Search

Women comprise a significant portion of the agricultural workforce in developing countries but are often less likely to attend government sponsored training events. The objective of this study was to assess the feasibility of using machine-supported decision-making to increase overall training turnout while enhancing gender inclusivity. Using data obtained from 1,067 agricultural extension training events in Bangladesh (130,690 farmers), models were created to assess gender-based training patterns (e.g., preferences and availability for training). Using these models, simulations were performed to predict the top (most attended) training events for increasing total attendance (male and female combined) and female attendance, based on gender of the trainer, and when and where training took place. By selecting a mixture of the top training events for total attendance and female attendance, simulations indicate that total and female attendance can be concurrently increased. However, strongly emphasizing female participation can have negative consequences by reducing overall turnout, thus creating an ethical dilemma for policy makers. In addition to balancing the need for increasing overall training turnout with increased female representation, a balance between model performance and machine learning is needed. Model performance can be enhanced by reducing training variety to a few of the top training events. But given that models are early in development, more training variety is recommended to provide a larger solution space to find more optimal solutions that will lead to better future performance. Simulations show that selecting the top 25 training events for total attendance and the top 25 training events for female attendance can increase female participation by over 82% while at the same time increasing total turnout by 14%. In conclusion, this study supports the use of machine-supported decision-making when developing gender inclusivity policies in agriculture extension services and lays the foundation for future applications of machine learning in this area.

Despite the recognized importance of women’s participation in agricultural extension services, research continues to show inequalities in women’s participation. Emerging capacities for conducting large-scale extension training using information and communication technologies (ICTs) now afford opportunities for generating the rich datasets needed to analyze situational factors that affect women’s participation. Data was recorded from 1,070 video-based agricultural extension training events (131,073 farmers) in four Administrative Divisions of Bangladesh (Rangpur, Dhaka, Khulna, and Rajshahi). The study analyzed the effect of gender of the trainer, time of the day, day of the week, month of the year, Bangladesh Administrative Division, and venue type on (1) the expected number of extension event attendees and (2) the odds of females attending the event conditioned on the total number of attendees. The study revealed strong gender specific training preferences. Several factors that increased total participation, decreased female attendance (e.g., male-led training event held after 3:30 pm in Rangpur). These findings highlight the dilemma faced by extension trainers seeking to maximize attendance at training events while avoiding exacerbating gender inequalities. The study concludes with a discussion of ways to mitigate gender exclusion in extension training by extending data collection processes, incorporating machine learning to understand gender preferences, and applying optimization theory to increase total participation while concurrently improving gender inclusivity.

The risk stratification of patients in the emergency department begins at triage. It is vital to stratify patients early based on their severity, since undertriage can lead to increased morbidity, mortality and costs. Our aim was to present a new approach to assist healthcare professionals at triage in the stratification of patients and in identifying those with higher risk of ICU admission. Adult patients assigned Manchester Triage System (MTS) or Emergency Severity Index (ESI) 1 to 3 from a Portuguese and a United States Emergency Departments were analyzed. Variables routinely collected at triage were used and natural language processing was applied to the patient chief complaint. Stratified random sampling was applied to split the data in train (70%) and test (30%) sets and 10-fold cross validation was performed for model training. Logistic regression, random forests, and a random undersampling boosting algorithm were used. We compared the performance obtained with the reference model-using only triage priorities-with the models using additional variables. For both hospitals, a logistic regression model achieved higher overall performance, yielding areas under the receiver operating characteristic and precision-recall curves of 0.91 (95% CI 0.90-0.92) and 0.30 (95% CI 0.27-0.33) for the United States hospital and of 0.85 (95% CI 0.83-0.86) and 0.06 (95% CI 0.05-0.07) for the Portuguese hospital. Heart rate, pulse oximetry, respiratory rate and systolic blood pressure were the most important predictors of ICU admission. Compared to the reference models, the models using clinical variables and the chief complaint presented higher recall for patients assigned MTS/ESI 3 and can identify patients assigned MTS/ESI 3 who are at risk for ICU admission.

Background Among patients with acute respiratory failure requiring prolonged mechanical ventilation, tracheostomies are typically placed after approximately 7 to 10 days. Yet half of patients admitted to the intensive care unit receiving tracheostomy will die within a year, often within three months. Existing mortality prediction models for prolonged mechanical ventilation, such as the ProVent Score, have poor sensitivity and are not applied until after 14 days of mechanical ventilation. We developed a model to predict 3-month mortality in patients requiring more than 7 days of mechanical ventilation using deep learning techniques and compared this to existing mortality models. Methods Retrospective cohort study. Setting: The Medical Information Mart for Intensive Care III Database. Patients: All adults requiring ≥ 7 days of mechanical ventilation. Measurements: A neural network model for 3-month mortality was created using process-of-care variables, including demographic, physiologic and clinical data. The area under the receiver operator curve (AUROC) was compared to the ProVent model at predicting 3 and 12-month mortality. Shapley values were used to identify the variables with the greatest contributions to the model. Results There were 4,334 encounters divided into a development cohort (n = 3467) and a testing cohort (n = 867). The final deep learning model included 250 variables and had an AUROC of 0.74 for predicting 3-month mortality at day 7 of mechanical ventilation versus 0.59 for the ProVent model. Older age and elevated Simplified Acute Physiology Score II (SAPS II) Score on intensive care unit admission had the largest contribution to predicting mortality. Discussion We developed a deep learning prediction model for 3-month mortality among patients requiring ≥ 7 days of mechanical ventilation using a neural network approach utilizing readily available clinical variables. The model outperforms the ProVent model for predicting mortality among patients requiring ≥ 7 days of mechanical ventilation. This model requires external validation.

BackgroundPotassium replenishment protocols are often employed across broad patient populations to prevent cardiac arrhythmias. Tailoring potassium thresholds to specific patient populations would reduce unnecessary tasks and cost. The objective of this retrospective cohort study was to determine the threshold at which hypokalemia increases the risk for medically treated arrhythmias in cardiac versus medical and surgical intensive care units.MethodsPatients captured in the publicly available Philips eICU database were assessed for initiation of either intravenous amiodarone, adenosine, ibutilide, isoproterenol, or lidocaine as a surrogate for a clinically significant arrhythmia. A landmark time-to-event analysis was conducted to investigate the association of serum potassium values and time-marked administration of an antiarrhythmic drug. Analysis was adjusted for comorbidities, the use of vasopressor agents, diuretics, as well as age, gender and severity of illness.ResultsAmong 20,665 admissions to cardiac intensive care units, 1,371 (6.6%) were treated with either amiodarone, adenosine, ibutilide, isoproterenol, or lidocaine. For potassium values of ≥3.0ConclusionsSerum potassium levels

With the accumulation of large amounts of health related data, predictive analytics could stimulate the transformation of reactive medicine towards Predictive, Preventive and Personalized (PPPM) Medicine, ultimately affecting both cost and quality of care. However, high-dimensionality and high-complexity of the data involved, prevents data-driven methods from easy translation into clinically relevant models. Additionally, the application of cutting edge predictive methods and data manipulation require substantial programming skills, limiting its direct exploitation by medical domain experts. This leaves a gap between potential and actual data usage. In this study, the authors address this problem by focusing on open, visual environments, suited to be applied by the medical community. Moreover, we review code free applications of big data technologies. As a showcase, a framework was developed for the meaningful use of data from critical care patients by integrating the MIMIC-II database in a data mining environment (RapidMiner) supporting scalable predictive analytics using visual tools (RapidMiner’s Radoop extension). Guided by the CRoss-Industry Standard Process for Data Mining (CRISP-DM), the ETL process (Extract, Transform, Load) was initiated by retrieving data from the MIMIC-II tables of interest. As use case, correlation of platelet count and ICU survival was quantitatively assessed. Using visual tools for ETL on Hadoop and predictive modeling in RapidMiner, we developed robust processes for automatic building, parameter optimization and evaluation of various predictive models, under different feature selection schemes. Because these processes can be easily adopted in other projects, this environment is attractive for scalable predictive analytics in health research., National Institutes of Health (U.S.) (National Institute for Biomedical Imaging and Bioengineering (U.S.) Grant R01 EB01720501A1)

Emergency department triage is the first point in time when a patient’s acuity level is determined. The time to assign a priority at triage is short and it is vital to accurately stratify patients at this stage, since under-triage can lead to increased morbidity, mortality and costs. Our aim was to present a model that can assist healthcare professionals in triage decision making, namely in the stratification of patients through the risk prediction of a composite critical outcome—mortality and cardiopulmonary arrest. Our study cohort consisted of 235826 adult patients triaged at a Portuguese Emergency Department from 2012 to 2016. Patients were assigned to emergent, very urgent or urgent priorities of the Manchester Triage System (MTS). Demographics, clinical variables routinely collected at triage and the patients’ chief complaint were used. Logistic regression, random forests and extreme gradient boosting were developed using all available variables. The term frequency–inverse document frequency (TF-IDF) natural language processing weighting factor was applied to vectorize the chief complaint. Stratified random sampling was used to split the data into train (70%) and test (30%) data sets. Ten-fold cross validation was performed in train to optimize model hyper-parameters. The performance obtained with the best model was compared against the reference model—a regularized logistic regression trained using only triage priorities. Extreme gradient boosting exhibited good calibration properties and yielded areas under the receiver operating characteristic and precision-recall curves of 0.96 (95% CI 0.95-0.97) and 0.31 (95% CI 0.26-0.36), respectively. The predictors ranked with higher importance by this model were the Glasgow coma score, the patients’ age, pulse oximetry and arrival mode. Compared to the reference, the extreme gradient boosting model using clinical variables and the chief complaint presented higher recall for patients assigned MTS-3 and can identify those who are at risk of the composite outcome.

In secondary analysis of electronic health records, a crucial task consists in correctly identifying the patient cohort under investigation. In many cases, the most valuable and relevant information for an accurate classification of medical conditions exist only in clinical narratives. Therefore, it is necessary to use natural language processing (NLP) techniques to extract and evaluate these narratives. The most commonly used approach to this problem relies on extracting a number of clinician-defined medical concepts from text and using machine learning techniques to identify whether a particular patient has a certain condition. However, recent advances in deep learning and NLP enable models to learn a rich representation of (medical) language. Convolutional neural networks (CNN) for text classification can augment the existing techniques by leveraging the representation of language to learn which phrases in a text are relevant for a given medical condition. In this work, we compare concept extraction based methods with CNNs and other commonly used models in NLP in ten phenotyping tasks using 1,610 discharge summaries from the MIMIC-III database. We show that CNNs outperform concept extraction based methods in almost all of the tasks, with an improvement in F1-score of up to 26 and up to 7 percentage points in area under the ROC curve (AUC). We additionally assess the interpretability of both approaches by presenting and evaluating methods that calculate and extract the most salient phrases for a prediction. The results indicate that CNNs are a valid alternative to existing approaches in patient phenotyping and cohort identification, and should be further investigated. Moreover, the deep learning approach presented in this paper can be used to assist clinicians during chart review or support the extraction of billing codes from text by identifying and highlighting relevant phrases for various medical conditions.

Background Tuberculosis is a major cause of morbidity and mortality in the developing world. Drug resistance, which is predicted to rise in many countries worldwide, threatens tuberculosis treatment and control. Objective To identify features associated with treatment failure and to predict which patients are at highest risk of treatment failure. Methods On a multi-country dataset managed by the National Institute of Allergy and Infectious Diseases we applied various machine learning techniques to identify factors statistically associated with treatment failure and to predict treatment failure based on baseline demographic and clinical characteristics alone. Results The complete-case analysis database consisted of 587 patients (68% males) with a median (p25-p75) age of 40 (30–51) years. Treatment failure occurred in approximately one fourth of the patients. The features most associated with treatment failure were patterns of drug sensitivity, imaging findings, findings in the microscopy Ziehl-Nielsen stain, education status, and employment status. The most predictive model was forward stepwise selection (AUC: 0.74), although most models performed at or above AUC 0.7. A sensitivity analysis using the 643 original patients filling the missing values with multiple imputation showed similar predictive features and generally increased predictive performance. Conclusion Machine learning can help to identify patients at higher risk of treatment failure. Closer monitoring of these patients may decrease treatment failure rates and prevent emergence of antibiotic resistance. The use of inexpensive basic demographic and clinical features makes this approach attractive in low and middle-income countries.

Metabolic chambers are powerful tools for assessing human energy expenditure, providing flexibility and comfort for the subjects in a near free-living environment. However, the flexibility offered by the large living room size creates challenges in the assessment of dynamic human metabolic signals-such as those generated during high-intensity interval training and short-term involuntary physical activities-with sufficient temporal accuracy. Therefore, this paper presents methods to improve the temporal accuracy of metabolic chambers. The proposed methods include 1) adopting a shortest possible step size, here one minute, to compute the finite derivative terms for the metabolic rate calculation, and 2) applying a robust noise reduction method-total variation denoising-to minimize the large noise generated by the short derivative term whilst preserving the transient edges of the dynamic metabolic signals. Validated against 24-hour gas infusion tests, the proposed method reconstructs dynamic metabolic signals with the best temporal accuracy among state-of-the-art approaches, achieving a root mean square error of 0.27 kcal/min (18.8 J/s), while maintaining a low cumulative error in 24-hour total energy expenditure of less than 45 kcal/day (188280 J/day). When applied to a human exercise session, the proposed methods also show the best performance in terms of recovering the dynamics of exercise energy expenditure. Overall, the proposed methods improve the temporal resolution of the chamber system, enabling metabolic studies involving dynamic signals such as short interval exercises to carry out the metabolic chambers.

Optical coherence tomography (OCT) is an established catheter-based imaging modality for the assessment of coronary artery disease and the guidance of stent placement during percutaneous coronary intervention. Manual analysis of large OCT datasets for vessel contours or stent struts detection is time-consuming and unsuitable for real-time applications. In this study, a fully automatic method was developed for detection of both vessel contours and stent struts. The method was applied to in vitro OCT scans of eight stented silicone bifurcation phantoms for validation purposes. The proposed algorithm comprised four main steps, namely pre-processing, lumen border detection, stent strut detection, and three-dimensional point cloud creation. The algorithm was validated against manual segmentation performed by two independent image readers. Linear regression showed good agreement between automatic and manual segmentations in terms of lumen area (r>0.99). No statistically significant differences in the number of detected struts were found between the segmentations. Mean values of similarity indexes were >95% and >85% for the lumen and stent detection, respectively. Stent point clouds of two selected cases, obtained after OCT image processing, were compared to the centerline points of the corresponding stent reconstructions from micro computed tomography, used as ground-truth. Quantitative comparison between the corresponding stent points resulted in median values of ~150 μm and ~40 μm for the total and radial distances of both cases, respectively. The repeatability of the detection method was investigated by calculating the lumen volume and the mean number of detected struts per frame for seven repeated OCT scans of one selected case. Results showed low deviation of values from the median for both analyzed quantities. In conclusion, this study presents a robust automatic method for detection of lumen contours and stent struts from OCT as supported by focused validation against both manual segmentation and micro computed tomography and by good repeatability.

Recent years have seen a surge of studies in machine learning in health and biomedicine, driven by digitalization of healthcare environments and increasingly accessible computer systems for conducting analyses. Many of us believe that these developments will lead to significant improvements in patient care. Like many academic disciplines, however, progress is hampered by lack of code and data sharing. In bringing together this PLOS ONE collection on machine learning in health and biomedicine, we sought to focus on the importance of reproducibility, making it a requirement, as far as possible, for authors to share data and code alongside their papers.

The RET S836S variant has been associated with early onset and increased risk for metastatic disease in medullary thyroid carcinoma (MTC). However, the mechanism by which this variant modulates MTC pathogenesis is still open to discuss. Of interest, strong linkage disequilibrium (LD) between RET S836S and 3'UTR variants has been reported in Hirschsprung's disease patients., info:eu-repo/semantics/published

Coagulation factor Xa appears involved in the pathogenesis of pulmonary fibrosis. Through its interaction with protease activated receptor-1, this protease signals myofibroblast differentiation in lung fibroblasts. Although fibrogenic stimuli induce factor X synthesis by alveolar cells, the mechanisms of local posttranslational factor X activation are not fully understood. Cell-derived microparticles are submicron vesicles involved in different physiological processes, including blood coagulation; they potentially activate factor X due to the exposure on their outer membrane of both phosphatidylserine and tissue factor. We postulated a role for procoagulant microparticles in the pathogenesis of interstitial lung diseases. Nineteen patients with interstitial lung diseases and 11 controls were studied. All subjects underwent bronchoalveolar lavage; interstitial lung disease patients also underwent pulmonary function tests and high resolution CT scan. Microparticles were enumerated in the bronchoalveolar lavage fluid with a solid-phase assay based on thrombin generation. Microparticles were also tested for tissue factor activity. In vitro shedding of microparticles upon incubation with H2O2 was assessed in the human alveolar cell line, A549 and in normal bronchial epithelial cells. Tissue factor synthesis was quantitated by real-time PCR. Total microparticle number and microparticle-associated tissue factor activity were increased in interstitial lung disease patients compared to controls (84±8 vs. 39±3 nM phosphatidylserine; 293±37 vs. 105±21 arbitrary units of tissue factor activity; mean±SEM; p

Protein tyrosine phosphatase non-receptor type 22 (PTPN22) is a negative regulator of T-cell activation associated with several autoimmune diseases, including systemic lupus erythematosus (SLE). Missense rs2476601 is associated with SLE in individuals with European ancestry. Since the rs2476601 risk allele frequency differs dramatically across ethnicities, we assessed robustness of PTPN22 association with SLE and its clinical sub-phenotypes across four ethnically diverse populations. Ten SNPs were genotyped in 8220 SLE cases and 7369 controls from in European-Americans (EA), African-Americans (AA), Asians (AS), and Hispanics (HS). We performed imputation-based association followed by conditional analysis to identify independent associations. Significantly associated SNPs were tested for association with SLE clinical sub-phenotypes, including autoantibody profiles. Multiple testing was accounted for by using false discovery rate. We successfully imputed and tested allelic association for 107 SNPs within the PTPN22 region and detected evidence of ethnic-specific associations from EA and HS. In EA, the strongest association was at rs2476601 (P = 4.7 × 10(-9), OR = 1.40 (95% CI = 1.25-1.56)). Independent association with rs1217414 was also observed in EA, and both SNPs are correlated with increased European ancestry. For HS imputed intronic SNP, rs3765598, predicted to be a cis-eQTL, was associated (P = 0.007, OR = 0.79 and 95% CI = 0.67-0.94). No significant associations were observed in AA or AS. Case-only analysis using lupus-related clinical criteria revealed differences between EA SLE patients positive for moderate to high titers of IgG anti-cardiolipin (aCL IgG >20) versus negative aCL IgG at rs2476601 (P = 0.012, OR = 1.65). Association was reinforced when these cases were compared to controls (P = 2.7 × 10(-5), OR = 2.11). Our results validate that rs2476601 is the most significantly associated SNP in individuals with European ancestry. Additionally, rs1217414 and rs3765598 may be associated with SLE. Further studies are required to confirm the involvement of rs2476601 with aCL IgG.

Background The link between histologic acute chorioamnionitis and infection is well established in preterm deliveries, but less well-studied in term pregnancies, where infection is much less common. Methodology/Principal Findings We conducted a secondary analysis among 195 low-risk women with term pregnancies enrolled in a randomized trial. Histologic and microbiologic evaluation of placentas included anaerobic and aerobic cultures (including mycoplasma/ureaplasma species) as well as PCR. Infection was defined as ≥1,000 cfu of a single known pathogen or a ≥2 log difference in counts for a known pathogen versus other organisms in a mixed culture. Placental membranes were scored and categorized as: no chorioamnionitis, Grade 1 (subchorionitis and patchy acute chorioamnionitis), or Grade 2 (severe, confluent chorioamnionitis). Grade 1 or grade 2 histologic chorioamnionitis was present in 34% of placentas (67/195), but infection was present in only 4% (8/195). Histologic chorioamnionitis was strongly associated with intrapartum fever >38°C [69% (25/36) fever, 26% (42/159) afebrile, P