Small Farmers Large Field (SFLF): a synchronized collective action model for improving the livelihood of small farmers in India

This study pilots the collective action model “Small Farmers Large Field (SFLF)” to overcome the disadvantages faced by millions of small and marginal farmers due to diseconomies of scale and lack of bargaining power in the supply chain. This model is participatory and flexible and allows small farmers to benefit from achieving economies of scale by organizing themselves into groups and synchronizing and harmonizing selected operations. It was piloted in two villages of Odisha, an eastern Indian state, with 112 farmers (35 females and 77 males). These farmers organized themselves into groups and synchronized their operations such as nursery bed management, transplanting, and harvesting collectively to achieve economies of scale. The SFLF farmers purchased inputs (seed and fertilizer) and sold paddy as a group to increase their bargaining power in price negotiations. The results from this pilot study showed that the participating farmers almost doubled their profits. Apart from the monetary benefits, these farmers saved time in many joint activities, including input (seed and fertilizer) purchase, paddy sale, and nursery bed management. Other important benefits of the harmonization and synchronization of farming operations were social harmony and sustainability of the farming system.

Predictive modeling of hospital Length of Stay in COVID-19 patients using Artificial Neural Networks

BackgroundThe current pandemic of coronavirus disease (COVID-19) causes unexpected economic burdens to worldwide health organizations with severe shortages in hospital bed capacity and other related medical resources. Therefore, predicting the length of stay (LOS) is essential to ensure optimal allocating scarce hospital resources and inform evidence-based decision-making. Thus, the purpose of this research is to construct a model for predicting COVID-19 patients' hospital LOS by multiple multilayer perceptron-artificial neural network (MLP-ANN) algorithms. Material and MethodsUsing a single-center registry, the records of 1225 laboratory-confirmed COVID-19 hospitalized cases from February 9, 2020, to December 20, 2020, were analyzed. The correlation coefficient technique was developed to determine the most significant variables as the input of the ANN models. Only variables with a correlation coefficient at the P-value< 0.2 were used in model construction. Ultimately the prediction models were developed based on 12 ANN techniques according to selected variables. ResultsAfter implementing feature selection, a total of 20 variables was determined as the most relevant predictors to build the models. The results indicated that the best performance belongs to a neural network with 20 and 10 neurons in the hidden layer of the Bayesian Regularization classifier for whole and selected features with RMSE of 1.6213 and 2.2332, respectively. ConclusionThe developed model in this study can help in the better calculation of LOS in COVID-19 patients. This model also can be leveraged in hospital bed management and optimized resource utilization.

Machine Learning–Based Hospital Discharge Prediction for Patients With Cardiovascular Diseases: Development and Usability Study

Background Effective resource management in hospitals can improve the quality of medical services by reducing labor-intensive burdens on staff, decreasing inpatient waiting time, and securing the optimal treatment time. The use of hospital processes requires effective bed management; a stay in the hospital that is longer than the optimal treatment time hinders bed management. Therefore, predicting a patient’s hospitalization period may support the making of judicious decisions regarding bed management. Objective First, this study aims to develop a machine learning (ML)–based predictive model for predicting the discharge probability of inpatients with cardiovascular diseases (CVDs). Second, we aim to assess the outcome of the predictive model and explain the primary risk factors of inpatients for patient-specific care. Finally, we aim to evaluate whether our ML-based predictive model helps manage bed scheduling efficiently and detects long-term inpatients in advance to improve the use of hospital processes and enhance the quality of medical services. Methods We set up the cohort criteria and extracted the data from CardioNet, a manually curated database that specializes in CVDs. We processed the data to create a suitable data set by reindexing the date-index, integrating the present features with past features from the previous 3 years, and imputing missing values. Subsequently, we trained the ML-based predictive models and evaluated them to find an elaborate model. Finally, we predicted the discharge probability within 3 days and explained the outcomes of the model by identifying, quantifying, and visualizing its features. Results We experimented with 5 ML-based models using 5 cross-validations. Extreme gradient boosting, which was selected as the final model, accomplished an average area under the receiver operating characteristic curve score that was 0.865 higher than that of the other models (ie, logistic regression, random forest, support vector machine, and multilayer perceptron). Furthermore, we performed feature reduction, represented the feature importance, and assessed prediction outcomes. One of the outcomes, the individual explainer, provides a discharge score during hospitalization and a daily feature influence score to the medical team and patients. Finally, we visualized simulated bed management to use the outcomes. Conclusions In this study, we propose an individual explainer based on an ML-based predictive model, which provides the discharge probability and relative contributions of individual features. Our model can assist medical teams and patients in identifying individual and common risk factors in CVDs and can support hospital administrators in improving the management of hospital beds and other resources.

Abstract 1122‐000099: Establishing “Code NI” in Addition to “Code Stroke” is Warranted When Mechanical Thrombectomy is Needed

Introduction : Hospital medical emergencies are prone to inefficiencies related to delayed dissemination of information, communication error, role confusion, and delayed decision making. The use of medical codes is intended to convey emergent and essential information quickly while preventing stress and mismanagement. The more complex, critical, and time sensitive an event is, the greater the need to establish a Code. Major mechanical thrombectomy (MT) trials published in 2015 and 2016 proved emergent MT to be more effective compared to IV tPA in stroke patients with large vessel occlusion (LVO). It has been proven that time to reperfusion with MT is directly proportional to severity of patient outcomes, coining the phrase, “save a minute, save a week”. When compared to the use of percutaneous intervention (PCI) in the treatment of STEMI, the number needed to treat for MT is estimated at 5 compared to 16 for PCI. Despite this fact, most hospitals have yet to adopt a code specific to MT. Our Purpose is to emphasize the importance of establishing a dedicated Code NI (Neuro‐Intervention) for stroke patients who require MT by sharing our Methods : After defining the problems, measuring the need, and analyzing the process, we identified the urgency for improvements in our facility. The administration was persuaded to support us in implementation of improvements after realizing the success of MT trials in patient outcomes, length of stay, hospital rankings, Comprehensive Stroke Center Certification, and insurance company compensation. Results : In early 2018, after many presentations and meetings, it was decided to implement “Code NI” for acute stroke patients who met MT criteria. Many teams and individuals including Neurointervention, Neuroradiology, Angio Suite, Anesthesia, ICU, Bed management, and transport were alerted. Following these implementations, from 2018 to 2021, our Door to Puncture Time and Puncture to Recanalization Time has been trending down from 219 to 120; and 261 to 147 minutes respectively. Conclusions : Approximately 70% of stroke patients with LVO have the potential of a meaningful recovery if treated efficiently and effectively. Establishing a “Code NI” for this time sensitive medical emergency helps the patients, their families, hospitals, and society.

Examining the association between paramedic transport to the emergency department and hospital admission: a population-based cohort study

Background Increasing hospitalization rates present unique challenges to manage limited inpatient bed capacity and services. Transport by paramedics to the emergency department (ED) may influence hospital admission decisions independent of patient need/acuity, though this relationship has not been established. We examined whether mode of transportation to the ED was independently associated with hospital admission. Methods We conducted a retrospective cohort study using the National Ambulatory Care Reporting System (NACRS) from April 1, 2015 to March 31, 2020 in Ontario, Canada. We included all adult patients (≥18 years) who received a triage score in the ED and presented via paramedic transport or self-referral (walk-in). Multivariable binary logistic regression was used to determine the association of mode of transportation between hospital admission, after adjusting for important patient and visit characteristics. Results During the study period, 21,764,640 ED visits were eligible for study inclusion. Approximately one-fifth (18.5%) of all ED visits were transported by paramedics. All-cause hospital admission incidence was greater when transported by paramedics (35.0% vs. 7.5%) and with each decreasing Canadian Triage and Acuity Scale level. Paramedic transport was independently associated with hospital admission (OR = 3.76; 95%CI = 3.74–3.77), in addition to higher medical acuity, older age, male sex, greater than two comorbidities, treatment in an urban setting and discharge diagnoses specific to the circulatory or digestive systems. Conclusions Transport by paramedics to an ED was independently associated with hospital admission as the disposition outcome, when compared against self-referred visits. Our findings highlight patient and visit characteristics associated with hospital admission, and can be used to inform proactive healthcare strategizing for in-patient bed management.

Machine Learning–Based Hospital Discharge Prediction for Patients With Cardiovascular Diseases: Development and Usability Study (Preprint)

BACKGROUND Effective resource management in hospitals can improve the quality of medical services by reducing labor-intensive burdens on staff, decreasing inpatient waiting time, and securing the optimal treatment time. The use of hospital processes requires effective bed management; a stay in the hospital that is longer than the optimal treatment time hinders bed management. Therefore, predicting a patient’s hospitalization period may support the making of judicious decisions regarding bed management. OBJECTIVE First, this study aims to develop a machine learning (ML)–based predictive model for predicting the discharge probability of inpatients with cardiovascular diseases (CVDs). Second, we aim to assess the outcome of the predictive model and explain the primary risk factors of inpatients for patient-specific care. Finally, we aim to evaluate whether our ML-based predictive model helps manage bed scheduling efficiently and detects long-term inpatients in advance to improve the use of hospital processes and enhance the quality of medical services. METHODS We set up the cohort criteria and extracted the data from CardioNet, a manually curated database that specializes in CVDs. We processed the data to create a suitable data set by reindexing the date-index, integrating the present features with past features from the previous 3 years, and imputing missing values. Subsequently, we trained the ML-based predictive models and evaluated them to find an elaborate model. Finally, we predicted the discharge probability within 3 days and explained the outcomes of the model by identifying, quantifying, and visualizing its features. RESULTS We experimented with 5 ML-based models using 5 cross-validations. Extreme gradient boosting, which was selected as the final model, accomplished an average area under the receiver operating characteristic curve score that was 0.865 higher than that of the other models (ie, logistic regression, random forest, support vector machine, and multilayer perceptron). Furthermore, we performed feature reduction, represented the feature importance, and assessed prediction outcomes. One of the outcomes, the individual explainer, provides a discharge score during hospitalization and a daily feature influence score to the medical team and patients. Finally, we visualized simulated bed management to use the outcomes. CONCLUSIONS In this study, we propose an individual explainer based on an ML-based predictive model, which provides the discharge probability and relative contributions of individual features. Our model can assist medical teams and patients in identifying individual and common risk factors in CVDs and can support hospital administrators in improving the management of hospital beds and other resources. CLINICALTRIAL

Operating Room (Re)Scheduling with Bed Management via ASP

The Operating Room Scheduling (ORS) problem is the task of assigning patients to operating rooms (ORs), taking into account different specialties, lengths, and priority scores of each planned surgery, OR session durations, and the availability of beds for the entire length of stay (LOS) both in the Intensive Care Unit (ICU) and in the wards. A proper solution to the ORS problem is of primary importance for the healthcare service quality and the satisfaction of patients in hospital environments. In this paper we first present a solution to the problem based on Answer Set Programming (ASP). The solution is tested on benchmarks with realistic sizes and parameters, on three scenarios for the target length on 5-day scheduling, common in small–medium-sized hospitals, and results show that ASP is a suitable solving methodology for the ORS problem in such setting. Then, we also performed a scalability analysis on the schedule length up to 15 days, which still shows the suitability of our solution also on longer plan horizons. Moreover, we also present an ASP solution for the rescheduling problem, that is, when the offline schedule cannot be completed for some reason. Finally, we introduce a web framework for managing ORS problems via ASP that allows a user to insert the main parameters of the problem, solve a specific instance, and show results graphically in real time.