Decision Support Research Articles

Impact Assessment Frameworks for Nature-Based Climate Solutions: A Review of Contemporary Approaches

This study provides a comparative analysis of ecological impact assessment (EcIA) guidance for the design and approval stages of carbon sequestration and emission reduction projects, which are rapidly proliferating in response to the global need for climate change mitigation. Previous reports of negative effects on biodiversity from such projects suggest a need for more robust project design and assessment processes to improve synergies with conservation. Using a content and thematic analysis methodology, we compared four published frameworks that guide the assessment of carbon projects in natural environments. The results showed considerable variation in environmental assessment components including the level of attention to ecosystem services and the identification of areas of high conservation value that may require specific protections. There was a general lack of guidance on the inclusion of indirect and supply chain effects despite their relevance to ecological impacts. Critically, guidance in common use in the climate mitigation sector shows differing applications of the baseline and counterfactual scenarios that are used to quantify impacts. We discuss the need to focus assessment and reporting on comparisons with recent baselines to identify the contributions of individual projects and enable adaptive management and show how aligning with the concepts of Nature-based Solutions and nature-positive could be used to reimagine the role of EcIA to achieve these objectives. If these current weaknesses can be improved, EcIA has the potential to become an important implementation pathway for the conservation–climate change nexus due to its pivotal role in project design and approval processes. Conversely, a failure to reliably address these aspects will undermine the utility of EcIA as a decision support tool for sustainable development. We encourage the further exploration of EcIA practices in this direction and highlight the pressing need for reliable comparisons to support more strategic and sustainable solutions for both the conservation and climate change agendas.

Hotel digital intelligence capability: dimension exploration and scale development

Purpose This study aims to explore the dimensional structure of hotel digital intelligence capability and develop a measurement scale. Design/methodology/approach This study adopts qualitative and quantitative approaches to conduct an exploratory inquiry into the structural dimensions of hotel digital intelligence capability with the help of grounded theory. Based on this, several questionnaires were developed to test the measurement scale and verify its validity. Findings The results reveal that hotel digital intelligence capability comprises four dimensions: data collection and processing capability, customer service personalization capability, digital intelligence decision support capability and sustainable development capability. The measurement scale consists of four factors and 13 items, with reliability and validity tests demonstrating ideal levels. Originality/value This study not only provides a new perspective to understand hotel digital intelligence capability but also develops a corresponding measurement scale, laying a solid theoretical basis for hotel managers to scientifically evaluate this capability to achieve sustainable competitive advantage.

In Silico Evaluation of Algorithm-Based Clinical Decision Support Systems: Protocol for a Scoping Review

Background Integrating algorithm-based clinical decision support (CDS) systems poses significant challenges in evaluating their actual clinical value. Such CDS systems are traditionally assessed via controlled but resource-intensive clinical trials. Objective This paper presents a review protocol for preimplementation in silico evaluation methods to enable broadened impact analysis under simulated environments before clinical trials. Methods We propose a scoping review protocol that follows an enhanced Arksey and O’Malley framework and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines to investigate the scope and research gaps in the in silico evaluation of algorithm-based CDS models—specifically CDS decision-making end points and objectives, evaluation metrics used, and simulation paradigms used to assess potential impacts. The databases searched are PubMed, Embase, CINAHL, PsycINFO, Cochrane, IEEEXplore, Web of Science, and arXiv. A 2-stage screening process identified pertinent articles. The information extracted from articles was iteratively refined. The review will use thematic, trend, and descriptive analyses to meet scoping aims. Results We conducted an automated search of the databases above in May 2023, with most title and abstract screenings completed by November 2023 and full-text screening extended from December 2023 to May 2024. Concurrent charting and full-text analysis were carried out, with the final analysis and manuscript preparation set for completion in July 2024. Publication of the review results is targeted from July 2024 to February 2025. As of April 2024, a total of 21 articles have been selected following a 2-stage screening process; these will proceed to data extraction and analysis. Conclusions We refined our data extraction strategy through a collaborative, multidisciplinary approach, planning to analyze results using thematic analyses to identify approaches to in silico evaluation. Anticipated findings aim to contribute to developing a unified in silico evaluation framework adaptable to various clinical workflows, detailing clinical decision-making characteristics, impact measures, and reusability of methods. The study’s findings will be published and presented in forums combining artificial intelligence and machine learning, clinical decision-making, and health technology impact analysis. Ultimately, we aim to bridge the development-deployment gap through in silico evaluation-based potential impact assessments. International Registered Report Identifier (IRRID) DERR1-10.2196/63875

Artificial intelligence in soil microbiome analysis: a potential application in predicting and enhancing soil health—a review

Abstract Soil is a depletable and non-renewable resource essential for food production, crop growth, and supporting ecosystem services, such as the retaining and cycling of various elements, including water. Therefore characterization and preservation of soil biological health is a key point for the development of sustainable agriculture. We conducted a comprehensive review of the use of Artificial Intelligence (AI) techniques to develop forecasting models based on soil microbiota data able to monitor and predict soil health. We also investigated the potentiality of AI-based Decision Support Systems (DSSs) for improving the use of microorganisms to enhance soil health and fertility. While available studies are limited, potential applications of AI seem relevant to develop predictive models for soil fertility, based on its biological properties and activities, and implement sustainable precision agriculture, safeguarding ecosystems, bolstering soil resilience, and ensuring the production of high-quality food.

Forecasting Agricultural Trade Based on TCN-LightGBM Models: A Data-Driven Decision

Facing the increasing complexity and dynamic fluctuations of the global agricultural trade market, accurate forecasting plays a key role in supporting agricultural policy formulation, stabilising the market and optimising resource allocation. In order to increase the precision and stability of agricultural trade predictions, this research suggests a hybrid model built on a temporal convolution network (TCN) and a lightweight gradient boosting tree (LightGBM). The TCN module effectively captures the long-term dependence characteristics of time series data through dilated convolution, which improves the model’s ability to identify seasonal and periodic trends. The LightGBM module, on the other hand, makes use of the characteristics of gradient boosting decision trees and excels at efficiently handling nonlinear relationships and avoiding overfitting. Experimental results show that the TCN-LightGBM model outperforms traditional models in terms of mean square error (MSE), mean absolute error (MAE) and prediction accuracy. Specifically, compared with ARIMA, LSTM, TCN alone or LightGBM alone, TCN-LightGBM achieves a prediction accuracy of 91.3% on the test data, with MSE and MAE of 0.021 and 0.115 respectively, significantly improving prediction accuracy and stability. In addition, parameter sensitivity analysis shows that the TCN-LightGBM model maintains a highly consistent prediction trend under different parameter configurations, which verifies the robustness of the model and its practical application value. This study provides a data-driven decision support tool with high accuracy and strong stability, providing a new solution for agricultural trade forecasting and other complex time series prediction tasks.

Water Reuse: Contribution of a Decision Support Model

Sustainability seeks to strike a balance between preserving the environment and meeting human needs without compromising future generations. In this context, and considering the effects of climate change on water availability, water reuse is emerging as an alternative to conventional water sources for various purposes, contributing to sustainability. Water reuse projects are, in general, not simple to implement due to different technical, environmental, social and economic aspects. In this paper, a support decision model for water reuse projects is presented, identifying relevant indicators and parameters. Based on a literature review, four indicators or dimensions (technical, social, environmental and economic) and twelve parameters (e.g., WWTP safety, transport complexity, existence of legislation, risk to health and environment, energy consumption, degree of acceptance and required investment and operation and maintenance costs) are proposed. The Fuzzy Analytic Hierarchy Process (FAHP) method is used as a component of the model to determine the weights of the indicators and parameters in order to allow the calculation of a reuse feasibility index (RFI). The developed model was applied to the city of Aquiraz, Ceará, Brazil, and the RFI found was 82%, which means that the water reuse project had very high viability. The results underwent a sensitivity analysis, which confirms the consistency of the conclusions.

Customer Relationship Management System with Decision Support

This paper studied customer relationship management system with decision support. At present, the fitness studio management system has accumulated a large amount of customer data, but the studio still has problems in customer management such as inaccurate customer target positioning and imperfect customer relationship management functions. It is still unable to conduct intelligent analysis, resulting in a decline in the overall management ability of customer groups. As such, customer turnover is high, and customer loyalty is reduced. To solve such problems, this research constructed a customer relationship management system with decision support, which can be used to identify customers with high studio and high platform loyalty, and with repeated purchase of GT fitness studio. With the purpose of helping the studio achieve accurate customer relationship management and business decision management, this study built an intelligent customer cluster analysis system through K-means clustering algorithm, which can automatically cluster customers into four (4) categories, indicate the characteristics of consumer behavior under each category, and screen out high-quality fitness customers with large consumption amount, high consumption frequency, high platform evaluation, high loyalty, and heavy consumption. At the same time, it also screens out general customers. Moreover, the intelligent group display of the clustered customers is visualized in the form of reports, and the visual display of each group is also carried out, so that decision makers can conveniently implement accurate group management of different groups of customers.

A Systematic Review on Decision-Making Models for Evaluating Supply Risks

Objective: The objective of the present study is to carry out a systematic review of the literature regarding quantitative models for assessing supply risks. Theoretical Framework: Organizations and their supply chains are increasingly exposed to risks. Given the uncertainties of the business environment, the occurrence of adverse events may result in the interruption of supply in these chains, causing disruption and losses. The development of decision-making models to support risk assessment helps prevent supply discontinuity and can contribute to increasing the robustness of supply chains. Method: Aiming to map quantitative models to support supply risk assessment, the systematic literature review was carried out based on the PRISMA method. Seven factors were considered to classify the selected studies, namely: year of publication, purpose of risk assessment, technique(s) used, criteria, types of input data, support for group decisions and application sector. Results and Discussion: It was found that most of the techniques used are aimed at environments of uncertainty and group decision-making processes. There was also a predominance of applications in companies in the automotive industry and the focus on risk assessment for supplier selection. The most frequent decision technique was AHP. Research Implications: In addition to mapping the state of the art on this topic, some opportunities for future studies were identified in order to assist managers and researchers interested in developing new decision-making models for assessing supply risks. Originality/Value: Based on the bibliographical research carried out, it can be stated that this is the first study focused on mapping decision-making models for assessing supply risks. This study complements previous systematic reviews on risk management in supply chains and can be valuable for the development of tools aimed at mitigating supply risks.

Performance of heat transfer in Al2O3/MWCNT hybrid nanofluid flow using machine learning models

Abstract This investigation diverges from traditional studies concentrating on single-component nanofluids, instead examining the thermophysical benefits of hybrid nanofluids, like Al₂O₃/MWCNT, aimed at improving thermal conductivity and heat transfer efficiency in passive systems. Machine learning is a promising solution for designing efficient heat exchangers by understanding intricate relationships and utilizing suitable modelling techniques. Numerical simulations were conducted to validate the benchmark results; later, passive techniques were incorporated into the numerical model to predict the heat transfer characteristics. The dataset derived from numerical simulation results is employed to train contemporary machine learning methodologies, including support vector regression (SVR), decision tree (DT), and random forest (RF). Data from experiments and CFD analysis were gathered for preprocessing and machine learning (ML) analysis. The preprocessing phase involved the application of a standard scaler operation to enhance accuracy levels. The models underwent validation using ten experimental data samples to assess their performance against statistical tool metrics. A higher thermal performance factor (ThPF) is observed with the divergent nozzle insert in the plain tube at 0.028 vol% of MWCNT/Al2O3 (HNF3) at Reynolds number 3093. R2 values of SVR, DT and RF are predicted as 0.95, 0.98 and 0.99, respectively, for the case of HNF3 fluid flowing through the divergent nozzle insert. The investigation broadens its conclusions to include improvements in passive heat transfer, encompassing extended surfaces and geometric alterations, offering practical guidance for developing advanced heat exchanger designs.

Preservation empowered dual-warehousing for perishable product under trade-credit financing scheme incorporating diverse demand

This work addresses a dealer's operational planning problem for handling perishable product's two-level trade through a financially sustainable supply chain set-up under two-level trade-credit and dual-warehousing arrangement equipped with preservation technology. Financial support is provided to client at both levels of trade, under bilaterally agreed situation-based specific terms and conditions alleviating lean cash flow. Pivotal objective of this work is developing a mathematical model that supports this decision-making situation for optimising cost efficiency in supply chain operations. Formulating this mathematical model and its solution methodology are perplexing due to multiple cases divulging through the utilisation of warehousing arrangements combined with financial outcomes of two-level trade-credit settlements. Both are accomplished in this work. Ancillary models are further developed for evaluating strategic benefits of trade-credit financing and additional warehousing space availability. Implementations on real case-based multiple data sets are presented, wherein computational results confirm the capability of decision support developed on provisioning all circumstances of warehousing requirements and financial liabilities towards both levels of trade credit. Comparative analysis performed through computations on ancillary models establishes strategic benefits of addressed contemporary business practices. Furthermore, variational analysis is extensively performed for identifying crucial parameters pertaining to the stability of the developed decision mechanism.

To Study the Dynamics of Demand and Consumption Patterns of Wellness Tea in Different Provinces of China

In the present social context where health awareness is on the rise Chinese consumers appetite for healthy beverages is experiencing a rapid upward trend. Wellness tea beverages, which integrate traditional wellness concepts with modern beverage culture, are increasingly popular among consumers due to their potential health advantages.. This report offers an in-depth analysis of the dynamic changes in demand and consumption patterns of wellness tea across different provinces in China. By comprehensively dissecting the sales volume, price, and consumption behaviors of branded wellness tea in various cities and stores on the Taobao platform, it aims to disclose market trends and construct a regression forecast model for sales volume. The results indicate that the price factor (both pre-coupon and post-coupon prices) is the most decisive element influencing sales volume. Geographical regional disparities also exert a certain impact on sales volume, while macroeconomic indicators such as per capita GDP have a relatively minor impact. These discoveries not only provide decision support for market participants in the wellness tea industry, but also provide valuable reference information for policymakers, thereby facilitating the healthy progression of the industry and further tapping into the market potential.

A Generic Approach to Optimize a Blueprint Schedule for Multidisciplinary Group Therapy in Rehabilitation Care

This paper presents generic approach for tactical blueprint scheduling in multidisciplinary rehabilitation care. A blueprint prescribes both the timing of group therapy sessions and the allocation of therapist and treatment room capacity to these sessions and thus defines which appointment types can be booked on which time slots. The blueprint schedule was integrated in a decision support tool, and applied in the rehabilitation center of Sint Maartenskliniek in Nijmegen, the Netherlands.

COMCARE: A Collaborative Ensemble Framework for Context-Aware Medical Named Entity Recognition and Relation Extraction

The rapid expansion of medical information has resulted in named entity recognition (NER) and relation extraction (RE) essential for clinical decision support systems. Medical texts often contain specialized vocabulary, ambiguous abbreviations, synonyms, polysemous terms, and overlapping entities, which introduce significant challenges to the extraction process. Existing approaches, which typically rely on single models such as BiLSTM or BERT, often struggle with these complexities. Although large language models (LLMs) have shown promise in various NLP tasks, they still face limitations in handling token-level tasks critical for medical NER and RE. To address these challenges, we propose COMCARE, a collaborative ensemble framework for context-aware medical NER and RE that integrates multiple pre-trained language models through a collaborative decision strategy. For NER, we combined PubMedBERT and PubMed-T5, leveraging PubMedBERT’s contextual understanding and PubMed-T5’s generative capabilities to handle diverse forms of medical terminology, from standard domain-specific jargon to nonstandard representations, such as uncommon abbreviations and out-of-vocabulary (OOV) terms. For RE, we integrated general-domain BERT with biomedical-specific BERT and PubMed-T5, utilizing token-level information from the NER module to enhance the context-aware entity-based relation extraction. To effectively handle long-range dependencies and maintain consistent performance across diverse texts, we implemented a semantic chunking approach and combined the model outputs through a majority voting mechanism. We evaluated COMCARE on several biomedical datasets, including BioRED, ADE, RDD, and DIANN Corpus. For BioRED, COMCARE achieved F1 scores of 93.76% for NER and 68.73% for RE, outperforming BioBERT by 1.25% and 1.74%, respectively. On the RDD Corpus, COMCARE showed F1 scores of 77.86% for NER and 86.79% for RE while achieving 82.48% for NER on ADE and 99.36% for NER on DIANN. These results demonstrate the effectiveness of our approach in handling complex medical terminology and overlapping entities, highlighting its potential to improve clinical decision support systems.

Multi-Modal Fusion of Routine Care Electronic Health Records (EHR): A Scoping Review

Background: Electronic health records (EHR) are now widely available in healthcare institutions to document the medical history of patients as they interact with healthcare services. In particular, routine care EHR data are collected for a large number of patients.These data span multiple heterogeneous elements (i.e., demographics, diagnosis, medications, clinical notes, vital signs, and laboratory results) which contain semantic, concept, and temporal information. Recent advances in generative learning techniques were able to leverage the fusion of multiple routine care EHR data elements to enhance clinical decision support. Objective: A scoping review of the proposed techniques including fusion architectures, input data elements, and application areas is needed to synthesize variances and identify research gaps that can promote re-use of these techniques for new clinical outcomes. Design: A comprehensive literature search was conducted using Google Scholar to identify high impact fusion architectures over multi-modal routine care EHR data during the period 2018 to 2023. The guidelines from the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) extension for scoping review were followed. The findings were derived from the selected studies using a thematic and comparative analysis. Results: The scoping review revealed the lack of standard definition for EHR data elements as they are transformed into input modalities. These definitions ignore one or more key characteristics of the data including source, encoding scheme, and concept level. Moreover, in order to adapt to emergent generative learning techniques, the classification of fusion architectures should distinguish fusion from learning and take into consideration that learning can concurrently happen in all three layers of new fusion architectures (i.e., encoding, representation, and decision). These aspects constitute the first step towards a streamlined approach to the design of multi-modal fusion architectures for routine care EHR data. In addition, current pretrained encoding models are inconsistent in their handling of temporal and semantic information thereby hindering their re-use for different applications and clinical settings. Conclusions: Current routine care EHR fusion architectures mostly follow a design-by-example methodology. Guidelines are needed for the design of efficient multi-modal models for a broad range of healthcare applications. In addition to promoting re-use, these guidelines need to outline best practices for combining multiple modalities while leveraging transfer learning and co-learning as well as semantic and temporal encoding.

Monitoring Yield and Quality of Forages and Grassland in the View of Precision Agriculture Applications—A Review

The potential of precision agriculture (PA) in forage and grassland management should be more extensively exploited to meet the increasing global food demand on a sustainable basis. Monitoring biomass yield and quality traits directly impacts the fertilization and irrigation practises and frequency of utilization (cuts) in grasslands. Therefore, the main goal of the review is to examine the techniques for using PA applications to monitor productivity and quality in forage and grasslands. To achieve this, the authors discuss several monitoring technologies for biomass and plant stand characteristics (including quality) that make it possible to adopt digital farming in forages and grassland management. The review provides an overview about mass flow and impact sensors, moisture sensors, remote sensing-based approaches, near-infrared (NIR) spectroscopy, and mapping field heterogeneity and promotes decision support systems (DSSs) in this field. At a small scale, advanced sensors such as optical, thermal, and radar sensors mountable on drones; LiDAR (Light Detection and Ranging); and hyperspectral imaging techniques can be used for assessing plant and soil characteristics. At a larger scale, we discuss coupling of remote sensing with weather data (synergistic grassland yield modelling), Sentinel-2 data with radiative transfer modelling (RTM), Sentinel-1 backscatter, and Catboost–machine learning methods for digital mapping in terms of precision harvesting and site-specific farming decisions. It is known that the delineation of sward heterogeneity is more difficult in mixed grasslands due to spectral similarity among species. Thanks to Diversity-Interactions models, jointly assessing various species interactions under mixed grasslands is allowed. Further, understanding such complex sward heterogeneity might be feasible by integrating spectral un-mixing techniques such as the super-pixel segmentation technique, multi-level fusion procedure, and combined NIR spectroscopy with neural network models. This review offers a digital option for enhancing yield monitoring systems and implementing PA applications in forages and grassland management. The authors recommend a future research direction for the inclusion of costs and economic returns of digital technologies for precision grasslands and fodder production.

Assessment of using transfer learning with different classifiers in hypodontia diagnosis

BackgroundHypodontia is the absence of one or more teeth in the primary or permanent dentition during development, and radiographic imaging is the most common method of diagnosis. However, in recent years, artificial intelligence-based decision support systems have been employed to make highly accurate diagnoses. The aim of this study was to classify single premolar agenesis, multiple premolar agenesis, and without tooth agenesis using various artificial intelligence approaches.MethodsOne thousand sixty-eight panoramic radiographs from pediatric patients aged between 6 and 12 years without systemic disease were sorted into three separate classes: single premolar agenesis (n = 336), multiple premolar agenesis (n = 324), and without tooth agenesis (n = 408). Pretrained convolutional neural network models (AlexNet, DarkNet-19, DarkNet-53, DenseNet-201, EfficientNet, GoogLeNet, InceptionV3, IncResV2, MobileNetV2, NasNet-Mobile, Places365, ResNet-18, ResNet-50, ResNet-101, ShuffleNet, SqueezeNet, VGG-16, VGG-19, and Xception) were used for training with the fine-tuning method and different machine learning classifiers (decision trees, discriminant analysis, logistic regression, naive Bayes, support vector machines, nearest neighbor, ensemble method, and artificial neural network). The dataset was divided into 80% for training and 20% for testing. Performance was evaluated via accuracy, recall, precision, F1-score, specificity and area under the curve (AUC) parameters.ResultsAll of the data were classified via a VGG-19 model with a bilayered neural network classifier, which achieved 95.63% accuracy, 93.26% precision, 93.34% recall, 96.73% specificity, 93.25% F1-score and 95.03% AUC and was identified as the most successful model. The accuracy values for this model were distributed as follows: 96.72% for without tooth agenesis, 95.79% for multiple premolar agenesis, and 94.39% for single premolar agenesis.ConclusionsSuccessful results of pretrained models have been demonstrated for the radiographic diagnosis of hypodontia in pediatric patients. It is expected that artificial intelligence approaches will facilitate the diagnosis of hypodontia.

Palliative Care Initiated in the Emergency Department: A Cluster Randomized Clinical Trial.

The emergency department (ED) offers an opportunity to initiate palliative care for older adults with serious, life-limiting illness. To assess the effect of a multicomponent intervention to initiate palliative care in the ED on hospital admission, subsequent health care use, and survival in older adults with serious, life-limiting illness. Cluster randomized, stepped-wedge, clinical trial including patients aged 66 years or older who visited 1 of 29 EDs across the US between May 1, 2018, and December 31, 2022, had 12 months of prior Medicare enrollment, and a Gagne comorbidity score greater than 6, representing a risk of short-term mortality greater than 30%. Nursing home patients were excluded. A multicomponent intervention (the Primary Palliative Care for Emergency Medicine intervention) included (1) evidence-based multidisciplinary education; (2) simulation-based workshops on serious illness communication; (3) clinical decision support; and (4) audit and feedback for ED clinical staff. The primary outcome was hospital admission. The secondary outcomes included subsequent health care use and survival at 6 months. There were 98 922 initial ED visits during the study period (median age, 77 years [IQR, 71-84 years]; 50% were female; 13% were Black and 78% were White; and the median Gagne comorbidity score was 8 [IQR, 7-10]). The rate of hospital admission was 64.4% during the preintervention period vs 61.3% during the postintervention period (absolute difference, -3.1% [95% CI, -3.7% to -2.5%]; adjusted odds ratio [OR], 1.03 [95% CI, 0.93 to 1.14]). There was no difference in the secondary outcomes before vs after the intervention. The rate of admission to an intensive care unit was 7.8% during the preintervention period vs 6.7% during the postintervention period (adjusted OR, 0.98 [95% CI, 0.83 to 1.15]). The rate of at least 1 revisit to the ED was 34.2% during the preintervention period vs 32.2% during the postintervention period (adjusted OR, 1.00 [95% CI, 0.91 to 1.09]). The rate of hospice use was 17.7% during the preintervention period vs 17.2% during the postintervention period (adjusted OR, 1.04 [95% CI, 0.93 to 1.16]). The rate of home health use was 42.0% during the preintervention period vs 38.1% during the postintervention period (adjusted OR, 1.01 [95% CI, 0.92 to 1.10]). The rate of at least 1 hospital readmission was 41.0% during the preintervention period vs 36.6% during the postintervention period (adjusted OR, 1.01 [95% CI, 0.92 to 1.10]). The rate of death was 28.1% during the preintervention period vs 28.7% during the postintervention period (adjusted OR, 1.07 [95% CI, 0.98 to 1.18]). This multicomponent intervention to initiate palliative care in the ED did not have an effect on hospital admission, subsequent health care use, or short-term mortality in older adults with serious, life-limiting illness. ClinicalTrials.gov Identifier: NCT03424109.

KISAN BUDDY

The Kisan Buddy project is a mobile application designed to empower Indian farmers by addressing critical challenges such as limited market access, outdated market prices, and inefficient trade systems. With agriculture being the backbone of India’s economy, improving farmers’ accessibility to real-time data and optimized trade mechanisms is essential for sustainable growth. Despite existing applications, research highlights significant gaps, including a lack of real-time market updates, user-friendly interfaces, and robust decision-making support. Kisan Buddy bridges these gaps by leveraging Firebase Authentication for secure login and registration, Firebase Realtime Database for seamless data management, and Firestore for structured, scalable data storage. The app offers features like real-time mandi price updates, personalized cost estimation, and intuitive navigation to nearby mandis through Google Maps integration. Methodologically, the application integrates advanced mobile technologies, ensuring offline functionality to cater to the diverse needs of Indian farmers. Early testing has demonstrated improved decision-making, market transparency, and accessibility, fostering better economic outcomes. By addressing issues such as market inefficiencies and digital literacy barriers, the app aligns with the United Nations' Sustainable Development Goals, particularly those related to economic growth and reduced inequalities. Kisan Buddy represents a transformative solution, combining innovative technology with user-centric design to enhance agricultural productivity and profitability. This research underscores the potential of digital tools in revolutionizing rural livelihoods, offering a scalable and adaptable framework for improving the socio-economic conditions of farmers in India. The findings highlight its ability to bridge existing gaps and its role in advancing sustainable agricultural practices. Keywords— Android Application Development, Firebase Authentication, Firebase Realtime Database, Firestore Integration, Mandi Recommendations, Google Maps Navigation

Multicomponent Deimplementation Strategy to Reduce Low-Value Preoperative Testing.

Routine preoperative blood tests and electrocardiograms before low-risk surgery do not prevent adverse events or change management but waste resources and can cause patient harm. Given this, multispecialty organizations recommend against routine testing before low-risk surgery. To determine whether a multicomponent deimplementation strategy (the intervention) would reduce low-value preoperative testing before low-risk general surgery operations. This study had a pre-post quality improvement interventional design using interrupted time series and difference-in-difference analytic approaches. The setting was a single academic, quaternary referral hospital with 2 freestanding ambulatory surgery centers and a central preoperative clinic. Included in the study were adult patients undergoing nonurgent outpatient inguinal hernia repairs, lumpectomy, or laparoscopic cholecystectomy between June 2022 and August 2023. Eligible clinicians included those treating at least 1 patient during both the preintervention and postintervention periods. All clinicians were exposed to the multicomponent deimplementation intervention, and their testing practices were compared before and after the intervention. The strategy components were evidenced-based decisional support, multidisciplinary stakeholder engagement, educational sessions, and consensus building with surgeons and physician assistants staffing a preoperative clinic. The primary end point of the trial was the rate of unnecessary preoperative tests across each trial period. A total of 1143 patients (mean [SD] age, 58.7 [15.5] years; 643 female [56.3%]) underwent 261 operations (23%) in the preintervention period, 510 (45%) in the intervention period, and 372 (33%) in the postintervention period. Unnecessary testing rates decreased over each period (intervention testing rate, -16%; 95% CI, -4% to -27%; P = .01; postintervention testing rate, -27%; 95% CI, -17% to -38%; P = .003) and within each test category. The decrease in overall testing was not observed at other hospitals in the state on adjusted difference-in-difference analysis. In this quality improvement study, a multicomponent deimplementation strategy was associated with a reduction in unnecessary preoperative testing before low-risk general surgery operations. The resulting changes in testing practice patterns were not associated with temporal trends within or outside the study hospital. Results suggest that this intervention was effective, applicable to common general surgery operations, and adaptable for expansion into appropriate clinical settings.

Ensemble-based customer churn prediction in banking: a voting classifier approach for improved client retention using demographic and behavioral data

Customer turnover is a crucial issue in banking since maintained profitability depends on keeping clients. This work aims to categorize consumer turnover in banks by using a new ensemble approach combining many machine learning methods, hence enhancing churn prediction models. Using a comprehensive dataset including demographic, financial, and behavioral data—such as credit score, account balance, tenure, and activity levels—the study employs the goal variable revealing if a customer has left the bank. The study starts with univariate, bivariate, and multivariate feature exploration and subsequently uses the Interquartile Range (IQR) approach to identify outliers thereby improving the data quality. Five models—K-Nearest Neighbors, Support Vector Classifier, Random Forest, Decision Tree, and XGBoost—a Voting Classifier ensemble—are used to estimate project churn. Building upon all the strengths of each model, this approach improves the prediction of classification and provides a balanced and highly robust classification system. The applied approaches are K-Nearest Neighbors (KNN), Support Vector Classifier (SVC), Random Forest, Decision Tree, and XGBoost within a Voting Classifier configuration. The performance of the Voting Classifier without SMOTE yields the following results: Accuracy: 0.87, precision: 0.87, recall: 0.80, and F1-Score: 0.87. The proposed model that extend the base model using SMOTE (Synthetic Minority Over-sampling Technique), yields a higher prediction accuracy of 0.90, precision of 0.90, recall of 0.90 and F1-Score of 0.90. This enhancement is proving the efficiency of SMOTE to handle the class imbalance problem in order to render the churn prediction more balanced and reliable system. The proposed approach assures a reliable solution to the strategies to retain the customers in the banking organisations.