 10-4 for PCoA and P = 2.8 × 10-4 for NMDS), and also with the relative abundance of Bifidobacterium and Prevotella. The abundance of Bifidobacterium was also linked to intake of several nutrients, including carbohydrate, saturated fat, and alcohol via composite variables. Notably, the association between the composite variables and AR was much stronger than the association between the relative abundance of individual genera and AR. Our results highlight the usefulness of the dimension reduction methods for investigating the association of microbial composition with lifestyle and disease in clinical research.

Generative artificial intelligence and non-pharmacological bias: an experimental study on cancer patient sexual health communications

Objectives The objective of this study was to explore the feature of generative artificial intelligence (AI) in asking sexual health among cancer survivors, which are often challenging for patients to discuss.Methods We employed the Generative Pre-trained Transformer-3.5 (GPT) as the generative AI platform and used DocsBot for citation retrieval (June 2023). A structured prompt was devised to generate 100 questions from the AI, based on epidemiological survey data regarding sexual difficulties among cancer survivors. These questions were submitted to Bot1 (standard GPT) and Bot2 (sourced from two clinical guidelines).Results No censorship of sexual expressions or medical terms occurred. Despite the lack of reflection on guideline recommendations, 'consultation' was significantly more prevalent in both bots' responses compared with pharmacological interventions, with ORs of 47.3 (p<0.001) in Bot1 and 97.2 (p<0.001) in Bot2.Discussion Generative AI can serve to provide health information on sensitive topics such as sexual health, despite the potential for policy-restricted content. Responses were biased towards non-pharmacological interventions, which is probably due to a GPT model designed with the 's prohibition policy on replying to medical topics. This shift warrants attention as it could potentially trigger patients' expectations for non-pharmacological interventions.

Sodium-glucose co-transporter 2 inhibitor therapy reduces the administration frequency of anti-vascular endothelial growth factor agents in patients with diabetic macular oedema with a history of anti-vascular endothelial growth factor agent use: A cohort study using the Japanese health insurance claims database

AIM

We assessed the effectiveness of sodium-glucose co-transporter 2 inhibitors (SGLT2is) in reducing the administration frequency of anti-vascular endothelial growth factor (VEGF) agents in patients with diabetic macular oedema (DMO) using a health insurance claims database.

MATERIALS AND METHODS

This retrospective cohort study analysed health insurance claims data covering 11 million Japanese patients between 2005 and 2019. We analysed the frequency and duration of intravitreal injection of anti-VEGF agents after initiating SGLT2is or other antidiabetic drugs.

RESULTS

Among 2412 matched patients with DMO, the incidence rates of anti-VEGF agent injections were 230.1 per 1000 person-year in SGLT2i users and 228.4 times per 1000 person-year in non-users, respectively, and the risk ratio for events was unchanged in both groups. Sub-analysis of each baseline characteristic of the patients showed that SGLT2is were particularly effective in patients with a history of anti-VEGF agent use [p = .027, hazard ratio (HR): 0.44, 95% confidence interval (CI): 0.22-0.91]. SGLT2is reduced the risk for the first (p = .023, HR: 0.45, 95% CI: 0.22-0.91) and second (p = .021, HR: 0.39, 95% CI: 0.17-0.89) anti-VEGF agent injections.

CONCLUSIONS

There was no difference in the risk ratio for the addition of anti-VEGF therapy between the two treatment groups. However, the use of SGLT2is reduced the frequency of anti-VEGF agent administration in patients with DMO requiring anti-VEGF therapy. Therefore, SGLT2i therapy may be a novel, non-invasive, low-cost adjunctive therapy for DMO requiring anti-VEGF therapy.

Best practices for multimodal clinical data management and integration: An atopic dermatitis research case

BACKGROUND

In clinical research on multifactorial diseases such as atopic dermatitis, data-driven medical research has become more widely used as means to clarify diverse pathological conditions and to realize precision medicine. However, modern clinical data, characterized as large-scale, multimodal, and multi-center, causes difficulties in data integration and management, which limits productivity in clinical data science.

METHODS

We designed a generic data management flow to collect, cleanse, and integrate data to handle different types of data generated at multiple institutions by 10 types of clinical studies. We developed MeDIA (Medical Data Integration Assistant), a software to browse the data in an integrated manner and extract subsets for analysis.

RESULTS

MeDIA integrates and visualizes data and information on research participants obtained from multiple studies. It then provides a sophisticated interface that supports data management and helps data scientists retrieve the data sets they need. Furthermore, the system promotes the use of unified terms such as identifiers or sampling dates to reduce the cost of pre-processing by data analysts. We also propose best practices in clinical data management flow, which we learned from the development and implementation of MeDIA.

CONCLUSIONS

The MeDIA system solves the problem of multimodal clinical data integration, from complex text data such as medical records to big data such as omics data from a large number of patients. The system and the proposed best practices can be applied not only to allergic diseases but also to other diseases to promote data-driven medical research.

Explainable Machine Learning Classification to Identify Vulnerable Groups Among Parenting Mothers: Web-Based Cross-Sectional Questionnaire Study

BACKGROUND

One life event that requires extensive resilience and adaptation is parenting. However, resilience and perceived support in child-rearing vary, making the real-world situation unclear, even with postpartum checkups.

OBJECTIVE

This study aimed to explore the psychosocial status of mothers during the child-rearing period from newborn to toddler, with a classifier based on data on the resilience and adaptation characteristics of mothers with newborns.

METHODS

A web-based cross-sectional survey was conducted. Mothers with newborns aged approximately 1 month (newborn cohort) were analyzed to construct an explainable machine learning classifier to stratify parenting-related resilience and adaptation characteristics and identify vulnerable populations. Explainable k-means clustering was used because of its high explanatory power and applicability. The classifier was applied to mothers with infants aged 2 months to 1 year (infant cohort) and mothers with toddlers aged >1 year to 2 years (toddler cohort). Psychosocial status, including depressed mood assessed by the Edinburgh Postnatal Depression Scale (EPDS), bonding assessed by the Postpartum Bonding Questionnaire (PBQ), and sleep quality assessed by the Pittsburgh Sleep Quality Index (PSQI) between the classified groups, was compared.

RESULTS

A total of 1559 participants completed the survey. They were split into 3 cohorts, comprising populations of various characteristics, including parenting difficulties and psychosocial measures. The classifier, which stratified participants into 5 groups, was generated from the self-reported scores of resilience and adaptation in the newborn cohort (n=310). The classifier identified that the group with the greatest difficulties in resilience and adaptation to a child's temperament and perceived support had higher incidences of problems with depressed mood (relative prevalence [RP] 5.87, 95% CI 2.77-12.45), bonding (RP 5.38, 95% CI 2.53-11.45), and sleep quality (RP 1.70, 95% CI 1.20-2.40) compared to the group with no difficulties in perceived support. In the infant cohort (n=619) and toddler cohort (n=461), the stratified group with the greatest difficulties had higher incidences of problems with depressed mood (RP 9.05, 95% CI 4.36-18.80 and RP 4.63, 95% CI 2.38-9.02, respectively), bonding (RP 1.63, 95% CI 1.29-2.06 and RP 3.19, 95% CI 2.03-5.01, respectively), and sleep quality (RP 8.09, 95% CI 4.62-16.37 and RP 1.72, 95% CI 1.23-2.42, respectively) compared to the group with no difficulties.

CONCLUSIONS

The classifier, based on a combination of resilience and adaptation to the child's temperament and perceived support, was able identify psychosocial vulnerable groups in the newborn cohort, the start-up stage of childcare. Psychosocially vulnerable groups were also identified in qualitatively different infant and toddler cohorts, depending on their classifier. The vulnerable group identified in the infant cohort showed particularly high RP for depressed mood and poor sleep quality.

d -Alanine Affects the Circadian Clock to Regulate Glucose Metabolism in the Kidney

Key Points

d -Alanine affects the circadian clock to regulate gluconeogenesis in the kidney. d -Alanine itself has a clear intrinsic circadian rhythm, which is regulated by urinary excretion, and acts on the circadian rhythm. d -Alanine is a signal activator for circadian rhythm and gluconeogenesis through circadian transcriptional network.

Background

The aberrant glucose circadian rhythm is associated with the pathogenesis of diabetes. Similar to glucose metabolism in the kidney and liver, d -alanine, a rare enantiomer of alanine, shows circadian alteration, although the effect of d- alanine on glucose metabolism has not been explored. Here, we show that d- alanine acts on the circadian clock and affects glucose metabolism in the kidney.

Methods

The blood and urinary levels of d -alanine in mice were measured using two-dimensional high-performance liquid chromatography system. Metabolic effects of d -alanine were analyzed in mice and in primary culture of kidney proximal tubular cells from mice. Behavioral and gene expression analyses of circadian rhythm were performed using mice bred under constant darkness.

Results

d- Alanine levels in blood exhibited a clear intrinsic circadian rhythm. Since this rhythm was regulated by the kidney through urinary excretion, we examined the effect of d -alanine on the kidney. In the kidney, d -alanine induced the expressions of genes involved in gluconeogenesis and circadian rhythm. Treatment of d- alanine mediated glucose production in mice. Ex vivo glucose production assay demonstrated that the treatment of d -alanine induced glucose production in primary culture of kidney proximal tubular cells, where d -amino acids are known to be reabsorbed, but not in that of liver cells. Gluconeogenetic effect of d -alanine has an intraday variation, and this effect was in part mediated through circadian transcriptional network. Under constant darkness, treatment of d- alanine normalized the circadian cycle of behavior and kidney gene expressions.

Conclusions

d- Alanine induces gluconeogenesis in the kidney and adjusts the period of the circadian clock. Normalization of circadian cycle by d -alanine may provide the therapeutic options for life style–related diseases and shift workers.

Synovial Tissue Heterogeneity in Japanese Patients With Rheumatoid Arthritis Elucidated Using a Cell-Type Deconvolution Approach

OBJECTIVE

Recent advances in single-cell RNA sequencing technology have improved our understanding of the immunological landscape of rheumatoid arthritis (RA). We aimed to stratify the synovium from East Asian patients with RA by immune cell compositions and gain insight into the inflammatory drivers of each synovial phenotype.

METHODS

Synovial tissues were obtained from East Asian patients in Japan with RA (n = 41) undergoing articular surgery. The cellular composition was quantified by a deconvolution approach using a public single-cell-based reference. Inflammatory pathway activity was calculated by gene set variation analysis, and chromatin accessibility was evaluated using assay of transposase accessible chromatin-sequencing.

RESULTS

We stratified RA synovium into three distinct subtypes based on the hierarchical clustering of cellular composition data. One subtype was characterized by abundant HLA-DRAhigh synovial fibroblasts, autoimmune-associated B cells, GZMK+ GZMB+ CD8+ T cells, interleukin (IL)1-β+ monocytes, and plasmablasts. In addition, tumor necrosis factor (TNF)-α, interferons (IFNs), and IL-6 signaling were highly activated in this subtype, and the expression of various chemokines was significantly enhanced. Moreover, we found an open chromatin region overlapping with RA risk locus rs9405192 near the IRF4 gene, suggesting the genetic background influences the development of this inflammatory synovial state. The other two subtypes were characterized by increased IFNs and IL-6 signaling, and expression of molecules associated with degeneration, respectively.

CONCLUSION

This study adds insights into the synovial heterogeneity in East Asian patients and shows a promising link with predominant inflammatory signals. Evaluating the site of inflammation has the potential to lead to appropriate drug selection that matches the individual pathology.

Developing Medical Education Curriculum Reform Strategies to Address the Impact of Generative AI: Qualitative Study

BACKGROUND

Generative artificial intelligence (GAI), represented by large language models, have the potential to transform health care and medical education. In particular, GAI's impact on higher education has the potential to change students' learning experience as well as faculty's teaching. However, concerns have been raised about ethical consideration and decreased reliability of the existing examinations. Furthermore, in medical education, curriculum reform is required to adapt to the revolutionary changes brought about by the integration of GAI into medical practice and research.

OBJECTIVE

This study analyzes the impact of GAI on medical education curricula and explores strategies for adaptation.

METHODS

The study was conducted in the context of faculty development at a medical school in Japan. A workshop involving faculty and students was organized, and participants were divided into groups to address two research questions: (1) How does GAI affect undergraduate medical education curricula? and (2) How should medical school curricula be reformed to address the impact of GAI? The strength, weakness, opportunity, and threat (SWOT) framework was used, and cross-SWOT matrix analysis was used to devise strategies. Further, 4 researchers conducted content analysis on the data generated during the workshop discussions.

RESULTS

The data were collected from 8 groups comprising 55 participants. Further, 5 themes about the impact of GAI on medical education curricula emerged: improvement of teaching and learning, improved access to information, inhibition of existing learning processes, problems in GAI, and changes in physicians' professionality. Positive impacts included enhanced teaching and learning efficiency and improved access to information, whereas negative impacts included concerns about reduced independent thinking and the adaptability of existing assessment methods. Further, GAI was perceived to change the nature of physicians' expertise. Three themes emerged from the cross-SWOT analysis for curriculum reform: (1) learning about GAI, (2) learning with GAI, and (3) learning aside from GAI. Participants recommended incorporating GAI literacy, ethical considerations, and compliance into the curriculum. Learning with GAI involved improving learning efficiency, supporting information gathering and dissemination, and facilitating patient involvement. Learning aside from GAI emphasized maintaining GAI-free learning processes, fostering higher cognitive domains of learning, and introducing more communication exercises.

CONCLUSIONS

This study highlights the profound impact of GAI on medical education curricula and provides insights into curriculum reform strategies. Participants recognized the need for GAI literacy, ethical education, and adaptive learning. Further, GAI was recognized as a tool that can enhance efficiency and involve patients in education. The study also suggests that medical education should focus on competencies that GAI hardly replaces, such as clinical experience and communication. Notably, involving both faculty and students in curriculum reform discussions fosters a sense of ownership and ensures broader perspectives are encompassed.

Multifaceted analysis of cross-tissue transcriptomes reveals phenotype-endotype associations in atopic dermatitis

Atopic dermatitis (AD) is a skin disease that is heterogeneous both in terms of clinical manifestations and molecular profiles. It is increasingly recognized that AD is a systemic rather than a local disease and should be assessed in the context of whole-body pathophysiology. Here we show, via integrated RNA-sequencing of skin tissue and peripheral blood mononuclear cell (PBMC) samples along with clinical data from 115 AD patients and 14 matched healthy controls, that specific clinical presentations associate with matching differential molecular signatures. We establish a regression model based on transcriptome modules identified in weighted gene co-expression network analysis to extract molecular features associated with detailed clinical phenotypes of AD. The two main, qualitatively differential skin manifestations of AD, erythema and papulation are distinguished by differential immunological signatures. We further apply the regression model to a longitudinal dataset of 30 AD patients for personalized monitoring, highlighting patient heterogeneity in disease trajectories. The longitudinal features of blood tests and PBMC transcriptome modules identify three patient clusters which are aligned with clinical severity and reflect treatment history. Our approach thus serves as a framework for effective clinical investigation to gain a holistic view on the pathophysiology of complex human diseases.

Monitoring of blood biochemical markers for periprosthetic joint infection using ensemble machine learning and UMAP embedding

INTRODUCTION

Periprosthetic joint infection (PJI) is a serious complication after total joint arthroplasty. It is important to accurately identify PJI and monitor postoperative blood biochemical marker changes for the appropriate treatment strategy. In this study, we aimed to monitor the postoperative blood biochemical characteristics of PJI by contrasting with non-PJI joint replacement cases to understand how the characteristics change postoperatively.

MATERIALS AND METHODS

A total of 144 cases (52 of PJI and 92 of non-PJI) were reviewed retrospectively and split into development and validation cohorts. After exclusion of 11 cases, a total of 133 (PJI: 50, non-PJI: 83) cases were enrolled finally. An RF classifier was developed to discriminate between PJI and non-PJI cases based on 18 preoperative blood biochemical tests. We evaluated the similarity/dissimilarity between cases based on the RF model and embedded the cases in a two-dimensional space by Uniform Manifold Approximation and Projection (UMAP). The RF model developed based on preoperative data was also applied to the same 18 blood biochemical tests at 3, 6, and 12 months after surgery to analyze postoperative pathological changes in PJI and non-PJI. A Markov chain model was applied to calculate the transition probabilities between the two clusters after surgery.

RESULTS

PJI and non-PJI were discriminated with the RF classifier with the area under the receiver operating characteristic curve of 0.778. C-reactive protein, total protein, and blood urea nitrogen were identified as the important factors that discriminates between PJI and non-PJI patients. Two clusters corresponding to the high- and low-risk populations of PJI were identified in the UMAP embedding. The high-risk cluster, which included a high proportion of PJI patients, was characterized by higher CRP and lower hemoglobin. The frequency of postoperative recurrence to the high-risk cluster was higher in PJI than in non-PJI.

CONCLUSIONS

Although there was overlap between PJI and non-PJI, we were able to identify subgroups of PJI in the UMAP embedding. The machine-learning-based analytical approach is promising in consecutive monitoring of diseases such as PJI with a low incidence and long-term course.

Prediction of Change in Pelvic Tilt After Total Hip Arthroplasty Using Machine Learning

BACKGROUND

A postoperative change in pelvic flexion following total hip arthroplasty (THA) is considered to be one of the causes of dislocation. This study aimed to predict the change of pelvic flexion after THA integrating preoperative and postoperative information with artificial intelligence.

METHODS

This study involved 415 hips which underwent primary THA. Pelvic flexion angle (PFA) is defined as the angle created by the anterior pelvic plane and the horizontal/vertical planes in the supine/standing positions, respectively. Changes in PFA from preoperative supine position to standing position at 5 years after THA were recorded and which were defined as a 5-year change in PFA. Machine learning analysis was performed to predict 5-year change in PFA less than -20° using demographic, blood biochemical, and radiographic data as explanatory variables. Decision trees were constructed based on the important predictors for 5-year change in PFA that can be handled by humans in clinical practice.

RESULTS

Among several machine learning models, random forest showed the highest accuracy (area under the curve = 0.852). Lumbo-lordotic angle, femoral anteversion angle, body mass index, pelvic tilt, and sacral slope were most important random forest predictors. By integrating these preoperative predictors with those obtained 1 year after the surgery, we developed a clinically applicable decision tree model that can predict 5-year change in PFA with area under the curve = 0.914.

CONCLUSION

A machine learning model to predict 5-year change in PFA after THA has been developed by integrating preoperative and postoperative patient information, which may have capabilities for preoperative planning of THA.

Non-negative tensor factorization workflow for time series biomedical data

Non-negative tensor factorization (NTF) enables the extraction of a small number of latent components from high-dimensional biomedical data. However, NTF requires many steps, which is a hurdle to implementation. Here, we provide a protocol for TensorLyCV, an easy to run and reproducible NTF analysis pipeline using Snakemake workflow management system and Docker container. Using vaccine adverse reaction data as an example, we describe steps for data processing, tensor decomposition, optimal rank parameter estimation, and visualization of factor matrices. For complete details on the use and execution of this protocol, please refer to Kei Ikeda et al.1.

Predicting dry weight change in Hemodialysis patients using machine learning

BACKGROUND

Machine Learning has been increasingly used in the medical field, including managing patients undergoing hemodialysis. The random forest classifier is a Machine Learning method that can generate high accuracy and interpretability in the data analysis of various diseases. We attempted to apply Machine Learning to adjust dry weight, the appropriate volume status of patients undergoing hemodialysis, which requires a complex decision-making process considering multiple indicators and the patient's physical conditions.

METHODS

All medical data and 69,375 dialysis records of 314 Asian patients undergoing hemodialysis at a single dialysis center in Japan between July 2018 and April 2020 were collected from the electronic medical record system. Using the random forest classifier, we developed models to predict the probabilities of adjusting the dry weight at each dialysis session.

RESULTS

The areas under the receiver-operating-characteristic curves of the models for adjusting the dry weight upward and downward were 0.70 and 0.74, respectively. The average probability of upward adjustment of the dry weight had sharp a peak around the actual change over time, while the average probability of downward adjustment of the dry weight formed a gradual peak. Feature importance analysis revealed that median blood pressure decline was a strong predictor for adjusting the dry weight upward. In contrast, elevated serum levels of C-reactive protein and hypoalbuminemia were important indicators for adjusting the dry weight downward.

CONCLUSIONS

The random forest classifier should provide a helpful guide to predict the optimal changes to the dry weight with relative accuracy and may be useful in clinical practice.

Protocol to acquire time series data on adverse reactions following vaccination using a smartphone or web-based platform

Data collection on adverse reactions in recipients after vaccination is vital to evaluate potential health issues, but health observation diaries are onerous for participants. Here, we present a protocol to collect time series information using a smartphone or web-based platform, thus eliminating the need for paperwork and data submission. We describe steps for setting up the platform using the Model-View-Controller web framework, uploading lists of recipients, sending notifications, and managing respondent data. For complete details on the use and execution of this protocol, please refer to Ikeda et al. (2022).¹.

A simple scoring model based on machine learning predicts intravenous immunoglobulin resistance in Kawasaki disease

INTRODUCTION

In Kawasaki disease (KD), accurate prediction of intravenous immunoglobulin (IVIG) resistance is crucial to reduce a risk for developing coronary artery lesions.

OBJECTIVE

To establish a simple scoring model predicting IVIG resistance in KD patients based on the machine learning model.

METHODS

A retrospective cohort study of 1002 KD patients diagnosed at 12 facilities for 10 years, in which 22.7% were resistant to initial IVIG treatment. We performed machine learning with diverse models using 30 clinical variables at diagnosis in 801 and 201 cases for training and test datasets, respectively. SHAP was applied to identify the variables that influenced the prediction model. A scoring model was designed using the influential clinical variables based on the Shapley additive explanation results.

RESULTS

Light gradient boosting machine model accurately predicted IVIG resistance (area under the receiver operating characteristic curve (AUC), 0.78; sensitivity, 0.50; specificity, 0.88). Next, using top three influential features (days of illness at initial therapy, serum levels of C-reactive protein, and total cholesterol), we designed a simple scoring system. In spite of its simplicity, it predicted IVIG resistance (AUC, 0.72; sensitivity, 0.49; specificity, 0.82) as accurately as machine learning models. Moreover, accuracy of our scoring system with three clinical features was almost identical to that of Gunma score with seven clinical features (AUC, 0.73; sensitivity, 0.53; specificity, 0.83), a well-known logistic regression scoring model.

CONCLUSION

A simple scoring system based on the findings in machine learning seems to be a useful tool to accurately predict IVIG resistance in KD patients.

Machine-learning predicts time-series prognosis factors in metastatic prostate cancer patients treated with androgen deprivation therapy

Machine learning technology is expected to support diagnosis and prognosis prediction in medicine. We used machine learning to construct a new prognostic prediction model for prostate cancer patients based on longitudinal data obtained from age at diagnosis, peripheral blood and urine tests of 340 prostate cancer patients. Random survival forest (RSF) and survival tree were used for machine learning. In the time-series prognostic prediction model for metastatic prostate cancer patients, the RSF model showed better prediction accuracy than the conventional Cox proportional hazards model for almost all time periods of progression-free survival (PFS), overall survival (OS) and cancer-specific survival (CSS). Based on the RSF model, we created a clinically applicable prognostic prediction model using survival trees for OS and CSS by combining the values of lactate dehydrogenase (LDH) before starting treatment and alkaline phosphatase (ALP) at 120 days after treatment. Machine learning provides useful information for predicting the prognosis of metastatic prostate cancer prior to treatment intervention by considering the nonlinear and combined impacts of multiple features. The addition of data after the start of treatment would allow for more precise prognostic risk assessment of patients and would be beneficial for subsequent treatment selection.

Machine learning approach to stratify complex heterogeneity of chronic heart failure: A report from the CHART-2 study

AIMS

Current approaches to classify chronic heart failure (HF) subpopulations may be limited due to the diversity of pathophysiology and co-morbidities in chronic HF. We aimed to elucidate the clusters of chronic patients with HF by data-driven approaches with machine learning in a hospital-based registry.

METHODS AND RESULTS

A total of 4649 patients with a broad spectrum of left ventricular ejection fraction (LVEF) in the CHART-2 (Chronic Heart Failure Analysis and Registry in the Tohoku District-2) study were enrolled to this study. Chronic HF patients were classified using random forest clustering with 56 multiscale clinical parameters. We assessed the influence of the clusters on cardiovascular death, non-cardiovascular death, all-cause death, and free from hospitalization by HF. Latent class analysis using random forest clustering identified 10 clusters with four primary components: cardiac function (LVEF, left atrial and ventricular diameters, diastolic blood pressure, and brain natriuretic peptide), renal function (glomerular filtration rate and blood urea nitrogen), anaemia (red blood cell, haematocrit, haemoglobin, and platelet count), and nutrition (albumin and body mass index). All 11 significant clinical parameters in the four primary components and two disease aetiologies (ischaemic heart disease and valvular heart disease) showed statistically significant differences among the 10 clusters (P < 0.01). Cluster 1 (26.7% of patients), which is characterized by preserved LVEF (<59%, 37% of the total) with lowest brain natriuretic peptide (>111.3 pg/mL, 0.9%) and lowest left atrial diameter (>42 mm, 37.4%), showed the best 5 year survival rate of 98.1% for cardiovascular death, 95.9% for non-cardiovascular death, 92.9% for all-cause death, and 91.7% for free from hospitalization by HF. Cluster 10 (6.0% of the total), which is co-morbid disorders of all four primary components, showed the worst survival rate of 39.1% for cardiovascular death, 68.9% for non-cardiovascular death, 23.9% for all-cause death, and 28.1% for free from hospitalization by HF.

CONCLUSIONS

These results suggest the potential applicability of the machine leaning approach, providing useful clinical prognostic information to stratify complex heterogeneity in patients with HF.

Predicting pathological highly invasive lung cancer from preoperative [18F]FDG PET/CT with multiple machine learning models

PURPOSE

The efficacy of sublobar resection of primary lung cancer have been proven in recent years. However, sublobar resection for highly invasive lung cancer increases local recurrence. We developed and validated multiple machine learning models predicting pathological invasiveness of lung cancer based on preoperative [¹⁸F]fluorodeoxyglucose (FDG) positron emission tomography (PET) and computed tomography (CT) radiomic features.

METHODS

Overall, 873 patients who underwent lobectomy or segmentectomy for primary lung cancer were enrolled. Radiomics features were extracted from preoperative PET/CT images with the PyRadiomics package. Seven machine learning models and an ensemble of all models (ENS) were evaluated after 100 iterations. In addition, the probability of highly invasive lung cancer was calculated in a nested cross-validation to assess the calibration plot and clinical usefulness and to compare to consolidation tumour ratio (CTR) on CT images, one of the generally used diagnostic criteria.

RESULTS

In the training set, when PET and CT features were combined, all models achieved an area under the curve (AUC) of ≥ 0.880. In the test set, ENS showed the highest mean AUC of 0.880 and smallest standard deviation of 0.0165, and when the cutoff was 0.5, accuracy of 0.804, F1 of 0.851, precision of 0.821, and recall of 0.885. In the nested cross-validation, the AUC of 0.882 (95% CI: 0.860-0.905) showed a high discriminative ability, and the calibration plot indicated consistency with a Brier score of 0.131. A decision curve analysis showed that the ENS was valid with a threshold probability ranging from 3 to 98%. Accuracy showed an improvement of more than 8% over the CTR.

CONCLUSION

The machine learning model based on preoperative [¹⁸F]FDG PET/CT images was able to predict pathological highly invasive lung cancer with high discriminative ability and stability. The calibration plot showed good consistency, suggesting its usefulness in quantitative risk assessment.

Statistical Analysis of Mortality Rates of Coronavirus Disease 2019 (COVID-19) Patients in Japan Across the 4C Mortality Score Risk Groups, Age Groups, and Epidemiological Waves: A Report From the Nationwide COVID-19 Cohort

Background

The mortality rates of coronavirus disease 2019 (COVID-19) have been changed across the epidemiological waves. The aim was to investigate the differences in mortality rates of COVID-19 patients in Japan across the 6 epidemiological waves stratified by age group and Coronavirus Clinical Characterisation Consortium (4C) mortality score risk group.

Methods

A total of 56 986 COVID-19 patients in the COVID-19 Registry Japan from 2 March 2020 to 1 February 2022 were enrolled. These patients were categorized into 4 risk groups based on their 4C mortality score. Mortality rates of each risk group were calculated separately for different age groups: 18-64, 65-74, 75-89, and ≥90 years. In addition, mortality rates across the wave periods were calculated separately in 2 age groups: <75 and ≥75 years. All calculated mortality rates were compared with reported data from the United Kingdom (UK) during the early epidemic.

Results

The mortality rates of patients in Japan were significantly lower than in the UK across the board, with the exception of patients aged ≥90 years at very high risk. The mortality rates of patients aged ≥75 years at very high risk in the fourth and fifth wave periods showed no significant differences from those in the UK, whereas those in the sixth wave period were significantly lower in all age groups and in all risk groups.

Conclusions

The present analysis showed that COVID-19 patients had a lower mortality rate in the most recent sixth wave period, even among patients ≥75 years old at very high risk.

The Histone Methyltransferase SETD8 Regulates the Expression of Tumor Suppressor Genes via H4K20 Methylation and the p53 Signaling Pathway in Endometrial Cancer Cells

The histone methyltransferase SET domain-containing protein 8 (SETD8), which methylates histone H4 lysine 20 (H4K20) and non-histone proteins such as p53, plays key roles in human carcinogenesis. Our aim was to determine the involvement of SETD8 in endometrial cancer and its therapeutic potential and identify the downstream genes regulated by SETD8 via H4K20 methylation and the p53 signaling pathway. We examined the expression profile of SETD8 and evaluated whether SETD8 plays a critical role in the proliferation of endometrial cancer cells using small interfering RNAs (siRNAs). We identified the prognostically important genes regulated by SETD8 via H4K20 methylation and p53 signaling using chromatin immunoprecipitation sequencing, RNA sequencing, and machine learning. We confirmed that SETD8 expression was elevated in endometrial cancer tissues. Our in vitro results suggest that the suppression of SETD8 using siRNA or a selective inhibitor attenuated cell proliferation and promoted the apoptosis of endometrial cancer cells. In these cells, SETD8 regulates genes via H4K20 methylation and the p53 signaling pathway. We also identified the prognostically important genes related to apoptosis, such as those encoding KIAA1324 and TP73, in endometrial cancer. SETD8 is an important gene for carcinogenesis and progression of endometrial cancer via H4K20 methylation.

Population-based Screening for Hereditary Colorectal Cancer Variants in Japan

BACKGROUND & AIMS

Colorectal cancer (CRC) is one of the most common cancers in the world. A small proportion of CRCs can be attributed to recognizable hereditary germline variants of known CRC susceptibility genes. To better understand cancer risk, it is necessary to explore the prevalence of hereditary CRC and pathogenic variants of multiple cancer-predisposing genes in non-European populations.

METHODS

We analyzed the coding regions of 27 cancer-predisposing genes in 12,503 unselected Japanese CRC patients and 23,705 controls by target sequencing and genome-wide SNP chip. Their clinical significance was assessed using ClinVar and the guidelines by ACMG/AMP.

RESULTS

We identified 4,804 variants in the 27 genes and annotated them as pathogenic in 397 and benign variants in 941, of which 43.6% were novel. In total, 3.3% of the unselected CRC patients and 1.5% of the controls had a pathogenic variant. The pathogenic variants of MSH2 (odds ratio (OR) = 18.1), MLH1 (OR = 8.6), MSH6 (OR = 4.9), APC (OR = 49.4), BRIP1 (OR=3.6), BRCA1 (OR = 2.6), BRCA2 (OR = 1.9), and TP53 (OR = 1.7) were significantly associated with CRC development in the Japanese population (P-values<0.01, FDR<0.05). These pathogenic variants were significantly associated with diagnosis age and personal/family history of cancer. In total, at least 3.5% of the Japanese CRC population had a pathogenic variant or CNV of the 27 cancer-predisposing genes, indicating hereditary cancers.

CONCLUSIONS

This largest study of CRC heredity in Asia can contribute to the development of guidelines for genetic testing and variant interpretation for heritable CRCs.

Detecting time-evolving phenotypic components of adverse reactions against BNT162b2 mRNA SARS-CoV-2 vaccine via non-negative tensor factorization

Symptoms of adverse reactions to vaccines evolve over time, but traditional studies have focused only on the frequency and intensity of symptoms. Here, we attempt to extract the dynamic changes in vaccine adverse reaction symptoms as a small number of interpretable components by using non-negative tensor factorization. We recruited healthcare workers who received two doses of the BNT162b2 mRNA COVID-19 vaccine at Chiba University Hospital and collected information on adverse reactions using a smartphone/web-based platform. We analyzed the adverse-reaction data after each dose obtained for 1,516 participants who received two doses of vaccine. The non-negative tensor factorization revealed four time-evolving components that represent typical temporal patterns of adverse reactions for both doses. These components were differently associated with background factors and post-vaccine antibody titers. These results demonstrate that complex adverse reactions against vaccines can be explained by a limited number of time-evolving components identified by tensor factorization.

•

Tensor factorization identified 4 components that explain vaccine adverse reactions

•

These components were differently associated with background factors

•

Only 1 component was significantly associated with post-vaccine antibody titer

•

These methods and results will inform future studies on vaccine safety and efficacy

Diagnosis of Atrial Fibrillation Using Machine Learning With Wearable Devices After Cardiac Surgery: Algorithm Development Study

Background

Some attempts have been made to detect atrial fibrillation (AF) with a wearable device equipped with photoelectric volumetric pulse wave technology, and it is expected to be applied under real clinical conditions.

Objective

This study is the second part of a 2-phase study aimed at developing a method for immediate detection of paroxysmal AF, using a wearable device with built-in photoplethysmography (PPG). The objective of this study is to develop an algorithm to immediately diagnose AF by an Apple Watch equipped with a PPG sensor that is worn by patients undergoing cardiac surgery and to use machine learning on the pulse data output from the device.

Methods

A total of 80 patients who underwent cardiac surgery at a single institution between June 2020 and March 2021 were monitored for postoperative AF, using a telemetry-monitored electrocardiogram (ECG) and an Apple Watch. AF was diagnosed by qualified physicians from telemetry-monitored ECGs and 12-lead ECGs; a diagnostic algorithm was developed using machine learning on the pulse rate data output from the Apple Watch.

Results

One of the 80 patients was excluded from the analysis due to redness caused by wearing the Apple Watch. Of 79 patients, 27 (34.2%) developed AF, and 199 events of AF including brief AF were observed. Of them, 18 events of AF lasting longer than 1 hour were observed, and cross-correlation analysis showed that pulse rate measured by Apple Watch was strongly correlated (cross-correlation functions [CCF]: 0.6-0.8) with 8 events and very strongly correlated (CCF>0.8) with 3 events. The diagnostic accuracy by machine learning was 0.9416 (sensitivity 0.909 and specificity 0.838 at the point closest to the top left) for the area under the receiver operating characteristic curve.

Conclusions

We were able to safely monitor pulse rate in patients who wore an Apple Watch after cardiac surgery. Although the pulse rate measured by the PPG sensor does not follow the heart rate recorded by telemetry-monitored ECGs in some parts, which may reduce the accuracy of AF diagnosis by machine learning, we have shown the possibility of clinical application of using only the pulse rate collected by the PPG sensor for the early detection of AF.

Prediction algorithm for ICU mortality and length of stay using machine learning

Machine learning can predict outcomes and determine variables contributing to precise prediction, and can thus classify patients with different risk factors of outcomes. This study aimed to investigate the predictive accuracy for mortality and length of stay in intensive care unit (ICU) patients using machine learning, and to identify the variables contributing to the precise prediction or classification of patients. Patients (n = 12,747) admitted to the ICU at Chiba University Hospital were randomly assigned to the training and test cohorts. After learning using the variables on admission in the training cohort, the area under the curve (AUC) was analyzed in the test cohort to evaluate the predictive accuracy of the supervised machine learning classifiers, including random forest (RF) for outcomes (primary outcome, mortality; secondary outcome, length of ICU stay). The rank of the variables that contributed to the machine learning prediction was confirmed, and cluster analysis of the patients with risk factors of mortality was performed to identify the important variables associated with patient outcomes. Machine learning using RF revealed a high predictive value for mortality, with an AUC of 0.945 (95% confidence interval [CI] 0.922–0.977). In addition, RF showed high predictive value for short and long ICU stays, with AUCs of 0.881 (95% CI 0.876–0.908) and 0.889 (95% CI 0.849–0.936), respectively. Lactate dehydrogenase (LDH) was identified as a variable contributing to the precise prediction in machine learning for both mortality and length of ICU stay. LDH was also identified as a contributing variable to classify patients into sub-populations based on different risk factors of mortality. The machine learning algorithm could predict mortality and length of stay in ICU patients with high accuracy. LDH was identified as a contributing variable in mortality and length of ICU stay prediction and could be used to classify patients based on mortality risk.

Microbiota-Independent Spontaneous Dermatitis Associated With Increased Sebaceous Lipid Production in Tmem79-Deficient Mice

TMEM79 is a predisposing gene for atopic dermatitis (AD). Tmem79-deficient mice develop spontaneous dermatitis in a biphasic pattern. The 1^st-phase dermatitis is unique, as it occurs independent of microbiota status, whereas the 2^nd-phase dermatitis is microbiota-dependent. In this study, we sought to identify key factors mediating the development of 1^st-phase dermatitis. Structural analysis showed that sebaceous gland hyperplasia started from 1^st-phase dermatitis. Longitudinal RNA-sequencing analysis revealed significant activation of fatty acid lipid-metabolism pathways in 1^st-phase dermatitis, whereas Th17-based immune response genes were highly expressed in 2^nd-phase dermatitis. Quantitative reverse transcription-polymerase chain reaction analysis revealed that genes involved in fatty acid elongation and sebocyte differentiation were upregulated in 1^st-phase dermatitis. The results of thin-layer chromatography supported these findings with an increased abundance of wax esters, cholesterol esters, and fatty alcohols in hair lipids. Further gas chromatography-tandem mass spectrometry analysis showed an increase in total fatty acid production, including that of elongated C20-24 saturated and C18-24 mono-unsaturated fatty acids. Collectively, these results suggest that aberrant production of sebaceous long-chain fatty acids is associated with microbiota-independent dermatitis. Further investigation of Tmem79-deficient mice may clarify the role of certain fatty acids in dermatitis.

C10orf99/GPR15L Regulates Proinflammatory Response of Keratinocytes and Barrier Formation of the Skin

The epidermis, outermost layer of the skin, forms a barrier and is involved in innate and adaptive immunity in an organism. Keratinocytes participate in all these three protective processes. However, a regulator of keratinocyte protective responses against external dangers and stresses remains elusive. We found that upregulation of the orphan gene 2610528A11Rik was a common factor in the skin of mice with several types of inflammation. In the human epidermis, peptide expression of G protein-coupled receptor 15 ligand (GPR15L), encoded by the human ortholog C10orf99, was highly induced in the lesional skin of patients with atopic dermatitis or psoriasis. C10orf99 gene transfection into normal human epidermal keratinocytes (NHEKs) induced the expression of inflammatory mediators and reduced the expression of barrier-related genes. Gene ontology analyses showed its association with translation, mitogen-activated protein kinase (MAPK), mitochondria, and lipid metabolism. Treatment with GPR15L reduced the expression levels of filaggrin and loricrin in human keratinocyte 3D cultures. Instead, their expression levels in mouse primary cultured keratinocytes did not show significant differences between the wild-type and 2610528A11Rik deficient keratinocytes. Lipopolysaccharide-induced expression of Il1b and Il6 was less in 2610528A11Rik deficient mouse keratinocytes than in wild-type, and imiquimod-induced psoriatic dermatitis was blunted in 2610528A11Rik deficient mice. Furthermore, repetitive subcutaneous injection of GPR15L in mouse ears induced skin inflammation in a dose-dependent manner. These results suggest that C10orf99/GPR15L is a primary inducible regulator that reduces the barrier formation and induces the inflammatory response of keratinocytes.

Multiple nutritional and gut microbial factors associated with allergic rhinitis: the Hitachi Health Study

Several studies suggest the involvement of dietary habits and gut microbiome in allergic diseases. However, little is known about the nutritional and gut microbial factors associated with the risk of allergic rhinitis (AR). We recruited 186 participants with symptoms of AR and 106 control subjects without symptoms of AR at the Hitachi Health Care Center, Japan. The habitual consumption of 42 selected nutrients were examined using the brief-type self-administered diet history questionnaire. Faecal samples were collected and subjected to amplicon sequencing of the 16S ribosomal RNA gene hypervariable regions. Association analysis revealed that four nutrients (retinol, vitamin A, cryptoxanthin, and copper) were negatively associated with AR. Among 40 genera examined, relative abundance of Prevotella and Escherichia were associated with AR. Furthermore, significant statistical interactions were observed between retinol and Prevotella. The age- and sex-adjusted odds of AR were 25-fold lower in subjects with high retinol intake and high Prevotella abundance compared to subjects with low retinol intake and low Prevotella abundance. Our data provide insights into complex interplay between dietary nutrients, gut microbiome, and the development of AR.

Mitochondrial reactive oxygen species trigger metformin-dependent antitumor immunity via activation of Nrf2/mTORC1/p62 axis in tumor-infiltrating CD8T lymphocytes

Background

Metformin (Met) is the first-line treatment for type 2 diabetes mellitus and plays an effective role in treating various diseases, such as cardiovascular disease, neurodegenerative disease, cancer, and aging. However, the underlying mechanism of Met-dependent antitumor immunity remains to be elucidated.

Methods

MitoTEMPO, a scavenger of mitochondrial superoxide, abolished the antitumor effect of Met, but not antiprogrammed cell death (PD-1) antibody (Ab) treatment. Consequently, we studied the mechanism of the Met-induced antitumor effect. Expressions of glucose transporter (Glut)-1, mitochondrial reactive oxygen species (mtROS), interferon (IFN)-γ, Ki67, autophagy markers, activation markers for NF-E2-related factor 2 (Nrf2), and mammalian target of rapamaycin complex 1 (mTORC1) in CD8⁺ tumor-infiltrating T lymphocytes (CD8TILs) were examined by flow cytometry analysis. In addition, conditional knockout mice for Nrf2 and p62 were used to detect these markers, together with the monitoring of in vivo tumor growth. RNA sequencing was performed for CD8TILs and tumor cells. Melanoma cells containing an IFN-γ receptor (IFNγR) cytoplasmic domain deletion mutant was overexpressed and used for characterization of the metabolic profile of those tumor cells using a Seahorse Flux Analyzer.

Results

Met administration elevates mtROS and cell surface Glut-1, resulting in the production of IFN-γ in CD8TILs. mtROS activates Nrf2 in a glycolysis-dependent manner, inducing activation of autophagy, glutaminolysis, mTORC1, and p62/SQSTM1. mTORC1-dependent phosphorylation of p62 at serine 351 (p-p62(S351)) is also involved in activation of Nrf2. Conditional deletion of Nrf2 in CD8TILs abrogates mTORC1 activation and antitumor immunity by Met. In synergy with the effect of anti-PD-1 Ab, Met boosts CD8TIL proliferation and IFN-γ secretion, resulting in decreased glycolysis and oxidative phosphorylation in tumor cells. Consequently, Glut-1 is elevated in CD8TILs, together with the expansion of activated dendritic cells. Moreover, tumor cells lacking in IFNγR signaling abolish IFN-γ production and proliferation of CD8TILs.

Conclusions

We found that Met stimulates production of mtROS, which triggers Glut-1 elevation and Nrf2 activation in CD8TILs. Nrf2 activates mTORC1, whereas mTORC1 activates Nrf2 in a p-p62(S351)-dependent manner, thus creating a feedback loop that ensures CD8TILs’ proliferation. In combination with anti-PD-1 Ab, Met stimulates robust proliferation of CD8TILs and IFN-γ secretion, resulting in an IFN-γ-dependent reprogramming of the tumor microenvironment.

Variant PCGF1-PRC1 links PRC2 recruitment with differentiation-associated transcriptional inactivation at target genes

Polycomb repressive complexes-1 and -2 (PRC1 and 2) silence developmental genes in a spatiotemporal manner during embryogenesis. How Polycomb group (PcG) proteins orchestrate down-regulation of target genes upon differentiation, however, remains elusive. Here, by differentiating embryonic stem cells into embryoid bodies, we reveal a crucial role for the PCGF1-containing variant PRC1 complex (PCGF1-PRC1) to mediate differentiation-associated down-regulation of a group of genes. Upon differentiation cues, transcription is down-regulated at these genes, in association with PCGF1-PRC1-mediated deposition of histone H2AK119 mono-ubiquitination (H2AK119ub1) and PRC2 recruitment. In the absence of PCGF1-PRC1, both H2AK119ub1 deposition and PRC2 recruitment are disrupted, leading to aberrant expression of target genes. PCGF1-PRC1 is, therefore, required for initiation and consolidation of PcG-mediated gene repression during differentiation.

Polycomb repressive complexes (PRC1 and PRC2) repress genes that are crucial for development via epigenetic modifications; however, their role in differentiation is not well known. Here the authors reveal that a PCGF1-containing PRC1 variant facilitates exit from pluripotency by downregulating target genes and recruiting PRC2.

Exit from germinal center to become quiescent memory B cells depends on metabolic reprograming and provision of a survival signal

A still unanswered question is what drives the small fraction of activated germinal center (GC) B cells to become long-lived quiescent memory B cells. We found here that a small population of GC-derived CD38^intBcl6^hi/intEfnb1⁺ cells with lower mTORC1 activity favored the memory B cell fate. Constitutively high mTORC1 activity led to defects in formation of the CD38^intBcl6^hi/intEfnb1⁺ cells; conversely, decreasing mTORC1 activity resulted in relative enrichment of this memory-prone population over the recycling-prone one. Furthermore, the CD38^intBcl6^hi/intEfnb1⁺ cells had higher levels of Bcl2 and surface BCR that, in turn, contributed to their survival and development. We also found that downregulation of Bcl6 resulted in increased expression of both Bcl2 and BCR. Given the positive correlation between the strength of T cell help and mTORC1 activity, our data suggest a model in which weak help from T cells together with provision of an increased survival signal are key for GC B cells to adopt a memory B cell fate.

Associations of ultrasound-based inflammation patterns with peripheral innate lymphoid cell populations, serum cytokines/chemokines, and treatment response to methotrexate in rheumatoid arthritis and spondyloarthritis

Objectives

We aimed to explore the associations of musculoskeletal inflammation patterns with peripheral blood innate lymphoid cell (ILC) populations, serum cytokines/chemokines, and treatment response to methotrexate in patients with rheumatoid arthritis (RA) and spondyloarthritis (SpA).

Methods

We enrolled 100 patients with either RA or SpA and performed ultrasound to evaluate power Doppler signals for synovitis (52 joint regions), tenosynovitis (20 tendons), and enthesitis (44 sites). We performed clustering analysis using unsupervised random forest based on the multi-axis ultrasound information and classified the patients into groups. We identified and counted ILC1-3 populations in the peripheral blood by flow cytometry and also measured the serum levels of 20 cytokines/chemokines. We also determined ACR20 response at 3 months in 38 patients who began treatment with methotrexate after study assessment.

Results

Synovitis was more prevalent and severe in RA than in SpA, whereas tenosynovitis and enthesitis were comparable between RA and SpA. Patients were classified into two groups which represented synovitis-dominant and synovitis-nondominant inflammation patterns. While peripheral ILC counts were not significantly different between RA and SpA, they were significantly higher in the synovitis-nondominant group than in the synovitis-dominant group (ILC1-3: p = 0.0007, p = 0.0061, and p = 0.0002, respectively). On the other hand, clustering of patients based on serum cytokines/chemokines did not clearly correspond either to clinical diagnoses or to synovitis-dominant/nondominant patterns. The synovitis-dominant pattern was the most significant factor that predicted clinical response to methotrexate (p = 0.0065).

Conclusions

Musculoskeletal inflammation patterns determined by ultrasound are associated with peripheral ILC counts and could predict treatment response to methotrexate.

Multiomics Investigation Revealing the Characteristics of HIV-1-Infected Cells In Vivo

For eradication of HIV-1 infection, it is important to elucidate the detailed features and heterogeneity of HIV-1-infected cells in vivo. To reveal multiple characteristics of HIV-1-producing cells in vivo, we use a hematopoietic-stem-cell-transplanted humanized mouse model infected with GFP-encoding replication-competent HIV-1. We perform multiomics experiments using recently developed technology to identify the features of HIV-1-infected cells. Genome-wide HIV-1 integration-site analysis reveals that productive HIV-1 infection tends to occur in cells with viral integration into transcriptionally active genomic regions. Bulk transcriptome analysis reveals that a high level of viral mRNA is transcribed in HIV-1-infected cells. Moreover, single-cell transcriptome analysis shows the heterogeneity of HIV-1-infected cells, including CXCL13^high cells and a subpopulation with low expression of interferon-stimulated genes, which can contribute to efficient viral spread in vivo. Our findings describe multiple characteristics of HIV-1-producing cells in vivo, which could provide clues for the development of an HIV-1 cure.

Staphylococcus cohnii is a potentially biotherapeutic skin commensal alleviating skin inflammation

Host-microbe interactions orchestrate skin homeostasis, the dysregulation of which has been implicated in chronic inflammatory conditions such as atopic dermatitis and psoriasis. Here, we show that Staphylococcus cohnii is a skin commensal capable of beneficially inhibiting skin inflammation. We find that Tmem79^-/- mice spontaneously develop interleukin-17 (IL-17)-producing T-cell-driven skin inflammation. Comparative skin microbiome analysis reveals that the disease activity index is negatively associated with S. cohnii. Inoculation with S. cohnii strains isolated from either mouse or human skin microbiota significantly prevents and ameliorates dermatitis in Tmem79^-/- mice without affecting pathobiont burden. S. cohnii colonization is accompanied by activation of host glucocorticoid-related pathways and induction of anti-inflammatory genes in the skin and is therefore effective at suppressing inflammation in diverse pathobiont-independent dermatitis models, including chemically induced, type 17, and type 2 immune-driven models. As such, S. cohnii strains have great potential as effective live biotherapeutics for skin inflammation.

Targeting critical kinases and anti-apoptotic molecules overcomes steroid resistance in MLL-rearranged leukaemia

BACKGROUND

Acute lymphoblastic leukaemia with mixed lineage leukaemia gene rearrangement (MLL-ALL) frequently affects infants and is associated with a poor prognosis. Primary refractory and relapsed disease due to resistance to glucocorticoids (GCs) remains a substantial hurdle to improving clinical outcomes. In this study, we aimed to overcome GC resistance of MLL-ALL.

METHODS

Using leukaemia patient specimens, we performed bioinformatic analyses to identify target genes/pathways. To test inhibition of target pathways in vivo, we created pre-clinical therapeutic mouse patient-derived xenograft (PDX)-models by transplanting human MLL-ALL leukaemia initiating cells (LIC) into immune-deficient NSG mice. Finally, we conducted B-cell lymphoma-2 (BCL-2) homology domain 3 (BH3) profiling to identify BH3 peptides responsible for treatment resistance in MLL-leukaemia.

FINDINGS

Src family kinases (SFKs) and Fms-like tyrosine kinase 3 (FLT3) signaling pathway were over-represented in MLL-ALL cells. PDX-models of infant MLL- ALL recapitulated GC-resistance in vivo but RK-20449, an inhibitor of SFKs and FLT3 eliminated human MLL-ALL cells in vivo, overcoming GC-resistance. Further, we identified BCL-2 dependence as a mechanism of treatment resistance in MLL-ALL through BH3 profiling. Furthermore, MLL-ALL cells resistant to RK-20449 treatment were dependent on the anti-apoptotic BCL-2 protein for their survival. Combined inhibition of SFKs/FLT3 by RK-20449 and of BCL-2 by ABT-199 led to substantial elimination of MLL-ALL cells in vitro and in vivo. Triple treatment combining GCs, RK-20449 and ABT-199 resulted in complete elimination of MLL-ALL cells in vivo.

INTERPRETATION

SFKs/FLT3 signaling pathways are promising targets for treatment of treatment-resistant MLL-ALL. Combined inhibition of these kinase pathways and anti-apoptotic BCL-2 successfully eliminated highly resistant MLL-ALL and demonstrated a new treatment strategy for treatment-resistant poor-outcome MLL-ALL.

FUNDING

This study was supported by RIKEN (RIKEN President's Discretionary Grant) for FI, Japan Agency for Medical Research and Development (the Basic Science and Platform Technology Program for Innovative Biological Medicine for FI and by NIH CA034196 for LDS. The funders had no role in the study design, data collection, data analysis, interpretation nor writing of the report.

Metabolic remodeling in the right ventricle of rats with severe pulmonary arterial hypertension

It is generally considered that there is an increase in glycolysis in the hypertrophied right ventricle (RV) during pulmonary hypertension (PH), which leads to a decrease in glucose oxidation through the tricarboxylic acid (TCA) cycle. Although recent studies have demonstrated that fatty acid (FA) and glucose accumulated in the RV of patients with PH, the details of this remain to be elucidated. The purpose of the current study was to assess the metabolic remodeling in the RV of rats with PH using a metabolic analysis. Male rats were treated with the vascular endothelial growth factor receptor blocker SU5416 followed by 3 weeks of hypoxic conditions and 5 weeks of normoxic conditions (Su/Hx rats). Hemodynamic measurements were conducted, and the RV was harvested for the measurement of metabolites. A metabolomics analysis revealed a decreasing trend in the levels of alanine, argininosuccinic acid and downstream TCA cycle intermediates, including fumaric and malic acid and an increasing trend in branched‑chain amino acids (BCAAs) in Su/Hx rats compared with the controls; however, no trends in glycolysis were indicated. The FA metabolomics analysis also revealed a decreasing trend in the levels of long‑chain acylcarnitines, which transport FA from the cytosol to the mitochondria and are essential for beta‑oxidation. The current study demonstrated that the TCA cycle was less activated because of a decreasing trend in the expression of fumaric acid and malic acid, which might be attributable to the expression of adenylosuccinic acid and argininosuccinic acid. These results suggest that dysregulated BCAA metabolism and a decrease in FA oxidation might contribute to the reduction of the TCA cycle reactions.

The Cxxc1 subunit of the Trithorax complex directs epigenetic licensing of CD4+ T cell differentiation

Different dynamics of gene expression are observed during cell differentiation. In T cells, genes that are turned on early or turned off and stay off have been thoroughly studied. However, genes that are initially turned off but then turned on again after stimulation has ceased have not been defined; they are obviously important, especially in the context of acute versus chronic inflammation. Using the Th1/Th2 differentiation paradigm, we found that the Cxxc1 subunit of the Trithorax complex directs transcription of genes initially down-regulated by TCR stimulation but up-regulated again in a later phase. The late up-regulation of these genes was impaired either by prolonged TCR stimulation or Cxxc1 deficiency, which led to decreased expression of Trib3 and Klf2 in Th1 and Th2 cells, respectively. Loss of Cxxc1 resulted in enhanced pathogenicity in allergic airway inflammation in vivo. Thus, Cxxc1 plays essential roles in the establishment of a proper CD4⁺ T cell immune system via epigenetic control of a specific set of genes.

Assessment of skin barrier function using skin images with topological data analysis

Recent developments of molecular biology have revealed diverse mechanisms of skin diseases, and precision medicine considering these mechanisms requires the frequent objective evaluation of skin phenotypes. Transepidermal water loss (TEWL) is commonly used for evaluating skin barrier function; however, direct measurement of TEWL is time-consuming and is not convenient for daily clinical practice. Here, we propose a new skin barrier assessment method using skin images with topological data analysis (TDA). TDA enabled efficient identification of structural features from a skin image taken by a microscope. These features reflected the regularity of the skin texture. We found a significant correlation between the topological features and TEWL. Moreover, using the features as input, we trained machine-learning models to predict TEWL and obtained good accuracy (R² = 0.524). Our results suggest that assessment of skin barrier function by topological image analysis is promising.

Improving the trans-ancestry portability of polygenic risk scores by prioritizing variants in predicted cell-type-specific regulatory elements

Poor trans-ancestry portability of polygenic risk scores is a consequence of Eurocentric genetic studies and limited knowledge of shared causal variants. Leveraging regulatory annotations may improve portability by prioritizing functional over tagging variants. We constructed a resource of 707 cell-type-specific IMPACT regulatory annotations by aggregating 5,345 epigenetic datasets to predict binding patterns of 142 transcription factors across 245 cell types. We then partitioned the common SNP heritability of 111 genome-wide association study summary statistics of European (average n ≈ 189,000) and East Asian (average n ≈ 157,000) origin. IMPACT annotations captured consistent SNP heritability between populations, suggesting prioritization of shared functional variants. Variant prioritization using IMPACT resulted in increased trans-ancestry portability of polygenic risk scores from Europeans to East Asians across all 21 phenotypes analyzed (49.9% mean relative increase in R2). Our study identifies a crucial role for functional annotations such as IMPACT to improve the trans-ancestry portability of genetic data.

Genetic characterization of pancreatic cancer patients and prediction of carrier status of germline pathogenic variants in cancer-predisposing genes

BACKGROUND

National Comprehensive Cancer Network (NCCN) recently recommended germline genetic testing for all pancreatic cancer patients. However, the genes targeted by genetic testing and the feasibility of selecting patients likely to carry pathogenic variants have not been sufficiently verified. The purpose of this study was to genetically characterize Japanese patients and examine whether the current guideline is applicable in this population.

METHODS

Using targeted sequencing, we analyzed the coding regions of 27 cancer-predisposing genes in 1,005 pancreatic cancer patients and 23,705 controls in Japan. We compared the pathogenic variant frequency between cases and controls and documented the demographic and clinical characteristics of carrier patients. We then examined if it was possible to use machine learning to predict carrier status based on those characteristics.

FINDINGS

We identified 205 pathogenic variants across the 27 genes. Pathogenic variants in BRCA2, ATM, and BRCA1 were significantly associated with pancreatic cancer. Characteristics associated with carrier status were inconsistent with previous investigations. Machine learning classifiers had a low performance in determining the carrier status of pancreatic cancer patients, while the same classifiers, when applied to breast cancer data as a positive control, had a higher performance that was comparable to that of the NCCN guideline.

INTERPRETATION

Our findings support the clinical significance of multigene panel testing for pancreatic cancer and indicate that at least 3.4% of Japanese patients may respond to poly (ADP ribose) polymerase inhibitor treatments. The difficulty in predicting carrier status suggests that offering germline genetic testing for all pancreatic cancer patients is reasonable.

FUNDING

AMED under Grant Number JP19kk0305010 and Australian National Health and Medical Research funding (ID177524).

[Health and Medical Revolution Driven by Artificial Intelligence]

With the development and diversification of medical care, the importance of precision medicine, which selects a suitable treatment for the individual patient from a huge number of options, is increasing. It is often difficult to explain multifactorial diseases such as cancer and chronic inflammatory diseases by a single hypothesis. In such case, a data-driven approach is essential to construct individualized models based on comprehensive observation of the target disease. The data-driven approach utilizes artificial intelligence to extract, predict, and classify patterns of data, considering different types of variables and complex dependencies between variables. In this paper, we introduce the basic idea, typical methods, and application examples of artificial intelligence and its core technology, machine learning. We would like to discuss a new framework of medical research toward the next generation medicine, while reviewing how machine learning is used in precise prediction and data-driven redefinition of diseases.

Tet2 and Tet3 in B cells are required to repress CD86 and prevent autoimmunity

A contribution of epigenetic modifications to B cell tolerance has been proposed but not directly tested. Here we report that deficiency of ten-eleven translocation (Tet) DNA demethylase family members Tet2 and Tet3 in B cells led to hyperactivation of B and T cells, autoantibody production and lupus-like disease in mice. Mechanistically, in the absence of Tet2 and Tet3, downregulation of CD86, which normally occurs following chronic exposure of self-reactive B cells to self-antigen, did not take place. The importance of dysregulated CD86 expression in Tet2- and Tet3-deficient B cells was further demonstrated by the restriction, albeit not complete, on aberrant T and B cell activation following anti-CD86 blockade. Tet2- and Tet3-deficient B cells had decreased accumulation of histone deacetylase 1 (HDAC1) and HDAC2 at the Cd86 locus. Thus, our findings suggest that Tet2- and Tet3-mediated chromatin modification participates in repression of CD86 on chronically stimulated self-reactive B cells, which contributes, at least in part, to preventing autoimmunity.

Large-scale genome-wide association study in a Japanese population identifies novel susceptibility loci across different diseases

The overwhelming majority of participants in current genetic studies are of European ancestry. To elucidate disease biology in the East Asian population, we conducted a genome-wide association study (GWAS) with 212,453 Japanese individuals across 42 diseases. We detected 320 independent signals in 276 loci for 27 diseases, with 25 novel loci (P < 9.58 × 10^-9). East Asian-specific missense variants were identified as candidate causal variants for three novel loci, and we successfully replicated two of them by analyzing independent Japanese cohorts; p.R220W of ATG16L2 (associated with coronary artery disease) and p.V326A of POT1 (associated with lung cancer). We further investigated enrichment of heritability within 2,868 annotations of genome-wide transcription factor occupancy, and identified 378 significant enrichments across nine diseases (false discovery rate < 0.05) (for example, NKX3-1 for prostate cancer). This large-scale GWAS in a Japanese population provides insights into the etiology of complex diseases and highlights the importance of performing GWAS in non-European populations.

Exploratory analysis of plasma cytokine/chemokine levels in 6-year-old children from a birth cohort study

This study aimed to reveal a new dimension of allergy profiles in the general population by using machine learning to explore complex relationships among various cytokines/chemokines and allergic diseases (asthma and atopic dermatitis; AD). We examined the symptoms related to asthma and AD and the plasma levels of 72 cytokines/chemokines obtained from a general population of 161 children at 6 years of age who participated in a pilot birth cohort study of the Japan Environment and Children's Study (JECS). The children whose signs and symptoms fulfilled the criteria of AD, which are mostly based on questionnaire including past symptoms, tended to have higher levels of the two chemokine ligands, CCL17 and CCL27, which are used for diagnosis of AD. On the other hand, another AD-related chemokine CCL22 level in plasma was higher only in children with visible flexural eczema, which is one of AD diagnostic criteria but was judged on the same day of blood examination unlike other criteria. Here, we also developed an innovative method of machine learning for elucidating the complex cytokine/chemokine milieu related to symptoms of allergic diseases by using clustering analysis based on the random forest dissimilarity measure that relies on artificial intelligence (AI) technique. To our surprise, the majority of children showing at least any asthma-related symptoms during the last month were divided by AI into the two clusters, either cluster-2 having elevated levels of IL-33 (related to eosinophil activation) or cluster-3 having elevated levels of CXCL7/NAP2 (related to neutrophil activation), among the total three clusters. Future studies will clarify better approach for allergic diseases by endotype classification.

Chronic circadian misalignment accelerates immune senescence and abbreviates lifespan in mice

Modern society characterized by a 24/7 lifestyle leads to misalignment between environmental cycles and endogenous circadian rhythms. Persisting circadian misalignment leads to deleterious effects on health and healthspan. However, the underlying mechanism remains not fully understood. Here, we subjected adult, wild-type mice to distinct chronic jet-lag paradigms, which showed that long-term circadian misalignment induced significant early mortality. Non-biased RNA sequencing analysis using liver and kidney showed marked activation of gene regulatory pathways associated with the immune system and immune disease in both organs. In accordance, we observed enhanced steatohepatitis with infiltration of inflammatory cells. The investigation of senescence-associated immune cell subsets from the spleens and mesenteric lymph nodes revealed an increase in PD-1⁺CD44^high CD4 T cells as well as CD95⁺GL7⁺ germinal center B cells, indicating that the long-term circadian misalignment exacerbates immune senescence and consequent chronic inflammation. Our results underscore immune homeostasis as a pivotal interventional target against clock-related disorders.

Osteoprotegerin-dependent M cell self-regulation balances gut infection and immunity

Microfold cells (M cells) are responsible for antigen uptake to initiate immune responses in the gut-associated lymphoid tissue (GALT). Receptor activator of nuclear factor-κB ligand (RANKL) is essential for M cell differentiation. Follicle-associated epithelium (FAE) covers the GALT and is continuously exposed to RANKL from stromal cells underneath the FAE, yet only a subset of FAE cells undergoes differentiation into M cells. Here, we show that M cells express osteoprotegerin (OPG), a soluble inhibitor of RANKL, which suppresses the differentiation of adjacent FAE cells into M cells. Notably, OPG deficiency increases M cell number in the GALT and enhances commensal bacterium-specific immunoglobulin production, resulting in the amelioration of disease symptoms in mice with experimental colitis. By contrast, OPG-deficient mice are highly susceptible to Salmonella infection. Thus, OPG-dependent self-regulation of M cell differentiation is essential for the balance between the infectious risk and the ability to perform immunosurveillance at the mucosal surface.

Microfold cells (M cells) sit at the gut epithelial surface to sample antigens and maintain local immune homeostasis. Here the authors show that M cells are feedback-regulated by M cell-originated osteoprotegerin (OPG) to suppress RNAKL-induced M cell differentiation, and that OPG deficiency alters both gut colitis and infection phenotypes.