Prediction and causal inference of cardiovascular and cerebrovascular diseases based on lifestyle questionnaires.

Cardiovascular and cerebrovascular diseases (CCVD) are prominent mortality causes in Japan, necessitating effective preventative measures, early diagnosis, and treatment to mitigate their impact. A diagnostic model was developed to identify patients with ischemic heart disease (IHD), stroke, or both, using specific health examination data. Lifestyle habits affecting CCVD development were analyzed using five causal inference methods. This study included 473,734 patients aged ≥ 40 years who underwent specific health examinations in Kanazawa, Japan between 2009 and 2018 to collect data on basic physical information, lifestyle habits, and laboratory parameters such as diabetes, lipid metabolism, renal function, and liver function. Four machine learning algorithms were used: Random Forest, Logistic regression, Light Gradient Boosting Machine, and eXtreme-Gradient-Boosting (XGBoost). The XGBoost model exhibited superior area under the curve (AUC), with mean values of 0.770 (± 0.003), 0.758 (± 0.003), and 0.845 (± 0.005) for stroke, IHD, and CCVD, respectively. The results of the five causal inference analyses were summarized, and lifestyle behavior changes were observed after the onset of CCVD. A causal relationship from 'reduced mastication' to 'weight gain' was found for all causal species theory methods. This prediction algorithm can screen for asymptomatic myocardial ischemia and stroke. By selecting high-risk patients suspected of having CCVD, resources can be used more efficiently for secondary testing.

Prediction and causal inference of hyperuricemia using gut microbiota.

Hyperuricemia (HUA) is a symptom of high blood uric acid (UA) levels, which causes disorders such as gout and renal urinary calculus. Prolonged HUA is often associated with hypertension, atherosclerosis, diabetes mellitus, and chronic kidney disease. Studies have shown that gut microbiota (GM) affect these chronic diseases. This study aimed to determine the relationship between HUA and GM. The microbiome of 224 men and 254 women aged 40 years was analyzed through next-generation sequencing and machine learning. We obtained GM data through 16S rRNA-based sequencing of the fecal samples, finding that alpha-diversity by Shannon index was significantly low in the HUA group. Linear discriminant effect size analysis detected a high abundance of the genera Collinsella and Faecalibacterium in the HUA and non-HUA groups. Based on light gradient boosting machine learning, we propose that HUA can be predicted with high AUC using four clinical characteristics and the relative abundance of nine bacterial genera, including Collinsella and Dorea. In addition, analysis of causal relationships using a direct linear non-Gaussian acyclic model indicated a positive effect of the relative abundance of the genus Collinsella on blood UA levels. Our results suggest abundant Collinsella in the gut can increase blood UA levels.

3D CNN-based Deep Learning Model-based Explanatory Prognostication in Patients with Multiple Myeloma using Whole-body MRI.

Although magnetic resonance imaging (MRI) data of patients with multiple myeloma (MM) are used to predict prognosis, few reports have applied artificial intelligence (AI) techniques for this purpose. We aimed to analyze whole-body diffusion-weighted MRI data using three-dimensional (3D) convolutional neural networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM), an explainable AI, to predict prognosis and explore the factors involved in prediction. We retrospectively analyzed the MRI data of a total of 142 patients with MM obtained from two medical centers. We defined the occurrence of progressive disease after MRI evaluation within 12 months as a poor prognosis and constructed a 3D CNN-based deep learning model to predict prognosis. Images from 111 cases were used as the training and internal validation data; images from 31 cases were used as the external validation data. Internal validation of the AI model with stratified 5-fold cross-validation resulted in a significant difference in progression-free survival (PFS) between good and poor prognostic cases (2-year PFS, 91.2% versus [vs.] 61.1%, P = 0.0002). The AI model clearly stratified good and poor prognostic cases in the external validation cohort (2-year PFS, 92.9% vs. 55.6%, P = 0.004), with an area under the receiver operating characteristic curve of 0.804. According to Grad-CAM, the MRI signals of the spleen and bones of the vertebrae and pelvis contributed to prognosis prediction. This study is the first to show that image analysis of whole-body MRI using a 3D CNN without any other clinical data is effective in predicting the prognosis of patients with MM.

A hyperaldosteronism subtypes predictive model using ensemble learning.

This study aimed to develop a machine-learning algorithm to diagnose aldosterone-producing adenoma (APA) for predicting APA probabilities. A retrospective cross-sectional analysis of the Japan Rare/Intractable Adrenal Diseases Study dataset was performed using the nationwide PA registry in Japan comprised of 41 centers. Patients treated between January 2006 and December 2019 were included. Forty-six features at screening and 13 features at confirmatory test were used for model development to calculate APA probability. Seven machine-learning programs were combined to develop the ensemble-learning model (ELM), which was externally validated. The strongest predictive factors for APA were serum potassium (s-K) at first visit, s-K after medication, plasma aldosterone concentration, aldosterone-to-renin ratio, and potassium supplementation dose. The average performance of the screening model had an AUC of 0.899; the confirmatory test model had an AUC of 0.913. In the external validation, the AUC was 0.964 in the screening model using an APA probability of 0.17. The clinical findings at screening predicted the diagnosis of APA with high accuracy. This novel algorithm can support the PA practice in primary care settings and prevent potentially curable APA patients from falling outside the PA diagnostic flowchart.

Comprehensive Steroid Assay with Non-Targeted Analysis Using Liquid Chromatography Ion Mobility Mass Spectrometry.

Aldosterone-producing adenomas (APAs) have different steroid profiles in serum, depending on the causative genetic mutation. Ion mobility is a separation technique for gas-phase ions based on their m/z values, shapes, and sizes. Human serum (100 µL) was purified by liquid-liquid extraction using tert-butyl methyl ether/ethyl acetate at 1/1 (v/v) and mixed with deuterium-labeled steroids as the internal standard. The separated supernatant was dried, re-dissolved in water containing 20% methanol, and injected into a liquid chromatography-ion mobility-mass spectrometer (LC/IM/MS). We established a highly sensitive assay system by separating 20 steroids based on their retention time, m/z value, and drift time. Twenty steroids were measured in the serum of patients with primary aldosteronism, essential hypertension, and healthy subjects and were clearly classified using principal component analysis. This method was also able to detect phosphatidylcholine and phosphatidylethanolamine, which were not targeted. LC/IM/MS has a high selectivity for known compounds and has the potential to provide information on unknown compounds. This analytical method has the potential to elucidate the pathogenesis of APA and identify unknown steroids that could serve as biomarkers for APA with different genetic mutations.

Impact of gut microbiome on dyslipidemia in japanese adults: Assessment of the Shika-machi super preventive health examination results for causal inference.

Dyslipidemia (DL) is one of the most common lifestyle-related diseases. There are few reports showing the causal relationship between gut microbiota (GM) and DL. In the present study, we used a linear non-Gaussian acyclic model (LiNGAM) to evaluate the causal relationship between GM and DL. A total of 79 men and 82 women aged 40 years or older living in Shika-machi, Ishikawa Prefecture, Japan were included in the analysis, and their clinical information was investigated. DNA extracted from the GM was processed to sequence the 16S rRNA gene using next-generation sequencing. Participants were divided into four groups based on sex and lipid profile information. The results of one-way analysis of covariance, linear discriminant analysis effect size, and least absolute value reduction and selection operator logistic regression model indicated that several bacteria between men and women may be associated with DL. The LiNGAM showed a presumed causal relationship between different bacteria and lipid profiles in men and women. In men, Prevotella 9 and Bacteroides were shown to be potentially associated with changes in low- and high-density lipoprotein cholesterol levels. In women, the LiNGAM results showed two bacteria, Akkermansia and Escherichia/Shigella, had a presumptive causal relationship with lipid profiles. These results may provide a new sex-based strategy to reduce the risk of developing DL and to treat DL through the regulation of the intestinal environment using specific GM.

Evaluating tubulointerstitial compartments in renal biopsy specimens using a deep learning-based approach for classifying normal and abnormal tubules.

Renal pathology is essential for diagnosing and assessing the severity and prognosis of kidney diseases. Deep learning-based approaches have developed rapidly and have been applied in renal pathology. However, methods for the automated classification of normal and abnormal renal tubules remain scarce. Using a deep learning-based method, we aimed to classify normal and abnormal renal tubules, thereby assisting renal pathologists in the evaluation of renal biopsy specimens. Consequently, we developed a U-Net-based segmentation model using randomly selected regions obtained from 21 renal biopsy specimens. Further, we verified its performance in multiclass segmentation by calculating the Dice coefficients (DCs). We used 15 cases of tubulointerstitial nephritis to assess its applicability in aiding routine diagnoses conducted by renal pathologists and calculated the agreement ratio between diagnoses conducted by two renal pathologists and the time taken for evaluation. We also determined whether such diagnoses were improved when the output of segmentation was considered. The glomeruli and interstitium had the highest DCs, whereas the normal and abnormal renal tubules had intermediate DCs. Following the detailed evaluation of the tubulointerstitial compartments, the proximal, distal, atrophied, and degenerated tubules had intermediate DCs, whereas the arteries and inflamed tubules had low DCs. The annotation and output areas involving normal and abnormal tubules were strongly correlated in each class. The pathological concordance for the glomerular count, t, ct, and ci scores of the Banff classification of renal allograft pathology remained high with or without the segmented images. However, in terms of time consumption, the quantitative assessment of tubulitis, tubular atrophy, degenerated tubules, and the interstitium was improved significantly when renal pathologists considered the segmentation output. Deep learning algorithms can assist renal pathologists in the classification of normal and abnormal tubules in renal biopsy specimens, thereby facilitating the enhancement of renal pathology and ensuring appropriate clinical decisions.

Explainable Machine Learning for Atrial Fibrillation in the General Population Using a Generalized Additive Model　- A Cross-Sectional Study.

Background: Atrial fibrillation (AF) is the most common arrhythmia and is associated with increased thromboembolic stroke risk and heart failure. Although various prediction models for AF risk have been developed using machine learning, their output cannot be accurately explained to doctors and patients. Therefore, we developed an explainable model with high interpretability and accuracy accounting for the non-linear effects of clinical characteristics on AF incidence. Methods and Results: Of the 489,073 residents who underwent specific health checkups between 2009 and 2018 and were registered in the Kanazawa Medical Association database, data were used for 5,378 subjects with AF and 167,950 subjects with normal electrocardiogram readings. Forty-seven clinical parameters were combined using a generalized additive model algorithm. We validated the model and found that the area under the curve, sensitivity, and specificity were 0.964, 0.879, and 0.920, respectively. The 9 most important variables were the physical examination of arrhythmia, a medical history of coronary artery disease, age, hematocrit, γ-glutamyl transpeptidase, creatinine, hemoglobin, systolic blood pressure, and HbA1c. Further, non-linear relationships of clinical variables to the probability of AF diagnosis were visualized. Conclusions: We established a novel AF risk explanation model with high interpretability and accuracy accounting for non-linear information obtained at general health checkups. This model contributes not only to more accurate AF risk prediction, but also to a greater understanding of the effects of each characteristic.

Impact of salt intake on urinary albumin excretion in patients with type 2 diabetic nephropathy: a retrospective cohort study based on a generalized additive model.

Diabetic kidney disease is an important and common cause of end-stage renal disease. Measurement of urinary albumin excretion (UAE) requires the diagnosis of the stage of diabetic nephropathy and the prognosis of renal function. We aimed to analyze the impact of lifestyle modification on UAE in patients with stage 2 and 3 type 2 diabetic nephropathy who received comprehensive medical care, using a generalized additive model (GAM), an explanatory machine learning model. In this retrospective observational study, we used changes in HbA1c, systolic blood pressure (SBP), and diastolic blood pressure (DBP) levels; body mass index (BMI); and daily salt intake as factors contributing to changes in UAE. In total, 269 patients with type 2 diabetic nephropathy were enrolled (stage 2, 217 patients; stage 3, 52 patients). The rankings that contributed to changes in UAE over 6 months by permutation importance were the changes in daily salt intake, HbA1c, SBP, DBP, and BMI. GAM, which predicts the change in UAE, showed that with increase in the changes in salt intake, SBP, and HbA1c, the delta UAE tended to increase. Salt intake was the most contributory factor for the changes in UAE, and daily salt intake was the best lifestyle factor to explain the changes in UAE. Strict control of salt intake may have beneficial effects on improving UAE in patients with stage 2 and 3 diabetic nephropathy.

Effect of sodium-glucose cotransporter-2 inhibitors on aldosterone-to-renin ratio in diabetic patients with hypertension: a retrospective observational study.

BACKGROUND: Plasma aldosterone-to-renin ratio (ARR) is popularly used for screening primary aldosteronism (PA). Some medications, including diuretics, are known to have an effect on ARR and cause false-negative and false-positive results in PA screening. Currently, there are no studies on the effects of sodium-glucose cotransporter-2 (SGLT2) inhibitors, which are known to have diuretic effects, on ARR. We aimed to investigate the effects of SGLT2 inhibitors on ARR. METHODS: We employed a retrospective design; the study was conducted from April 2016 to December 2018 and carried out in three hospitals. Forty patients with diabetes and hypertension were administered SGLT2 inhibitors. ARR was evaluated before 2 to 6 months after the administration of SGLT2 inhibitors to determine their effects on ARR. RESULTS: No significant changes in the levels of ARR (90.9 ± 51.6 vs. 81.4 ± 62.9) were found. Body mass index, diastolic blood pressure, heart rate, fasting plasma glucose, and hemoglobin A1c were significantly decreased by SGLT2 inhibitors. Serum creatinine was significantly increased. CONCLUSION: SGLT2 inhibitor administration yielded minimal effects on ARR and did not increase false-negative results in PA screening in patients with diabetes and hypertension more than 2 months after administration.

Impact of Gut Microbiome on Hypertensive Patients With Low-Salt Intake: Shika Study Results.

Salt intake is one of the most important environmental factors impacting hypertension onset. Meanwhile, the potential roles of the gut microbiome (GM) in altering the health status of hosts have drawn considerable attention. Here, we aimed to perform an observational study to investigate the impact of intestinal bacterial flora in hypertensive patients with low-salt or high-salt intake. A total of 239 participants were enrolled, and their gut microbiomes, clinical and demographic details, as well as physiological parameters pertaining to the renin-angiotensin-aldosterone system and inflammatory cytokine profiles, were examined. The participants were classified into four groups based on the presence of different enterotype bacteria, as determined via cluster analysis, and salt intake: low salt/GM enterotype 1, low salt/GM enterotype 2, high salt/GM enterotype 1, and high salt/GM enterotype 2. Results show that the prevalence of hypertension was significantly lower in the low-salt/GM enterotype 2 group (27%) compared to the low salt/GM enterotype 1 group (47%; p = 0.04). Alternatively, no significant differences were observed in hypertension prevalence between the two high-salt intake groups (GM enterotype 1 = 50%, GM enterotype 2 = 47%; p = 0.83). Furthermore, The low-salt/GM enterotype 2 was higher in the relative abundances of Blautia, Bifidobacterium, Escherichia-Shigella, Lachnoclostridium, and Clostridium sensu stricto than the low-salt/GM enterotype 1. differed significantly between the GM enterotypes. These results suggested that consumption of a low-salt diet was ineffective in regulating hypertension in individuals with a specific gut bacteria composition. Our findings support the restoration of GM homeostasis as a new strategy for controlling blood pressure and preventing the development of hypertension.