Validation of Distinct Bladder Pain Phenotypes Utilizing the MAPP Research Network Cohort

INTRODUCTION AND HYPOTHESIS

As interstitial cystitis/bladder pain syndrome (IC/BPS) likely represents multiple pathophysiologies, we sought to validate three clinical phenotypes of IC/BPS patients in a large, multi-center cohort using unsupervised machine learning (ML) analysis.

METHODS

Using the female Genitourinary Pain Index and O'Leary-Sant Indices, k-means unsupervised clustering was utilized to define symptomatic phenotypes in 130 premenopausal IC/BPS participants recruited through the Multidisciplinary Approach to the Study of Chronic Pelvic Pain (MAPP) research network. Patient-reported symptoms were directly compared between MAPP ML-derived phenotypic clusters to previously defined phenotypes from a single center (SC) cohort.

RESULTS

Unsupervised ML categorized IC/BPS participants into three phenotypes with distinct pain and urinary symptom patterns: myofascial pain, non-urologic pelvic pain, and bladder-specific pain. Defining characteristics included presence of myofascial pain or trigger points on examination for myofascial pain patients (p = 0.003) and bladder pain/burning for bladder-specific pain patients (p < 0.001). The three phenotypes were derived using only 11 features (fGUPI subscales and ICSI/ICPI items), in contrast to 49 items required previously. Despite substantial reduction in classification features, unsupervised ML independently generated similar symptomatic clusters in the MAPP cohort with equivalent symptomatic patterns and physical examination findings as the SC cohort.

CONCLUSIONS

The reproducible identification of IC/BPS phenotypes, distinguishing bladder-specific pain from myofascial and genital pain, using independent ML analysis of a multicenter database suggests these phenotypes reflect true pathophysiologic differences in IC/BPS patients.

Butyricimonas is a key gut microbiome component for predicting postoperative recurrence of esophageal cancer

BACKGROUND

Recently, intestinal bacteria have attracted attention as factors affecting the prognosis of patients with cancer. However, the intestinal microbiome is composed of several hundred types of bacteria, necessitating the development of an analytical method that can allow the use of this information as a highly accurate biomarker. In this study, we investigated whether the preoperative intestinal bacterial profile in patients with esophageal cancer who underwent surgery after preoperative chemotherapy could be used as a biomarker of postoperative recurrence of esophageal cancer.

METHODS

We determined the gut microbiome of the patients using 16S rRNA metagenome sequencing, followed by statistical analysis. Simultaneously, we performed a machine learning analysis using a random forest model with hyperparameter tuning and compared the data obtained.

RESULTS

Statistical and machine learning analyses revealed two common bacterial genera, Butyricimonas and Actinomyces, which were abundant in cases with recurrent esophageal cancer. Butyricimonas primarily produces butyrate, whereas Actinomyces are oral bacteria whose function in the gut is unknown.

CONCLUSION

Our results indicate that Butyricimonas spp. may be a biomarker of postoperative recurrence of esophageal cancer. Although the extent of the involvement of these bacteria in immune regulation remains unknown, future research should investigate their presence in other pathological conditions. Such research could potentially lead to a better understanding of the immunological impact of these bacteria on patients with cancer and their application as biomarkers.

Optimized strategy for schistosomiasis elimination: results from marginal benefit modeling

BACKGROUND

Poverty contributes to the transmission of schistosomiasis via multiple pathways, with the insufficiency of appropriate interventions being a crucial factor. The aim of this article is to provide more economical and feasible intervention measures for endemic areas with varying levels of poverty.

METHODS

We collected and analyzed the prevalence patterns along with the cost of control measures in 11 counties over the last 20 years in China. Seven machine learning models, including XGBoost, support vector machine, generalized linear model, regression tree, random forest, gradient boosting machine and neural network, were used for developing model and calculate marginal benefits.

RESULTS

The XGBoost model had the highest prediction accuracy with an R2 of 0.7308. Results showed that risk surveillance, snail control with molluscicides and treatment were the most effective interventions in controlling schistosomiasis prevalence. The best combination of interventions was interlacing seven interventions, including risk surveillance, treatment, toilet construction, health education, snail control with molluscicides, cattle slaughter and animal chemotherapy. The marginal benefit of risk surveillance is the most effective intervention among nine interventions, which was influenced by the prevalence of schistosomiasis and cost.

CONCLUSIONS

In the elimination phase of the national schistosomiasis program, emphasizing risk surveillance holds significant importance in terms of cost-saving.

Radiomics and machine learning analysis by computed tomography and magnetic resonance imaging in colorectal liver metastases prognostic assessment

OBJECTIVE

The aim of this study was the evaluation radiomics analysis efficacy performed using computed tomography (CT) and magnetic resonance imaging in the prediction of colorectal liver metastases patterns linked to patient prognosis: tumor growth front; grade; tumor budding; mucinous type. Moreover, the prediction of liver recurrence was also evaluated.

METHODS

The retrospective study included an internal and validation dataset; the first was composed by 119 liver metastases from 49 patients while the second consisted to 28 patients with single lesion. Radiomic features were extracted using PyRadiomics. Univariate and multivariate approaches including machine learning algorithms were employed.

RESULTS

The best predictor to identify tumor growth was the Wavelet_HLH_glcm_MaximumProbability with an accuracy of 84% and to detect recurrence the best predictor was wavelet_HLH_ngtdm_Complexity with an accuracy of 90%, both extracted by T1-weigthed arterial phase sequence. The best predictor to detect tumor budding was the wavelet_LLH_glcm_Imc1 with an accuracy of 88% and to identify mucinous type was wavelet_LLH_glcm_JointEntropy with an accuracy of 92%, both calculated on T2-weigthed sequence. An increase statistically significant of accuracy (90%) was obtained using a linear weighted combination of 15 predictors extracted by T2-weigthed images to detect tumor front growth. An increase statistically significant of accuracy at 93% was obtained using a linear weighted combination of 11 predictors by the T1-weigthed arterial phase sequence to classify tumor budding. An increase statistically significant of accuracy at 97% was obtained using a linear weighted combination of 16 predictors extracted on CT to detect recurrence. An increase statistically significant of accuracy was obtained in the tumor budding identification considering a K-nearest neighbors and the 11 significant features extracted T1-weigthed arterial phase sequence.

CONCLUSIONS

The results confirmed the Radiomics capacity to recognize clinical and histopathological prognostic features that should influence the choice of treatments in colorectal liver metastases patients to obtain a more personalized therapy.

On the predictability of short-lived particulate matter around a cement plant in Kerman, Iran: machine learning analysis

One of the greatest environmental risks in the cement industry is particulate matter emission (i.e., PM_2.5 and PM₁₀). This paper aims to develop descriptive-analytical solutions for increasing the accuracy of predicting particulate matter emissions using resample data of Kerman cement plant. Photometer instruments DUST TRAK and BS-EN-12341 method were used to determine concentration of PM_2.5 and PM₁₀. Sampling was performed on 4 environmental stations of Kerman cement plant in the four seasons. In order to accurate assessment of particulate matter concentration, a new model was proposed to resample cement plant time series data using Pandas in Python. The effect of meteorological parameters including wind speed, relative humidity, air temperature and rainfall on the particulate matter concentration was investigated through statistical analysis. The results indicated that the maximum annual average of 24-h of PM_2.5 belonged to the east side (opposite the clinker depot) in 2019 (31.50 μg m^-3) and west side (in front of the mine) in 2020 (31.00 μg m^-3). Also, maximum annual average of 24-h of PM₁₀ belonged to the west side (in front of the mine) in 2020 (121.00 μg m^-3) and east side (opposite the clinker depot) in 2020 (120.75 μg m^-3). The PM_2.5 and PM₁₀ concentrations are more than the allowable limit. The results demonstrate that particulate matter concentration increases with increasing relative humidity and rainfall. Finally, the SARIMA model was used to predict the particulate matter concentration.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s13762-022-04645-3.

A machine learning analysis of drought and rural population change on the North American Great Plains since the 1970s

Machine learning techniques have to date not been widely used in population-environment research, but represent a promising tool for identifying relationships between environmental variables and population outcomes. They may be particularly useful for instances where the nature of the relationship is not obvious or not easily detected using other methods, or where the relationship potentially varies across spatial scales within a given study unit. Machine learning techniques may also help the researcher identify the relative strength of influence of specific variables within a larger set of interacting ones, and so provide a useful methodological approach for exploratory research. In this study, we use machine learning techniques in the form of random forest and regression tree analyses to look for possible connections between drought and rural population loss on the North American Great Plains between 1970 and 2020. In doing so, we analyzed four decades of population count data (at county-size spatial scales), monthly climate data, and Palmer Drought Severity Index scores for Canada and the USA at multiple spatial scales (regional, sub-regional, national, and county/census division levels), along with county level irrigation data. We found that in some parts of Saskatchewan and the Dakotas - particularly those areas that fall within more temperate/less arid ecological sub-regions - drought conditions in the middle years of the 1970s had a significant association with rural population losses. A similar but weaker association was identified in a small cluster of North Dakota counties in the 1990s. Our models detected few links between drought and rural population loss in other decades or in other parts of the Great Plains. Based on R-squared results, models for US portions of the Plains generally exhibited stronger drought-population loss associations than did Canadian portions, and temperate ecological sub-regions exhibited stronger associations than did more arid sub-regions. Irrigation rates showed no significant influence on population loss. This article focuses on describing the methodological steps, considerations, and benefits of employing this type of machine learning approach to investigating connections between drought and rural population change.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11111-022-00399-9.

Gold nanorod arrays enable highly sensitive bacterial detection via surface-enhanced infrared absorption (SEIRA) spectroscopy

Infrared (IR) spectroscopy is a unique and powerful method in the identification, characterization, and classification of chemical and biological molecules. However, the low absorbance of biological molecules has arisen as a major bottleneck and inhibits the application of IR in practical applications. To overcome this limitation, in the last four decades, surface-enhanced IR absorption (SEIRA) spectroscopy has been proposed and has become the focus of interest in various applications. In this study, for the first time, we proposed the employment of 3D anisotropic gold nanorod arrays (GNAs) as a highly active SEIRA platform in bacterial detection. For this, GNA platforms were fabricated through an oblique angle deposition (OAD) approach by using a physical vapor deposition (PVD) system. OAD of gold at proper deposition angle (10°) created closely-packed and columnar gold nanorod structures onto the glass slides in a well-controlled manner. GNA platform was tested as a SEIRA system in three different species of bacteria (Escherichia coli, Staphylococcus aureus, and Bacillus subtilis) by collecting IR spectra of each bacteria from different parts of GNA. The employment of GNA provided robust IR spectra with high reproducibility and signal-to-noise ratio. For the comparison, IR spectra of each bacteria were collected from aluminum foil and a smooth gold surface (SGS). No or very low IR spectra were observed in comparison to the GNA platform for these substrates. Unsupervised (PCA, HCA) and supervised (SIMCA, LDA, and SVM classification) machine learning analysis of bacteria spectra obtained from GNA substrate indicated that all bacteria samples can be detected and identified without using a label-containing biosensor, in a fast and simple manner.

Prediction of good neurological recovery after out-of-hospital cardiac arrest: A machine learning analysis

BACKGROUND

This study aimed to train, validate and compare predictive models that use machine learning analysis for good neurological recovery in OHCA patients.

METHODS

Adult OHCA patients who had a presumed cardiac etiology and a sustained return of spontaneous circulation between 2013 and 2016 were analyzed; 80% of the individuals were analyzed for training and 20% were analyzed for validation. We developed using six machine learning algorithms: logistic regression (LR), extreme gradient boosting (XGB), support vector machine, random forest, elastic net (EN), and neural network. Variables that could be obtained within 24 hours of the emergency department visit were used. The area under the receiver operation curve (AUROC) was calculated to assess the discrimination. Calibration was assessed by the Hosmer-Lemeshow test. Reclassification was assessed by using the continuous net reclassification index (NRI).

RESULTS

A total of 19,860 OHCA patients were included in the analysis. Of the 15,888 patients in the training group, 2228 (14.0%) had a good neurological recovery; of the 3972 patients in the validation group, 577 (14.5%) had a good neurological recovery. The LR, XGB, and EN models showed the highest discrimination powers (AUROC (95% CI)) of 0.949 (0.941-0.957) for all), and all three models were well calibrated (Hosmer-Lemeshow test: p >0.05). The XGB model reclassified patients according to their true risk better than the LR model (NRI: 0.110), but the EN model reclassified patients worse than the LR model (NRI: -1.239).

CONCLUSION

The best performing machine learning algorithm was the XGB and LR algorithm.

Multivariate resting-state functional connectivity predicts responses to real and sham acupuncture treatment in chronic low back pain

Despite the high prevalence and socioeconomic impact of chronic low back pain (cLBP), treatments for cLBP are often unsatisfactory, and effectiveness varies widely across patients. Recent neuroimaging studies have demonstrated abnormal resting-state functional connectivity (rsFC) of the default mode, salience, central executive, and sensorimotor networks in chronic pain patients, but their role as predictors of treatment responsiveness has not yet been explored. In this study, we used machine learning approaches to test if pre-treatment rsFC can predict responses to both real and sham acupuncture treatments in cLBP patients. Fifty cLBP patients participated in 4 weeks of either real (N = 24, age = 39.0 ± 12.6, 16 females) or sham acupuncture (N = 26, age = 40.0 ± 13.7, 15 females) treatment in a single-blinded trial, and a resting-state fMRI scan prior to treatment was used in data analysis. Both real and sham acupuncture can produce significant pain reduction, with those receiving real treatment experiencing greater pain relief than those receiving sham treatment. We found that pre-treatment rsFC could predict symptom changes with up to 34% and 29% variances for real and sham treatment, respectively, and the rsFC characteristics that were significantly predictive for real and sham treatment differed. These results suggest a potential way to predict treatment responses and may facilitate the development of treatment plans that optimize time, cost, and available resources.