Biology subjects

Biswas, A. K.

Publications and source records attributed to Biswas, A. K..

2 recordsLinked to original sources

bioRxiv2024

On Monitoring Brain Health from the Depths of Sleep: Feature Engineering and Machine Learning Insights for Digital Biomarker Development

BackgrounSingle-channel sleep electroencephalography (EEG) is a promising technology for creating cost-effective and widely accessible digital biomarkers for monitoring brain health. Sleep, notable for its numerous connections to brain health, is of particular interest in this context. Indeed, several of the best studied and widely recognized risk factors for neurodegenerative disease are also connected to aspects of sleep physiology, including biological sex, hypertension, diabetes, obesity/metabolic dysregulation, and immune system dysfunction. In this study, we utilize the unique signal characteristics of slow wave sleep (SWS) oscillatory events as features in machine learning models to predict underlying biological processes that are highly relevant to brain health. Our objective is to establish a foundation for algorithms capable of effectively monitoring physiological processes in sleep that directly and indirectly inform brain health using single-channel sleep EEG as a functional metric of brain activity. MethodsUtilizing data from the Cleveland Family Study, we analyzed 726 overnight polysomnography recordings to extract features from slow waves and adjacent oscillatory events. Advanced signal processing and machine learning techniques, including random forest models, were employed to engineer features and predict health-related outcomes such as age, cerebrovascular risk factors, endocrine functions, immune system activity, and sleep apnea. ResultsOur models demonstrated significant predictive capability for several outcomes, including age (R2 = 0.643, p < 0.001), and sex classification (area under the receiver operator characteristic (AUROC) curve = 0.808), diabetes and hypertension diagnosis (AUROC = 0.832 and 0.755, respectively). Significant predictions were also modeled for metabolic/endocrine functions (including blood concentrations of IGF-1, leptin, ghrelin, adiponectin, and glucose), and immune markers (including IL-6, TNF-alpha, and CRP). In addition, this approach provided successful predictions in regression modeling of BMI and both regression and classification of sleep apnea. DiscussionThis study demonstrates the potential of using features from oscillatory events in single-channel sleep EEG as digital biomarkers. These biomarkers can identify key health and demographic factors that both affect brain health and are indicative of core brain functions. By capturing the complex interactions of neural, metabolic, endocrine, and immune systems during sleep, our findings support the development of single-channel EEG as a practical tool for monitoring complex biological processes through metrics that originate in brain physiology. Future research should aim to refine these digital biomarkers for broader home-based applications that may utilize inexpensive "wearable" devices to provide a scalable and accessible tool for tracking brain health-related outcomes.

neuroscience↗

bioRxiv2020

Modified split application of nitrogen with biochar improved grain yield and nitrogen use efficiency in rainfed maize grown in Vertisols of India

Conventionally, non-judicious and blanket fertilizer nitrogen (N) used in rainfed maize lead to higher N losses, low N use efficiency (NUEs) and poor yields due to substandard agronomic management practices. To avoid such N losses, fertilizer additions are synchronized with plant uptake requirements. In this context, agronomic based management focused on optimizing N rates and biochar application is essential for improved NUEs and crop productivity. Keeping this in view, a field experiment was conducted during 2014, 2015 and 2016 in rainfed maize (Zea mays L.) grown in Vertisols of India. In this study, twelve treatments that comprised of N omission plot (N0), skipping of basal rate, multi-split topdressing at varying time as broadcast and band placement, soil test crop response (STCR) based NPK with target yield 6.0 t ha-1 in maize and biochar application (10 t ha-1) were investigated. The experiment was conducted following a Randomized Complete Block Design (RCBD) set up with three replications. Pooled analysis of three years data revealed that the application of N rates (120 kg Nha-1) in 2 equal splits (60 kg Nha-1) at knee high (V8) and tasseling (VT) stages with skipped basal N rate, achieved higher maize grain yield (5.29 t ha-1) ascribed to the greater growth parameters, yield components and N uptake compared to the recommended practices. Biochar application (10 t ha-1) as soil amendments along with multi top dressed N (120 kg N ha-1) into 3 splits also increased the grain yield. Delayed N application at V8 and VT growth stages, resulted in higher N uptake, agronomy efficiency (AE), partial factor productivity (PFP), physiology efficiency (PE) and recovery efficiency (RE). Biochar along with N fertilizer also improved the soil organic carbon (5.47g kg-1), ammonium-N (2.40 mg kg-1) and nitrate-N (0.52 mg kg-1) concentration in soil (P<0.05) as compared to non-biochar treatments. Application of biochar along with chemical fertilizer (120 kg Nha-1) significantly increased the concentration of ammonium (2.40 mg kg-1) and nitrate (0.52 mg kg-1) in soil (P<0.05) as compared to non-biochar treatments. The perfect positive linear relationship illustrated that the grain yield of rainfed maize was highly dependent (R2=0.99 at p<0.0001) on N availability, as indicated by the fitted regression line of maize grain yield on N uptake. On the other hand, factor analysis revealed, the one to one positive function relationship of biomass with N uptake at V8 and VT growth stages. Principal Component Regression (PCR) analysis showed that PC1 acted as a major predictor variable for total dry matter yield (TDMY) and dominated by LAI and N uptake. Consequently, these results expressed that the agronomic management based multi-top dressed N application and biochar application to achieve higher yield and greater NUEs in rainfed maize is strongly linked with N application into splits.

plant biology↗