Feature importance: Opening a soil-transmitted helminth machine learning model via SHAP

Spatial patterns of intestinal parasite infections among children and adolescents in some indigenous communities in Argentina

Argentina has a heterogeneous prevalence of infections by intestinal parasites (IPs), with the north in the endemic area, especially for soil-transmitted helminths (STHs). We analyzed the spatial patterns of these infections in the city of Tartagal, Salta province, by an observational, correlational, and cross-sectional study in children and adolescents aged 1 to 15 years from native communities. One fecal sample per individual was collected to detect IPs using various diagnostic techniques: Telemann sedimentation, Baermann culture, and Kato-Katz. Moran's global and local indices were applied together with SaTScan to assess the spatial distribution, with a focus on cluster detection. The extreme gradient boosting (XGBoost) machine-learning model was used to predict the presence of IPs and their transmission pathways. Based on the analysis of 572 fecal samples, a prevalence of 78.3% was found. The most frequent parasite was Giardia lamblia (30.9%). High- and low-risk clusters were observed for most species, distributed in an east-west direction and polarized in two large foci, one near the city of Tartagal and the other in the km 6 community. Spatial XGBoost models were obtained based on distances with a minimum median accuracy of 0.69. Different spatial patterns reflecting the mechanisms of transmission were noted. The distribution of the majority of the parasites studied was aligned in a westerly direction close to the city, but the STH presence was higher in the km 6 community, toward the east. The purely spatial analysis provides a different and complementary overview for the detection of vulnerable hotspots and strategic intervention. Machine-learning models based on spatial variables explain a large percentage of the variability of the IPs.

Machine Learning Supported the Modified Gustafson's Criteria for Dental Age Estimation in Southwest China

Adult age estimation is one of the most challenging problems in forensic science and physical anthropology. In this study, we aimed to develop and evaluate machine learning (ML) methods based on the modified Gustafson's criteria for dental age estimation. In this retrospective study, a total of 851 orthopantomograms were collected from patients aged 15 to 40 years old. The secondary dentin formation (SE), periodontal recession (PE), and attrition (AT) of four mandibular premolars were analyzed according to the modified Gustafson's criteria. Ten ML models were generated and compared for age estimation. The partial least squares regressor outperformed other models in males with a mean absolute error (MAE) of 4.151 years. The support vector regressor (MAE = 3.806 years) showed good performance in females. The accuracy of ML models is better than the single-tooth model provided in the previous studies (MAE = 4.747 years in males and MAE = 4.957 years in females). The Shapley additive explanations method was used to reveal the importance of the 12 features in ML models and found that AT and PE are the most influential in age estimation. The findings suggest that the modified Gustafson method can be effectively employed for adult age estimation in the southwest Chinese population. Furthermore, this study highlights the potential of machine learning models to assist experts in achieving accurate and interpretable age estimation.

A European-scale analysis reveals the complex roles of anthropogenic and climatic factors in driving the initiation of large wildfires

Analysing wildfire initiation patterns and identifying their primary drivers is essential for the development of more efficient fire prevention strategies. However, such analyses have traditionally been conducted at local or national scales, hindering cross-border comparisons and the formulation of broad-scale policy initiatives. In this study, we present an analysis of the spatial variability of wildfire initiations across Europe, focusing specifically on moderate to large fires (> 100 ha), and examining the influence of both human and climatic factors on initiation areas. We estimated drivers of fire initiation using machine learning algorithms, specifically Random Forest (RF), covering the majority of the European territory (referred to as the "ET scale"). The models were trained using data on fire initiations extracted from a satellite burned area product, comprising fires occurring from 2001 to 2019. We developed six RF models: three considering all fires larger than 100 ha, and three focused solely on the largest events (> 1000 ha). Models were developed using climatic and human predictors separately, as well as both types of predictors mixed together. We found that both climatic and mixed models demonstrated moderate predictive capacity, with AUC values ranging from 79 % to 81 %; while models based only on human variables have had poor predictive capacity (AUC of 60 %). Feature importance analysis, using Shapley Additive Explanations (SHAP), allowed us to assess the primary drivers of wildfire initiations across the European Territory. Aridity and evapotranspiration had the strongest effect on fire initiation. Among human variables, population density and aging had considerable effects on fire initiation, the former with a strong effect in mixed models estimating large fires, while the latter had a more important role in the prediction of very large fires. Distance to roads and forest-agriculture interfaces were also relevant in some initiation models. A better understanding of drivers of main fire events should help designing European forest fire management strategies, particularly in the light of growing importance of climate change, as it would affect both fire severity and areas at risk. Factors of fire initiation should also be part of a comprehensive approach for fire risk assessment, reduction and adaption, contributing to more effective wildfire management and mitigation across the continent.

Identification of key immune cells infiltrated in lung adenocarcinoma microenvironment and their related long noncoding RNA

LncRNA associated with immune cell infiltration in tumor microenvironment (TME) may be a potential therapeutic target for lung adenocarcinoma. We established a machine learning (ML) model based on 3896 samples characterized by the degree of immune cell infiltration, and further screened the key lncRNA. In vitro experiments were applied to validate the prediction. Treg is the key immune cell in the TME of lung adenocarcinoma, and the degree of infiltration is negatively correlated with the prognosis. PCBP1-AS1 may affect the infiltration of Tregs by regulating the TGF-β pathway, which is a potential predictor of clinical response to immunotherapy. PCBP1-AS1 regulates cell proliferation, cell cycle, invasion, migration, and apoptosis in lung adenocarcinoma. The results of clinical sample staining and in vitro experiments showed that PCBP1-AS1 was negatively correlated with Treg infiltration and TGF-β expression. Tregs and related lncRNA PCBP1-AS1 can be used as targets for the diagnosis and treatment of lung adenocarcinoma.

Machine learning-based overall and cancer-specific survival prediction of M0 penile squamous cell carcinoma：A population-based retrospective study

Background

Penile cancer is a rare tumor and few studies have focused on the prognosis of M0 penile squamous cell carcinoma (PSCC). This retrospective study aimed to identify independent prognostic factors and construct predictive models for the overall survival (OS) and cancer-specific survival (CSS) of patients with M0 PSCC.

Methods

Data was extracted from the Surveillance, Epidemiology, and End Results database for patients diagnosed with malignant penile cancer. Eligible patients with M0 PSCC were selected according to predetermined inclusion and exclusion criteria. These patients were then divided into a training set, a validation set, and a test set. Univariate and multivariate COX regression analyses were initially performed to identify independent prognostic factors for OS and CSS in M0 PSCC patients. Subsequently, traditional and machine learning prognostic models, including random survival forest (RSF), COX, gradient boosting, and component-wise gradient boosting modelling, were constructed using the scikit-survival framework. The performance of each model was assessed by calculating time-dependent area under curve (AUC), C-index, and integrated Brier score (IBS), ultimately identifying the model with the highest performance. Finally, the Shapley additive explanation (SHAP) value, feature importance, and cumulative rates analyses were used to further estimate the selected model.

Results

A total of 2, 446 patients were included in our study. Cox regression analyses demonstrated that age, N stage, and tumor size were predictors of OS, while the N stage, tumor size, surgery, and residential area were predictors of CSS. The RSF and COX models had a higher time-independent AUC and C-index, and lower IBS value than other models in OS and CSS prediction. Feature importance analysis revealed the N stage as a common significant feature for predicting M0 PSCC patients' survival. The SHAP and cumulative rate analyses demonstrated that the selected models can effectively evaluate the prognosis of M0 PSCC patients.

Conclusion

In M0 PSCC patients, age, N stage, and tumor size were predictors of OS. In addition, the N stage, tumor size, surgery, and residential area were predictors of CSS. The machine learning-based RSF and COX models effectively predicted the prognosis of M0 PSCC patients.

Long-term gridded land evapotranspiration reconstruction using Deep Forest with high generalizability

Previous datasets have limitations in generalizing evapotranspiration (ET) across various land cover types due to the scarcity and spatial heterogeneity of observations, along with the incomplete understanding of underlying physical mechanisms as a deeper contributing factor. To fill in these gaps, here we developed a global Highly Generalized Land (HG-Land) ET dataset at 0.5° spatial resolution with monthly values covering the satellite era (1982-2018). Our approach leverages the power of a Deep Forest machine-learning algorithm, which ensures good generalizability and mitigates overfitting by minimizing hyper-parameterization. Model explanations are further provided to enhance model transparency and gain new insights into the ET process. Validation conducted at both the site and basin scales attests to the dataset's satisfactory accuracy, with a pronounced emphasis on the Northern Hemisphere. Furthermore, we find that the primary driver of ET predictions varies across different climatic regions. Overall, the HG-Land ET, underpinned by the interpretability of the machine-learning model, emerges as a validated and generalized resource catering to scientific research and various applications.

Predicting risk of obesity in overweight adults using interpretable machine learning algorithms

Objective

To screen for predictive obesity factors in overweight populations using an optimal and interpretable machine learning algorithm.

Methods

This cross-sectional study was conducted between June 2011 and January 2012. The participants were randomly selected using a simple random sampling technique. Seven commonly used machine learning methods were employed to construct obesity risk prediction models. A total of 5,236 Chinese participants from Ningde City, Fujian Province, Southeast China, participated in this study. The best model was selected through appropriate verification and validation and suitably explained. Subsequently, a minimal set of significant predictors was identified. The Shapley additive explanation force plot was used to illustrate the model at the individual level.

Results

Machine learning models for predicting obesity have demonstrated strong performance, with CatBoost emerging as the most effective in both model validity and net clinical benefit. Specifically, the CatBoost algorithm yielded the highest scores, registering 0.91 in the training set and an impressive 0.83 in the test set. This was further corroborated by the area under the curve (AUC) metrics, where CatBoost achieved 0.95 for the training set and 0.87 for the test set. In a rigorous five-fold cross-validation, the AUC for the CatBoost model ranged between 0.84 and 0.91, with an average AUC of ROC at 0.87 ± 0.022. Key predictors identified within these models included waist circumference, hip circumference, female gender, and systolic blood pressure.

Conclusion

CatBoost may be the best machine learning method for prediction. Combining Shapley's additive explanation and machine learning methods can be effective in identifying disease risk factors for prevention and control.

Disulfidptosis-associated lncRNAs predict breast cancer subtypes

Disulfidptosis is a newly discovered mode of cell death. However, its relationship with breast cancer subtypes remains unclear. In this study, we aimed to construct a disulfidptosis-associated breast cancer subtype prediction model. We obtained 19 disulfidptosis-related genes from published articles and performed correlation analysis with lncRNAs differentially expressed in breast cancer. We then used the random forest algorithm to select important lncRNAs and establish a breast cancer subtype prediction model. We identified 132 lncRNAs significantly associated with disulfidptosis (FDR < 0.01, |R|> 0.15) and selected the first four important lncRNAs to build a prediction model (training set AUC = 0.992). The model accurately predicted breast cancer subtypes (test set AUC = 0.842). Among the key lncRNAs, LINC02188 had the highest expression in the Basal subtype, while LINC01488 and GATA3-AS1 had the lowest expression in Basal. In the Her2 subtype, LINC00511 had the highest expression level compared to other key lncRNAs. GATA3-AS1 had the highest expression in LumA and LumB subtypes, while LINC00511 had the lowest expression in these subtypes. In the Normal subtype, GATA3-AS1 had the highest expression level compared to other key lncRNAs. Our study also found that key lncRNAs were closely related to RNA methylation modification and angiogenesis (FDR < 0.05, |R|> 0.1), as well as immune infiltrating cells (P.adj < 0.01, |R|> 0.1). Our random forest model based on disulfidptosis-related lncRNAs can accurately predict breast cancer subtypes and provide a new direction for research on clinical therapeutic targets for breast cancer.

Intestinal parasitic infections in a community from Pampa del Indio, Chaco (Argentina) and their association with socioeconomic and environmental factors

Neglected tropical diseases are a group of 20 disabling diseases, which, in particular, are the most common chronic infections in the most vulnerable people. This study aimed to characterize the infection by intestinal parasites (IPs) in dwellings from a peri-urban neighborhood in Pampa del Indio, Chaco (Argentina), and its association with socioeconomic and environmental variables. Single stool samples were collected from all individuals older than 1 year through household visits and processed using coprological sedimentation and flotation techniques. Standardized questionnaires were used at the household level to collect socio-economic information. Environmental variables were obtained from the Planetscope image, Landsat 8 images and remote sensors, while land-use layers were obtained through the use of a maximum likelihood algorithm. Stool samples were provided by 314 individuals. The prevalence of IPs found was 30.6% (n = 96), with a predominance of Giardia lamblia (12.7%, n = 40) and Hymenolepis nana (7.6%, n = 24). The only soil-transmitted helminth found was Strongyloides stercoralis with a 2.5% prevalence (n = 8). Individuals of adult age (> 18 years) were 0.65 times less likely to present parasitic infections with respect to children and adolescents. The only environmental variable that was closely associated with the presence of IPs, was the Normalized Difference Water Index (NDWI), a measure of humidity; being higher around houses with positive individuals. Most of the IPs found in this study were of water-borne transmission and those transmitted directly from person-to-person, therefore fecal contamination is present. We believe that the low prevalence of STH in this area, which requires a passage through the soil, is related to the environmental characteristics, which are unsuitable for the development/permanence of the infective stages of these parasites. The geospatial data and tools used herein proved to be useful for the study of the relationship between the different factors that influence the presence of IPs in a community, from an eco-health approach.

An application based on bioinformatics and machine learning for risk prediction of sepsis at first clinical presentation using transcriptomic data

Background: Linking genotypic changes to phenotypic traits based on machine learning methods has various challenges. In this study, we developed a workflow based on bioinformatics and machine learning methods using transcriptomic data for sepsis obtained at the first clinical presentation for predicting the risk of sepsis. By combining bioinformatics with machine learning methods, we have attempted to overcome current challenges in predicting disease risk using transcriptomic data.

Methods: High-throughput sequencing transcriptomic data processing and gene annotation were performed using R software. Machine learning models were constructed, and model performance was evaluated by machine learning methods in Python. The models were visualized and interpreted using the Shapley Additive explanation (SHAP) method.

Results: Based on the preset parameters and using recursive feature elimination implemented via machine learning, the top 10 optimal genes were screened for the establishment of the machine learning models. In a comparison of model performance, CatBoost was selected as the optimal model. We explored the significance of each gene in the model and the interaction between each gene through SHAP analysis.

Conclusion: The combination of CatBoost and SHAP may serve as the best-performing machine learning model for predicting transcriptomic and sepsis risks. The workflow outlined may provide a new approach and direction in exploring the mechanisms associated with genes and sepsis risk.

Big Geospatial Data or Geospatial Big Data? A Systematic Narrative Review on the Use of Spatial Data Infrastructures for Big Geospatial Sensing Data in Public Health

Background: Often combined with other traditional and non-traditional types of data, geospatial sensing data have a crucial role in public health studies. We conducted a systematic narrative review to broaden our understanding of the usage of big geospatial sensing, ancillary data, and related spatial data infrastructures in public health studies. Methods: English-written, original research articles published during the last ten years were examined using three leading bibliographic databases (i.e., PubMed, Scopus, and Web of Science) in April 2022. Study quality was assessed by following well-established practices in the literature. Results: A total of thirty-two articles were identified through the literature search. We observed the included studies used various data-driven approaches to make better use of geospatial big data focusing on a range of health and health-related topics. We found the terms ‘big’ geospatial data and geospatial ‘big data’ have been inconsistently used in the existing geospatial sensing studies focusing on public health. We also learned that the existing research made good use of spatial data infrastructures (SDIs) for geospatial sensing data but did not fully use health SDIs for research. Conclusions: This study reiterates the importance of interdisciplinary collaboration as a prerequisite to fully taking advantage of geospatial big data for future public health studies.