Should one go for individual- or group-level brain parcellations? A deep-phenotyping benchmark

The analysis and understanding of brain characteristics often require considering region-level information rather than voxel-sampled data. Subject-specific parcellations have been put forward in recent years, as they can adapt to individual brain organization and thus offer more accurate individual summaries than standard atlases. However, the price to pay for adaptability is the lack of group-level consistency of the data representation. Here, we investigate whether the good representations brought by individualized models are merely an effect of circular analysis, in which individual brain features are better represented by subject-specific summaries, or whether this carries over to new individuals, i.e., whether one can actually adapt an existing parcellation to new individuals and still obtain good summaries in these individuals. For this, we adapt a dictionary-learning method to produce brain parcellations. We use it on a deep-phenotyping dataset to assess quantitatively the patterns of activity obtained under naturalistic and controlled-task-based settings. We show that the benefits of individual parcellations are substantial, but that they vary a lot across brain systems.

Accelerating the Discovery and Design of Antimicrobial Peptides with Artificial Intelligence

Peptides modulate many processes of human physiology targeting ion channels, protein receptors, or enzymes. They represent valuable starting points for the development of new biologics against communicable and non-communicable disorders. However, turning native peptide ligands into druggable materials requires high selectivity and efficacy, predictable metabolism, and good safety profiles. Machine learning models have gradually emerged as cost-effective and time-saving solutions to predict and generate new proteins with optimal properties. In this chapter, we will discuss the evolution and applications of predictive modeling and generative modeling to discover and design safe and effective antimicrobial peptides. We will also present their current limitations and suggest future research directions, applicable to peptide drug design campaigns.

One-step analysis of growth kinetics of mesophilic Bacillus cereus in liquid egg yolk during treatment with phospholipase A2: Model development and validation

Liquid egg yolk (LEY) is often treated with phospholipase A2 (PLA2) to improve its emulsifying capacity and thermal stability. However, this process may allow certain pathogens to grow. The objective of this study was to evaluate the growth kinetics of mesophilic Bacillus cereus in LEY during PLA2 treatment. Samples, inoculated with B. cereus vegetative cells, were incubated isothermally at different temperatures between 9 and 50 °C to observe the bacterial growth and survival. Under the observation conditions, bacterial growth occurred between 15 and 48 °C, but not at 9 and 50 °C. The growth curves were analyzed using the USDA IPMP-Global Fit, with the no-lag phase model as the primary model in combination with either the cardinal temperatures model (CTM) or the Huang square-root model (HSRM) as the secondary model. While similar maximum growth temperatures (Tmax) were determined (48.4 °C for HSRM and 48.1 °C for CTM), the minimum growth temperature (Tmin) of the HSRM more accurately described the lower limit (9.26 °C), in contrast to 6.51 °C for CTM, suggesting that the combination of the no-lag phase model and HSRM was more suitable to describe the growth of mesophilic B. cereus in LEY. The root mean square error (RMSE) of model validation and development was <0.5 log CFU/g, indicating the combination of the no-lag phase model and HSRM could predict the growth of mesophilic B. cereus in LEY during PLA2 treatment. The results of this study may allow the food industry to choose a suitable temperature for PLA2 treatment of LEY to prevent the growth of mesophilic B. cereus.

Forecasting freshwater cyanobacterial harmful algal blooms for Sentinel-3 satellite resolved U.S. lakes and reservoirs

This forecasting approach may be useful for water managers and associated public health managers to predict near-term future high-risk cyanobacterial harmful algal blooms (cyanoHAB) occurrence. Freshwater cyanoHABs may grow to excessive concentrations and cause human, animal, and environmental health concerns in lakes and reservoirs. Knowledge of the timing and location of cyanoHAB events is important for water quality management of recreational and drinking water systems. No quantitative tool exists to forecast cyanoHABs across broad geographic scales and at regular intervals. Publicly available satellite monitoring has proven effective in detecting cyanobacteria biomass near-real time within the United States. Weekly cyanobacteria abundance was quantified from the Ocean and Land Colour Instrument (OLCI) onboard the Sentinel-3 satellite as the response variable. An Integrated Nested Laplace Approximation (INLA) hierarchical Bayesian spatiotemporal model was applied to forecast World Health Organization (WHO) recreation Alert Level 1 exceedance >12 μg L-1 chlorophyll-a with cyanobacteria dominance for 2192 satellite resolved lakes in the United States across nine climate zones. The INLA model was compared against support vector classifier and random forest machine learning models; and Dense Neural Network, Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Gneural Network (GNU) neural network models. Predictors were limited to data sources relevant to cyanobacterial growth, readily available on a weekly basis, and at the national scale for operational forecasting. Relevant predictors included water surface temperature, precipitation, and lake geomorphology. Overall, the INLA model outperformed the machine learning and neural network models with prediction accuracy of 90% with 88% sensitivity, 91% specificity, and 49% precision as demonstrated by training the model with data from 2017 through 2020 and independently assessing predictions with data from the 2021 calendar year. The probability of true positive responses was greater than false positive responses and the probability of true negative responses was less than false negative responses. This indicated the model correctly assigned lower probabilities of events when they didn't exceed the WHO Alert Level 1 threshold and assigned higher probabilities when events did exceed the threshold. The INLA model was robust to missing data and unbalanced sampling between waterbodies.

Geographical origin identification of mandarin fruits by analyzing fingerprint signatures based on multielemental composition

Given rising traders and consumers concerns, the global food industry is increasingly demanding authentic and traceable products. Consequently, there is a heightened focus on verifying geographical authenticity as food quality assurance. In this work, we assessed pattern recognition approaches based on elemental predictors to discern the provenance of mandarin juices from three distinct citrus-producing zones located in the Northeast region of Argentina. A total of 202 samples originating from two cultivars were prepared through microwave-assisted acid digestion and analyzed by microwave plasma atomic emission spectroscopy (MP-AES). Later, we applied linear discriminant analysis (LDA), k-nearest neighbor (k-NN), support vector machine (SVM), and random forest (RF) to the element data obtained. SVM accomplished the best classification performance with a 95.1% success rate, for which it was selected for citrus samples authentication. The proposed method highlights the capability of mineral profiles in accurately identifying the genuine origin of mandarin juices. By implementing this model in the food supply chain, it can prevent mislabeling fraud, thereby contributing to consumer protection.

Gut microbiome dynamics and associations with mortality in critically ill patients

BACKGROUND

Critical illness and care within the intensive care unit (ICU) leads to profound changes in the composition of the gut microbiome. The impact of such changes on the patients and their subsequent disease course remains uncertain. We hypothesized that specific changes in the gut microbiome would be more harmful than others, leading to increased mortality in critically ill patients.

METHODS

This was a prospective cohort study of critically ill adults in the ICU. We obtained rectal swabs from 52 patients and assessed the composition the gut microbiome using 16 S rRNA gene sequencing. We followed patients throughout their ICU course and evaluated their mortality rate at 28 days following admission to the ICU. We used selbal, a machine learning method, to identify the balance of microbial taxa most closely associated with 28-day mortality.

RESULTS

We found that a proportional ratio of four taxa could be used to distinguish patients with a higher risk of mortality from patients with a lower risk of mortality (p = .02). We named this binarized ratio our microbiome mortality index (MMI). Patients with a high MMI had a higher 28-day mortality compared to those with a low MMI (hazard ratio, 2.2, 95% confidence interval 1.1-4.3), and remained significant after adjustment for other ICU mortality predictors, including the presence of the acute respiratory distress syndrome (ARDS) and the Acute Physiology and Chronic Health Evaluation (APACHE II) score (hazard ratio, 2.5, 95% confidence interval 1.4-4.7). High mortality was driven by taxa from the Anaerococcus (genus) and Enterobacteriaceae (family), while lower mortality was driven by Parasutterella and Campylobacter (genera).

CONCLUSIONS

Dysbiosis in the gut of critically ill patients is an independent risk factor for increased mortality at 28 days after adjustment for clinically significant confounders. Gut dysbiosis may represent a potential therapeutic target for future ICU interventions.

Predicting the potential nationwide distribution of the snail vector, Oncomelania hupensis quadrasi, in the Philippines using the MaxEnt algorithm

Schistosomiasis remains a major public health concern affecting approximately 12 million people in the Philippines due to inadequate information about the disease and limited prevention and control efforts. Schistosoma japonicum, one of the causative agents of the disease, requires an amphibious snail Oncomelania hupensis quadrasi (O. h. quadrasi) to complete its life cycle. Using the geographical information system (GIS) and maximum entropy (MaxEnt) algorithm, this study aims to predict the potential high-risk habitats of O. h. quadrasi driven by environmental factors in the Philippines. Based on the bioclimatic determinants, a very high-performance model was generated (AUC = 0.907), with the mean temperature of the driest quarter (25.3%) contributing significantly to the prevalence of O. h. quadrasi. Also, the snail vector has a high focal distribution, preferring areas with a pronounced wet season and high precipitation throughout the year. However, the findings provided evidence for snail adaptation to different environmental conditions. High suitability of snail habitats was found in Quezon, Camarines Norte, Camarines Sur, Albay, Sorsogon, Northern Samar, Eastern Samar, Leyte, Bohol, Surigao del Norte, Surigao del Sur, Agusan del Norte, Davao del Norte, North Cotabato, Lanao del Norte, Misamis Occidental, and Zamboanga del Sur. Furthermore, snail habitat establishment includes natural and man-made waterlogged areas, with the progression of global warming and climate change predicted to be drivers of increasing schistosomiasis transmission zones in the country.

Developing a multi-institutional nomogram for assessing lung cancer risk in patients with 5-30 mm pulmonary nodules: a retrospective analysis

Background

The diagnosis of benign and malignant solitary pulmonary nodules based on personal experience has several limitations. Therefore, this study aims to establish a nomogram for the diagnosis of benign and malignant solitary pulmonary nodules using clinical information and computed tomography (CT) results.

Methods

Retrospectively, we collected clinical and CT characteristics of 1,160 patients with pulmonary nodules in Guang'an People's Hospital and the hospital affiliated with North Sichuan Medical College between 2019 and 2021. Among these patients, data from 773 patients with pulmonary nodules were used as the training set. We used the least absolute shrinkage and selection operator (LASSO) to optimize clinical and imaging features and performed a multivariate logistic regression to identify features with independent predictive ability to develop the nomogram model. The area under the receiver operating characteristic curve (AUC), C-index, decision curve analysis, and calibration plot were used to evaluate the performance of the nomogram model in terms of predictive ability, discrimination, calibration, and clinical utility. Finally, data from 387 patients with pulmonary nodules were utilized for validation.

Results

In the training set, the predictors for the nomogram were gender, density of the nodule, nodule diameter, lobulation, calcification, vacuole, vascular convergence, bronchiole, and pleural traction, selected through LASSO and logistic regression analysis. The resulting model had a C-index of 0.842 (95% CI [0.812-0.872]) and AUCs of 0.842 (95% CI [0.812-0.872]). In the validation set, the C-index was 0.856 (95% CI [0.811-0.901]), and the AUCs were 0.844 (95% CI [0.797-0.891]). Results from the calibration curve and clinical decision curve analyses indicate that the nomogram has a high fit and clinical benefit in both the training and validation sets.

Conclusion

The establishment of a nomogram for predicting the benign or malignant diagnosis of solitary pulmonary nodules by this study has shown good efficacy. Such a nomogram may help to guide the diagnosis, follow-up, and treatment of patients.

Structural and Functional Brain Patterns Predict Formal Thought Disorder's Severity and Its Persistence in Recent-Onset Psychosis: Results From the PRONIA Study

BACKGROUND

Formal thought disorder (FThD) is a core feature of psychosis, and its severity and long-term persistence relates to poor clinical outcomes. However, advances in developing early recognition and management tools for FThD are hindered by a lack of insight into the brain-level predictors of FThD states and progression at the individual level.

METHODS

Two hundred thirty-three individuals with recent-onset psychosis were drawn from the multisite European Prognostic Tools for Early Psychosis Management study. Support vector machine classifiers were trained within a cross-validation framework to separate two FThD symptom-based subgroups (high vs. low FThD severity), using cross-sectional whole-brain multiband fractional amplitude of low frequency fluctuations, gray matter volume and white matter volume data. Moreover, we trained machine learning models on these neuroimaging readouts to predict the persistence of high FThD subgroup membership from baseline to 1-year follow-up.

RESULTS

Cross-sectionally, multivariate patterns of gray matter volume within the salience, dorsal attention, visual, and ventral attention networks separated the FThD severity subgroups (balanced accuracy [BAC] = 60.8%). Longitudinally, distributed activations/deactivations within all fractional amplitude of low frequency fluctuation sub-bands (BACslow-5 = 73.2%, BACslow-4 = 72.9%, BACslow-3 = 68.0%), gray matter volume patterns overlapping with the cross-sectional ones (BAC = 62.7%), and smaller frontal white matter volume (BAC = 73.1%) predicted the persistence of high FThD severity from baseline to follow-up, with a combined multimodal balanced accuracy of BAC = 77%.

CONCLUSIONS

We report the first evidence of brain structural and functional patterns predictive of FThD severity and persistence in early psychosis. These findings open up avenues for the development of neuroimaging-based diagnostic, prognostic, and treatment options for the early recognition and management of FThD and associated poor outcomes.

Gaussian Process-based prediction of memory performance and biomarker status in ageing and Alzheimer's disease-A systematic model evaluation

Neuroimaging markers based on Magnetic Resonance Imaging (MRI) combined with various other measures (such as genetic covariates, biomarkers, vascular risk factors, neuropsychological tests etc.) might provide useful predictions of clinical outcomes during the progression towards Alzheimer's disease (AD). The use of multiple features in predictive frameworks for clinical outcomes has become increasingly prevalent in AD research. However, many studies do not focus on systematically and accurately evaluating combinations of multiple input features. Hence, the aim of the present work is to explore and assess optimal combinations of various features for MR-based prediction of (1) cognitive status and (2) biomarker positivity with a multi-kernel learning Gaussian process framework. The explored features and parameters included (A) combinations of brain tissues, modulation, smoothing, and image resolution; (B) incorporating demographics & clinical covariates; (C) the impact of the size of the training data set; (D) the influence of dimensionality reduction and the choice of kernel types. The approach was tested in a large German cohort including 959 subjects from the multicentric longitudinal study of cognitive impairment and dementia (DELCODE). Our evaluation suggests the best prediction of memory performance was obtained for a combination of neuroimaging markers, demographics, genetic information (ApoE4) and CSF biomarkers explaining 57% of outcome variance in out-of-sample predictions. The highest performance for Aβ42/40 status classification was achieved for a combination of demographics, ApoE4, and a memory score while usage of structural MRI further improved the classification of individual patient's pTau status.

Comparison of linear and non-linear decision boundaries to detect feedlot bloat using intensive data collection systems on Angus × Hereford steers

Ruminal tympany (bloat) has long been an issue for large and small livestock operations. Though improvements in feedlot management practices have reduced its occurrence, it is still highly prevalent and is known to detrimentally affect animal performance, welfare, and in many instances, lead to animal death. Current decision support systems and diet formulation software omit the inclusion of bloat prediction based on animal performance. Here, we aim to predict bloat incidence in implanted and non-implanted feedlot steers from performance data comparing linear (LDB) and non-linear decision boundaries. Eighteen crossbred Angus × Hereford steers: BW (491.13 ± 25.78 kg) and age (12 ± 1 mo) were randomly distributed into implanted and non-implanted treatments. All animals were randomly assigned to one of two pens fit with automated monitoring systems for BW, freshwater intake, and water intake behavior: water intake event visit, no water intake event visit (NWIE), and time spent drinking. DM intake (DMI) was individually recorded from all animals through the Calan Gate system for 135 d (30 d adaptation, 105 d experimental diet). Incidences of bloat were recorded as bloat instances regardless of severity to ensure that early onset detection of bloat was recorded and properly identified in predictive models. Logistic regression with a binomial distribution and a logit link function was utilized to predict the incidences of bloat through LDB. Feature selection and penalization of coefficients were explored through L1 (sum of absolute values) and L2 (sum of squares) penalization to avoid overfitting of models. Additional NLDB and a non-parametric LDB are examined for prediction. Accuracy, specificity, and sensitivity were high for the models reported. No significant differences were observed between LDB and NLDB, with the highest specificity (predicting bloat) value of 0.820 for stepwise feature selection algorithms, and a value of 0.832 for the artificial neural network. Highest accuracy was 0.829 for ridge regression, and 0.847 for the random forest with hyperparameter tuning. DM intake, BW, and NWIE were the three most important variables for the prediction of feedlot bloat showing clear drops in DMI and BW and increases in NWIE when animals bloated. The lack of difference in predictive performance between LDB and NLDB highlights the often-overlooked concept that machine learning algorithms are not always the only/best modeling technique. Additionally, the models reported herein carry acceptable predictive performance for inclusion into management decisions that reduce bloat incidences in feedlot cattle.

Covariate dependent Markov chains constructed with gradient boost modeling can effectively generate long-term predictions of obesity trends

IMPORTANCE

The prevalence of obesity among United States adults has increased from 30.5% in 1999 to 41.9% in 2020. However, despite the recognition of long-term weight gain as an important public health issue, there is a paucity of studies studying the long-term weight gain and building models for long-term projection.

METHODS

A retrospective, cross-sectional cohort study using the publicly available National Health and Nutrition Examination Survey (NHANES 2017-2020) was conducted in patients who completed the weight questionnaire and had accurate data for both weight at time of survey and weight ten years ago. Multistate gradient boost modeling classifiers were used to generate covariate dependent transition matrices and Markov chains were utilized for multistate modeling.

RESULTS

Of the 6146 patients that met the inclusion criteria, 3024 (49%) of patients were male and 3122 (51%) of patients were female. There were 2252 (37%) White patients, 1257 (20%) Hispanic patients, 1636 (37%) Black patients, and 739 (12%) Asian patients. The average BMI was 30.16 (SD = 7.15), the average weight was 83.67 kilos (SD = 22.04), and the average weight change was a 3.27 kg (SD = 14.97) increase in body weight (Fig. 1). A total of 2411 (39%) patients lost weight, and 3735 (61%) patients gained weight (Table 1). We observed that 87 (1%) of patients were underweight (BMI < 18.5), 2058 (33%) were normal weight (18.5 ≤ BMI < 25), 1376 (22%) were overweight (25 ≤ BMI < 30) and 2625 (43%) were obese (BMI > 30). From analysis of the transitions between normal/underweight, overweight, and obese, we observed that after 10 years, of the patients who were underweight, 65% stayed underweight, 32% became normal weight, 2% became overweight, and 2% became obese. After 10 years, of the patients who were normal weight, 3% became underweight, 78% stayed normal weight, 17% became overweight, and 2% became obese. Of the patients who were overweight, 71% stayed overweight, 0% became underweight, 14% became normal weight, and 15% became obese. Of the patients who were obese, 84% stayed obese, 0% became underweight, 1% became normal weight, and 14% became overweight.

CONCLUSIONS

United States adults are at risk of transitioning from normal weight to becoming overweight or obese. Covariate dependent Markov chains constructed with gradient boost modeling can effectively generate long-term predictions.

Integrated single-dose kinome profiling data is predictive of cancer cell line sensitivity to kinase inhibitors

Protein kinase activity forms the backbone of cellular information transfer, acting both individually and as part of a broader network, the kinome. Their central role in signaling leads to kinome dysfunction being a common driver of disease, and in particular cancer, where numerous kinases have been identified as having a causal or modulating role in tumor development and progression. As a result, the development of therapies targeting kinases has rapidly grown, with over 70 kinase inhibitors approved for use in the clinic and over double this number currently in clinical trials. Understanding the relationship between kinase inhibitor treatment and their effects on downstream cellular phenotype is thus of clear importance for understanding treatment mechanisms and streamlining compound screening in therapy development. In this work, we combine two large-scale kinome profiling data sets and use them to link inhibitor-kinome interactions with cell line treatment responses (AUC/IC50). We then built computational models on this data set that achieve a high degree of prediction accuracy (R2 of 0.7 and RMSE of 0.9) and were able to identify a set of well-characterized and understudied kinases that significantly affect cell responses. We further validated these models experimentally by testing predicted effects in breast cancer cell lines and extended the model scope by performing additional validation in patient-derived pancreatic cancer cell lines. Overall, these results demonstrate that broad quantification of kinome inhibition state is highly predictive of downstream cellular phenotypes.

Motor networks, but also non-motor networks predict motor signs in Parkinson's disease

OBJECTIVE

Investigate the brain functional networks associated with motor impairment in people with Parkinson's disease (PD).

BACKGROUND

PD is primarily characterized by motor dysfunction. Resting-state functional connectivity (RsFC) offers a unique opportunity to non-invasively characterize brain function. In this study, we hypothesized that the motor dysfunction observed in people with PD involves atypical connectivity not only in motor but also in higher-level attention networks. Understanding the interaction between motor and non-motor RsFC that are related to the motor signs could provide insights into PD pathophysiology.

METHODS

We used data from 88 people with PD (mean age: 68.2(SD:10), 55 M/33F) coming from 2 cohorts. Motor severity was assessed in practical OFF-medication state, using MDS-UPDRS Part-III motor scores (mean: 49 (SD:10)). RsFC was characterized using an atlas of 384 regions that were grouped into 13 functional networks. Associations between RsFC and motor severity were assessed independently for each RsFC using predictive modeling.

RESULTS

The top 5 % models that predicted the MDS-UPDRS-III motor scores with effect size >0.5 were the connectivity between (1) the somatomotor and Subcortical-Basal-ganglia, (2) somatomotor and Visual and (3) CinguloOpercular (CiO) and language/Ventral attention (Lan/VeA) network pairs.

DISCUSSION

Our findings suggest that, along with motor networks, visual- and attention-related cortical networks are also associated with the motor symptoms of PD. Non-motor networks may be involved indirectly in motor-coordination. When people with PD have deficits in motor networks, more attention may be needed to carry out formerly automatic motor functions, consistent with compensatory mechanisms in parkinsonian movement disorders.

Machine Learning Methods for Endocrine Disrupting Potential Identification Based on Single-Cell Data

Humans are continuously exposed to a variety of toxicants and chemicals which is exacerbated during and after environmental catastrophes such as floods, earthquakes, and hurricanes. The hazardous chemical mixtures generated during these events threaten the health and safety of humans and other living organisms. This necessitates the development of rapid decision-making tools to facilitate mitigating the adverse effects of exposure on the key modulators of the endocrine system, such as the estrogen receptor alpha (ERα), for example. The mechanistic stages of the estrogenic transcriptional activity can be measured with high content/high throughput microscopy-based biosensor assays at the single-cell level, which generates millions of object-based minable data points. By combining computational modeling and experimental analysis, we built a highly accurate data-driven classification framework to assess the endocrine disrupting potential of environmental compounds. The effects of these compounds on the ERα pathway are predicted as being receptor agonists or antagonists using the principal component analysis (PCA) projections of high throughput, high content image analysis descriptors. The framework also combines rigorous preprocessing steps and nonlinear machine learning algorithms, such as the Support Vector Machines and Random Forest classifiers, to develop highly accurate mathematical representations of the separation between ERα agonists and antagonists. The results show that Support Vector Machines classify the unseen chemicals correctly with more than 96% accuracy using the proposed framework, where the preprocessing and the PCA steps play a key role in suppressing experimental noise and unraveling hidden patterns in the dataset.

A comprehensive two-scale model for predicting the oxidizability of fatty acid methyl ester mixtures

The intricate mechanisms of oil thermooxidation and their accurate prediction have long been hampered by the combinatory nature of propagation and termination reactions involving randomly generated radicals. To unravel this complexity, we suggest a two-scale mechanistic description that connects the chemical functions (scale 1) with the molecular carriers of these functions (scale 2). Our method underscores the importance of accounting for cross-reactions between radicals in order to fully comprehend the reactivities in blends. We rigorously tested and validated the proposed two-scale scheme on binary and ternary mixtures of fatty acid methyl esters (FAMEs), yielding three key insights: (1) The abstraction of labile protons hinges on the carrier, defying the conventional focus on hydroperoxyl radical types. (2) Termination reactions between radicals adhere to the geometric mean law, exhibiting symmetric collision ratios. (3) The decomposition of hydroperoxides emerges as a monomolecular process above 80 °C, challenging the established combinatorial paradigm. Applicable across a wide temperature range (80 °C to 200 °C), our findings unlock the production of blends with controlled thermooxidation stability, optimizing the use of vegetable oils across applications: food science, biofuels, and lubricants.

Predicting readmission after bariatric surgery using machine learning

BACKGROUND

While bariatric surgery is an effective method for achieving long-term weight loss, postoperative readmissions are associated with negative clinical outcomes and significant costs.

OBJECTIVES

We aimed to use machine learning (ML) algorithms to predict readmissions and compare results to logistic regression.

SETTING

Hospitals participating in the Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program, United States.

METHODS

Patients who underwent sleeve gastrectomy (SG), Roux-en-Y gastric bypass (RYGB), and biliopancreatic diversion with duodenal switch between 2016 and 2020 were selected from the Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program (MBSAQIP) database. Patient variables reported by the MBSAQIP database were analyzed by ML algorithms random forest (RF), gradient boosting (XGB), and deep neural networks (NN), and the results of the predictive models were compared to logistic regression using area under the receiver operating characteristic curve (AUROC).

RESULTS

Our study included 863,348 patients, of which 39,068 (4.52%) were readmitted. AUROC scores were XGB .785 (95% CI .784-.786), RF .785 (95% CI .784-.785), and NN .754 (95% CI .753-.754), compared with .62 (95% CI .62-.621) for logistic regression (LR) (P < .001). The sensitivity and specificity for XGB, the best performing model, were 73.81% and 70%, compared with 52.94% and 70% for logistic regression. The most important variables were intervention or reoperation prior to discharge, unplanned ICU admission, initial procedure, and the intraoperative transfusion.

CONCLUSIONS

ML demonstrates significant advantages over logistic regression when predicting 30-day readmission following bariatric surgery. With external validation, models could identify the best candidates for early discharge or targeted postdischarge resources.

A predictive assessment of the uranium ore tailings impact on surface water contamination: Case study of the city of Kamianske, Ukraine

In this study, we present an assessment of the uranium ore tailings impact on groundwater and surface water contamination. The radioactive materials were deposited in the tailings storage facility "Dniprovske" (the city of Kamianske, Ukraine) from 1954 to 1968; now it contains about 5.85·106 m3 of hazardous waste on the area of about 76 ha in the floodplain of the Dnipro river. The lack of a proper waterproof screen below deposited tailings and in the earthen dam led to permanent watering of radioactive materials, their leaching and migration in groundwater into the nearest small Konoplianka river. We used the reports on previous site-specific studies conducted in 1999-2016, monitoring results, and the field studies conducted in 2022 with the authors' team participation. The calculations performed with the advection-dispersion model to simulate transport of radionuclides 238U, 230Th, 226Ra and 210Pb through the embankment to the Konoplianka river and dilution relations were compared to the monitoring data of the surface water quality. Among four radionuclides, uranium poses the greatest risks today; the subsurface runoff increases its concentration in the Konoplianka river water by several times over the background value. It is estimated that due to much more intensive sorption in the shallow aquifer, the contribution of 226Ra and 210Pb to the increase in radioactivity of Konoplianka river water is insignificant compared to uranium, whereas the migration front of 230Th has probably not yet reached the riverbank. In the next 50 years the radionuclide fluxes will increase by 1.3-3.7 times for different isotopes, with the uranium subsurface runoff growing at a slower rate than nowadays. These results are of high significance for improving hydrological, hydrogeological, and geotechnical monitoring on this hazardous facility to maintain its radiation safety.

Predictive model for early death risk in pediatric hemophagocytic lymphohistiocytosis patients based on machine learning

Background

Hemophagocytic Lymphohistiocytosis (HLH) is a rare and life-threatening disease in children, with a high early mortality rate. This study aimed to construct machine learning model to predict the risk of early death using clinical indicators at the time of HLH diagnosis.

Methods

This observational cohort study was conducted at the National Clinical Research Center for Child Health and Disease. Data was collected from pediatric HLH patients diagnosed by the HLH-2004 protocol between January 2006 and December 2022. Six machine learning models were constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) to select key clinical indicators for model construction.

Results

The study included 587 pediatric HLH patients, and the early mortality rate was 28.45 %. The logistic and XGBoost model with the best performance after feature screening were selected to predict early death of HLH patients. The logistic model had an AUC of 0.915 and an accuracy of 0.863, while the XGBoost model had an AUC of 0.889 and an accuracy of 0.829. The risk factors most associated with early death were the absence of immunochemotherapy, decreased TC levels, increased BUN and total bilirubin, and prolonged TT. We developed an online calculator tool for predicting the probability of early death in children with HLH.

Conclusions

We developed the first web-based early mortality prediction tool for pediatric HLH to assist clinicians in risk stratification at diagnosis and in developing personalized treatment protocols. This study is registered on the China Clinical Trials Registry platform (ChiCTR2200061315).

A semi-supervised approach to unobtrusively predict abnormality in breathing patterns using hydraulic bed sensor data in older adults aging in place

Shortness of breath is often considered a repercussion of aging in older adults, as respiratory illnesses like COPD1 or respiratory illnesses due to heart-related issues are often misdiagnosed, under-diagnosed or ignored at early stages. Continuous health monitoring using ambient sensors has the potential to ameliorate this problem for older adults at aging-in-place facilities. In this paper, we leverage continuous respiratory health data collected by using ambient hydraulic bed sensors installed in the apartments of older adults in aging-in-place Americare facilities to find data-adaptive indicators related to shortness of breath. We used unlabeled data collected unobtrusively over the span of three years from a COPD-diagnosed individual and used data mining to label the data. These labeled data are then used to train a predictive model to make future predictions in older adults related to shortness of breath abnormality. To pick the continuous changes in respiratory health we make predictions for shorter time windows (60-s). Hence, to summarize each day's predictions we propose an abnormal breathing index (ABI) in this paper. To showcase the trajectory of the shortness of breath abnormality over time (in terms of days), we also propose trend analysis on the ABI quarterly and incrementally. We have evaluated six individual cases retrospectively to highlight the potential and use cases of our approach.

Predicting soil available cadmium by machine learning based on soil properties

Cadmium (Cd) accumulation in edible plant tissues poses a serious threat to human health through the food chain. Assessing the availability of soil Cd is crucial for evaluating associated environmental risks. However, existing experimental methods and traditional models are time-consuming and inefficient. In this study, we developed machine learning models to predict soil available Cd based on soil properties, using a dataset comprising 585 data points covering 585 soils. Traditional machine learning models exhibited prediction values beyond the theoretical range, urging the need for alternative approaches. To address this, different models were tested, and the post-constraint eXtreme Gradient Boosting (XGBoost) model was found to possess the best predictive performance (R2 =0.81) outperform traditional linear regression model in terms of accuracy. Furthermore, we explored the relationship between soil available Cd and wheat grain Cd and rice grain Cd. Linear regression models were developed using 302 data points for wheat and 563 data points for rice. Results demonstrated a significant correlation between soil available Cd and wheat grain Cd (R2 =0.487) as well as rice grain Cd (R2 =0.43).

Trace metal content prediction along an AMD (acid mine drainage)-contaminated stream draining a coal mine using VNIR-SWIR spectroscopy

The current study investigated the use of VNIR-SWIR (visible/near infrared to short-wavelength infrared: 400-2500 nm) spectroscopy for predicting trace metals in overbank sediments collected in the study site. Here, we (i) derived spectral absorption feature parameters (SAFPs) from measured ground spectra for correlation with trace metal (Pb, Cd, As, and Cu) contents in overbank sediments, (ii) built univariate regression models to predict trace metal concentrations using the SAFPs, and (iii) evaluated the predictive capacities of the regression models. The derived SAFPs associated with goethite in overbank sediments were Depth433b, Asym433b, and Width433b, and those associated with kaolinite in overbank sediments were Depth1366b, Asym1366b, Width1366b, Depth2208b, Asym2208b, and Width2208b. Cadmium in the overbank sediments showed the strongest correlations with the goethite-related SAFPs, whereas Pb, As, and Cu showed strong correlations with goethite- and kaolinite-related SAFPs. The best predictive models were obtained for Cu (R2 = 0.73, SEE = 0.15) and Pb (R2 = 0.73, SEE = 0.21), while weaker models were obtained for As (R2 = 0.46, SEE = 0.31) and Cd (R2 = 0.17, SEE = 0.81). The results suggest that trace metals can be predicted indirectly using the SAFPs associated with goethite and kaolinite. This is an important benefit of VNIR-SWIR spectroscopy considering the difficulty in analyzing "trace" metal concentrations, on large scales, using conventional geochemical methods.

Implementation of a validated post-operative opioid nomogram into clinical gynecologic surgery practice: A quality improvement initiative

Objectives

The Gynecologic Oncology Postoperative Opioid use Predictive (GO-POP) calculator is a validated tool to provide evidence-based guidance on post-operative opioid prescribing. The objective of this study was to evaluate the impact of the implementation of GO-POP within an academic Gynecologic Oncology division.

Methods

Two cohorts of patients (pre-implementation and post-implementation) who underwent surgery were compared with reference to GO-POP calculator implementation. All patients were included in the post-implementation group, regardless of GO-POP calculator use. An additional expanded-implementation cohort was used to compare pain control between GO-POP users and non-GO-POP users prospectively. Wilcoxon rank sum tests or ANOVA for continuous variables and Chi-square or Fisher's exact tests were used to categorical variables.

Results

The median number of pills prescribed post-operatively decreased from 15 pills (Q1: 10, Q3: 20) to 10 pills (Q1: 8, Q3: 14.8) after implementation (p < 0.001). In the expanded-implementation cohort (293 patients), 41% patients were prescribed opioids using the GO-POP calculator. An overall median of 10 pills were prescribed with no difference by GO-POP calculator use (p = 0.26). Within the expanded-implementation cohort, refill requests (5% vs 9.2%; p = 0.26), clinician visits (0.8% vs 0.6%, p = 1), ED or urgent care visits (0% vs 2.3%, p = 0.15) and readmissions (0% vs 1.7%, p = 0.27) for pain did not differ between those prescribed opioids with and without the GO-POP calculator.

Conclusions

A 33% reduction in post-operative opioid pills prescribed was seen following implementation of the GO-POP calculator into the Gynecologic Oncology division without increasing post-operative pain metrics or encounters for refill requests.

A computational model of motion sickness dynamics during passive self-motion in the dark

Predicting the time course of motion sickness symptoms enables the evaluation of provocative stimuli and the development of countermeasures for reducing symptom severity. In pursuit of this goal, we present an observer-driven model of motion sickness for passive motions in the dark. Constructed in two stages, this model predicts motion sickness symptoms by bridging sensory conflict (i.e., differences between actual and expected sensory signals) arising from the observer model of spatial orientation perception (stage 1) to Oman's model of motion sickness symptom dynamics (stage 2; presented in 1982 and 1990) through a proposed "Normalized innovation squared" statistic. The model outputs the expected temporal development of human motion sickness symptom magnitudes (mapped to the Misery Scale) at a population level, due to arbitrary, 6-degree-of-freedom, self-motion stimuli. We trained model parameters using individual subject responses collected during fore-aft translations and off-vertical axis of rotation motions. Improving on prior efforts, we only used datasets with experimental conditions congruent with the perceptual stage (i.e., adequately provided passive motions without visual cues) to inform the model. We assessed model performance by predicting an unseen validation dataset, producing a Q2 value of 0.86. Demonstrating this model's broad applicability, we formulate predictions for a host of stimuli, including translations, earth-vertical rotations, and altered gravity, and we provide our implementation for other users. Finally, to guide future research efforts, we suggest how to rigorously advance this model (e.g., incorporating visual cues, active motion, responses to motion of different frequency, etc.).

ConnSearch: A framework for functional connectivity analysis designed for interpretability and effectiveness at limited sample sizes

Functional connectivity studies increasingly turn to machine learning methods, which typically involve fitting a connectome-wide classifier, then conducting post hoc interpretation analyses to identify the neural correlates that best predict a dependent variable. However, this traditional analytic paradigm suffers from two main limitations. First, even if classifiers are perfectly accurate, interpretation analyses may not identify all the patterns expressed by a dependent variable. Second, even if classifiers are generalizable, the patterns implicated via interpretation analyses may not replicate. In other words, this traditional approach can yield effective classifiers while falling short of most neuroscientists' goals: pinpointing the neural correlates of dependent variables. We propose a new framework for multivariate analysis, ConnSearch, which involves dividing the connectome into components (e.g., groups of highly connected regions) and fitting an independent model for each component (e.g., a support vector machine or a correlation-based model). Conclusions about the link between a dependent variable and the brain are based on which components yield predictive models rather than on interpretation analysis. We used working memory data from the Human Connectome Project (N = 50-250) to compare ConnSearch with four existing connectome-wide classification/interpretation methods. For each approach, the models attempted to classify examples as being from the high-load or low-load conditions (binary labels). Relative to traditional methods, ConnSearch identified neural correlates that were more comprehensive, had greater consistency with the WM literature, and better replicated across datasets. Hence, ConnSearch is well-positioned to be an effective tool for functional connectivity research.