Decision Algorithm Research Articles

Simplifying nasal reconstruction after Mohs surgery: an algorithm based on review of over 400 cases.

Literature on reconstruction techniques for post-Mohs nasal defects with particular emphasis on the unique properties of underlying skin is lacking. We aimed to develop an algorithm to simplify the approach to post-Mohs reconstruction of the nose based on defect size, location, and cutaneous features of the surrounding skin. Retrospective review of 404 patients who underwent post-Mohs nasal reconstruction by a single Mohs surgeon between 2018 and 2024 was conducted. Defects were divided into small, medium, and large sizes. Locations were categorized into 3 zones based on cutaneous characteristics. Frequency of reconstructive techniques based on defect size and location was analyzed. Trends towards specific repairs based on the cutaneous location and size of Mohs defects were utilized to develop an algorithm for reconstructive decision making. This algorithm was based on zones defined by cutaneous characteristics, and may serve as an initial guide for surgeons planning reconstruction of nasal defects.

Decision optimization in the linked electricity market at multi-timescale: Integrating coupled tradable green certificate and green power trading.

Achieving the national climate target would depend on national actions. China has implemented important market mechanisms for a green and low-carbon energy transition, including the Renewable Portfolio Standard (RPS), the Tradable Green Certificate (TGC) market, the green power trading market, and so on. However, how to effectively integrate coupled TGC and green power trading to achieve a balance between maximizing economic benefits and environmental friendliness remains to be explored. Therefore, this study extends prior research by establishing a bi-level decision optimization model to explore market participants' decision making from the perspective of energy supply and economic value, and analyzes the impact of the RPS, TGC price, and the penetration of renewable energy (RE) in the electricity market, the green power market, and the trading strategy of market participants in a multi-market equilibrium state. The feasibility and effectiveness of the bi-level decision optimization model and algorithm are verified using the example of IEEE14 node and historical data of Elia Energy. The results show that: (1) Under the market equilibrium condition, the clearing price in the day-ahead RE market is equal to the clearing price in the day-ahead traditional energy market plus the TGC price. (2) When green power participates in the spot market, there is a complementary relationship between RE generation and traditional energy generation. (3) A shift from decreasing to increasing costs for electricity consumers when RE penetration is above a certain threshold (α>30%) and the TGC price is 100 CNY/MWh, and a decrease in the growth rate of RE generators' profits when RE penetration is above a certain threshold (α>35%). (4) Traditional energy generators with small installed capacities adopt riskier market behaviors to declare more electricity and try to obtain higher profit in market transactions. These insights can make up for the research gap of decision optimization in multi-timescale electricity market, achieve energy optimization allocation and environmental sustainability.

Integrating EAHX and ventilation systems through a decision-making algorithm for enhanced energy efficiency and thermal comfort in smart buildings

Integrating EAHX and ventilation systems through a decision-making algorithm for enhanced energy efficiency and thermal comfort in smart buildings

Adapt to survive and thrive: the time is now for adaptive platform trials for preterm birth.

In this Viewpoint, we discuss the challenges facing perinatal clinical researchers, many of which are unique to this field, and how traditional two-arm randomised trials using frequentist analysis might no longer be fit for purpose for perinatology. We propose a solution: the adoption of adaptive platform trials (APTs) with Bayesian methodology to address perinatal research questions to improve outcomes of preterm birth. APTs use a master protocol as a foundation to efficiently assess multiple interventions simultaneously for a particular disease. APTs can study these interventions in a perpetual manner, with interventions allowed to enter or leave the platform on the basis of preplanned decision algorithms. In this Viewpoint, we outline the ways in which APTs can overcome some of the issues facing perinatal clinical research, and the challenges and essential requirements for the design and implementation of perinatal APTs that should be considered.

P-202. 7- Year experience with Clostridioides difficile Infection (CDI): pre- and post-COVID-19 pandemic, effect of diagnostic stewardship and the gender difference

Abstract Background Diagnostic stewardship interventions, such as order sets, reflex orders, hard and soft stop alerts and decision algorithms have shown to improve facility C. difficile rates. We aimed to examine the impact of COVID-19 infection and diagnostic stewardship on incidence and prevalence of CDI at our institution, based on gender. Methods Using National Healthcare Safety Network (NHSN) surveillance Laboratory Identification (Lab ID) events, 926 CDI cases, ≥ 18 years of age were identified among patients hospitalized at Hurley Medical Center from 01/2015 to 07/2022. NHSN surveillance definitions were used to describe the incident, recurrent cases and determine the epidemiologic categories. Hospital onset (HO) incident rate is described as per 10,000 patient days and inpatient community-onset (CO) CDI prevalence rate described as per 10,000 admissions (Figure 1).Table 1:Diagnostic stewardship and infection control interventions Results During the 7.6-year study period, overall HO CDI incident rate and inpatient CO CDI prevalence rate decreased, a percentage decrease of 34% and 53% respectively. The rates were lowest in 2020, onset of COVID-19 pandemic (percentage decrease of 22% for HO CDI incident and 7% for CO CDI prevalence rates as compared to 2019 pre-COVID-19 pandemic). There was a transient increase in 2021 (percentage increase of 36% for HO CDI incident and 14% for CO CDI prevalence rates as compared to 2019) (Figure 2, 3). HO CDI incident rates were slightly higher in men (average 11.4% difference) as compared to women except in 2017. CO CDI prevalence rates were much higher in women as compared to the men (average 13.4% difference) with the exception of 2017 and 2022.Figure 2:HO CDI Incidence rate 2015-2022, with 95% confidence intervals Conclusion HO CDI incident rate and inpatient CO CDI prevalence rates were lowest in 2020 (the onset of COVID-19 pandemic), likely secondary to computerized clinical decision support (CCDS) interventions introduced in 2019 (Table 1). The transient increase in rates seen in 2021, was likely due to increase in antibiotic utilization during the pandemic. Diagnostic stewardship played a key role in optimizing the diagnosis of CDI and improving CDI rates at our institution. There was a discrepancy of the CO CDI and HO CDI rates between the sexes, likely owing to the higher outpatient antibiotic use in women as compared to men, highlighting the importance of ambulatory stewardship.Figure 3:Inpatient CO CDI prevalence rate, with 95% confidence intervals Disclosures All Authors: No reported disclosures

Selection of sampling sites in Germany for the International Moss Survey 2020 using statistics and decision modelling

BackgroundAfter 1990, 1995, 2000, 2005 and 2015, Germany participated in the International Moss Monitoring 2020 (MM2020). The German contribution to MM2020 aimed at pilot studies on the suitability of bioindication with mosses for recording the atmospheric deposition of persistent organic pollutants and microplastics.ResultsThis investigation was based on moss samples collected at 25 sites in Germany: Eight sites at which concentrations of persistent organic pollutants were determined in the Moss Survey 2015 were included. In addition, twelve sites were selected from the pool of the total of 400 moss collection sites in 2015. Further five sites of the German moss monitoring network 2015 were added, at which moss samples were collected in 2020 for developing the sample preparation and for preliminary investigations. The selection of the five test sites was based on the same criteria as for the 20 target sites of the 2020 monitoring to make the analysis data of the test phase usable for later evaluations. To ensure methodological transparency and objectivity, a procedure based on statistical methods and decision modelling was developed for this purpose. The decision algorithm enabled taking into account a large number of technical criteria. Selected features of the three subsamples comprising 8, 20 and 25 sites were compared with those of the full sample (n = 400 sites of Moss Survey 2015) and inferentially tested whether the thinning of the 2015 sampling network (n = 400) to 8, 20 and 25 sites, respectively, leads to significant changes in its information quality or not.ConclusionsMethods of decision modelling and inferential statistics have proven their worth for transparently restructuring the moss monitoring network.

The diagnosis and management of acute traumatic diaphragmatic injury: A Western Trauma Association clinical decisions algorithm.

The diagnosis and management of acute traumatic diaphragmatic injury: A Western Trauma Association clinical decisions algorithm.

Small pulmonary nodule localization techniques in the era of lung cancer screening: a narrative review.

The widespread adoption of high-resolution computed tomography (CT) screening has led to increased detection of small pulmonary nodules, necessitating accurate localization techniques for surgical resection. This review examines the evolution, efficacy, and safety of various localization methods for small pulmonary nodules. Studies focusing on localization techniques for pulmonary nodules ≤30 mm in diameter were included, with emphasis on technical success rates and complication profiles. Preoperative CT-guided techniques, including hook-wire (success rate 94-98%) and anchored needle localization (success rate >99%, dislodgement rate 0%) demonstrate high technical success rates, though with varying complication profiles. Microcoil localization (97-98% success) shows comparable efficacy with lower complication rates. Dye-based methods offer simplicity but can be limited by rapid diffusion. Newer techniques like medical adhesive localization (success rate up to 100%) and electromagnetic navigation bronchoscopy (97.2% success) show promise in reducing complications and improving accuracy. Intraoperative methods such as ultrasound and hybrid operating room approaches provide real-time guidance but may be limited by nodule characteristics and available expertise. This review presents a radar chart analysis comparing techniques across key parameters and introduces an innovative decision-making algorithm that considers nodule characteristics, patient factors, and institutional resources, providing practical guidance and serving as a reference for clinicians. While no single method is universally superior, the trend towards minimally invasive, precise, and flexible approaches is evident. Future research should focus on large-scale comparative studies and the integration of artificial intelligence for optimized technique selection and improved patient outcomes.

Automatic Watering System on Microcontroller-Based Tomato Plants With The Fuzzy Logic Approach

One of the main challenges in crop cultivation is addressing irrigation issues, which are often carried out conventionally. This research aims to tackle this problem by implementing fuzzy logic in the development of an automatic irrigation system for tomato plants based on a microcontroller. The system is designed to create an intelligent irrigation solution capable of adjusting water supply according to environmental conditions and the needs of tomato plants. The research methodology includes system design, environmental data collection, and implementation of fuzzy logic algorithms for decision-making. The research findings demonstrate the effectiveness of the fuzzy logic-based approach in optimizing irrigation schedules, resulting in improved plant health and water conservation. Thus, the conclusion emphasizes the potential of fuzzy logic in enhancing precision farming practices and underscores the importance of adaptive irrigation systems in supporting sustainable crop production.

Multi-Objective Optimization Design of PCS Box Girder Bridges with Small and Medium Spans Using Genetic Algorithms

With the development of algorithms for autonomous decision-making in the field of structural engineering, the design of precast concrete segment (PCS) box girder bridges faces new challenges. This paper proposes using a multi-objective optimization method based on genetic algorithms for the rapid design of PCS box girder bridges with small and medium spans. By considering 20 design parameters such as the physical dimensions of the box girder cross-section, material properties, and prestressing parameters, the paper formulates and quantifies three objective functions: cost, safety, and structural performance. The multi-objective optimization was conducted using four optimization algorithms (NSGA-II, NSGA-III, GDE3, and PSO). An optimization evaluation index (φ[F(x)]) was established and weights were assigned to different optimization objectives. A specific design case based on the general diagram of a 3 × 25 m-long continuous PCS box girder bridge was carried out. The results indicate that genetic algorithms performed exceptionally well on this problem, with the NSGA-III algorithm achieving the best φ[F(x)] value of 0.2789 among all algorithms. A performance analysis was conducted on various optimization models using box plots and sensitivity studies. Scatter plots and surface plots of the Pareto front of the optimized solutions were generated, and corresponding cross-sectional design drawings were created based on the two proposed solutions. Compared with the general graph, the design cases provided by the NSGA-III algorithm model have a change rate of 8.03%, −0.29%, and 75.49% in the three optimization objectives, respectively, indicating a significant improvement effect. The research content of this paper provides a reasonable direction for future studies on intelligent bridge design methodologies.

Clinical use of measurable residual disease in adult ALL: recommendations from a panel of U.S. experts.

Measurable residual disease (MRD) is a powerful predictor of clinical outcomes in acute lymphoblastic leukemia (ALL). In addition to its clear prognostic importance, MRD information is increasingly used in clinical decision algorithms to guide therapeutic interventions. While it is well-established that achievement of MRD-negative remission is an important endpoint of ALL therapy, the prognostic and therapeutic implications of MRD in an individual patient are influenced by both disease-related factors (e.g. cytomolecular risk) and assay-related factors (e.g. sensitivity, specimen source, and timing of assessment), which add complexity to MRD-guided treatment decisions. In this review, we discuss the data supporting the use of MRD assessment in adult ALL and how this information can rationally inform clinical decisions, including selection of patients for MRD-directed therapies or allogeneic hematopoietic stem cell transplantation. We also discuss important interpretative challenges related to novel high sensitivity next-generation sequencing-based MRD assays, which are becoming increasingly used in clinical practice.

Schools of AI in the Public Sector: Fairness and Accountability Concerns

As decision-making algorithms become more prevalent in society, the importance efficiency and problem-solving abilities come into question when predictions impact individuals’ lives. High-risk applications require trusted AI systems to be designed with fairness and accountability; such trust and consideration is essential for public acceptance and successful deployment. Despite growing advocacy for ethical and trustworthy AI, along with the emergence of guidelines like the EU AI Act, controversies surrounding AI persist in the media. Public sector AI systems are being implemented haphazardly, whether in judicial decision-making, healthcare diagnostics, or social welfare distribution. These high-risk applications directly affect citizens’ quality of life, highlighting the need for a critical assessment of how AI are being designed and deployed in the public sector. My thesis explores the integration of fairness, accountability, and uncertainty in public sector AI to assess whether these systems are appropriately designed, effectively adapted, and capable of enhancing societal well-being. The research aims to provide actionable insights for designing AI systems that align with public sector needs and maximize societal benefits.

Improving Industrial Quality Control: A Transfer Learning Approach to Surface Defect Detection.

To automate the quality control of painted surfaces of heating devices, an automatic defect detection and classification system was developed by combining deflectometry and bright light-based illumination on the image acquisition, deep learning models for the classification of non-defective (OK) and defective (NOK) surfaces that fused dual-modal information at the decision level, and an online network for information dispatching and visualization. Three decision-making algorithms were tested for implementation: a new model built and trained from scratch and transfer learning of pre-trained networks (ResNet-50 and Inception V3). The results revealed that the two illumination modes employed widened the type of defects that could be identified with this system, while maintaining its lower computational complexity by performing multi-modal fusion at the decision level. Furthermore, the pre-trained networks achieved higher accuracies on defect classification compared to the self-built network, with ResNet-50 displaying higher accuracy. The inspection system consistently obtained fast and accurate surface classifications because it imposed OK classification on models trained with images from both illumination modes. The obtained surface information was then successfully sent to a server to be forwarded to a graphical user interface for visualization. The developed system showed considerable robustness, demonstrating its potential as an efficient tool for industrial quality control.

Integrating collision avoidance strategies into multi-robot task allocation for inspection

Recent research topics have been placed on reinforcing security and safety measures within high-risk industries to protect both equipment and the environment. Numerous industries carry substantial implications for their surroundings. During significant incidents like chemical spills, or nuclear accidents, swiftly gathering precise and dynamic data poses a considerable challenge. Subsequently, this paper focuses on optimizing a mission involving multiple mobile robots charged with inspecting an industrial zone. The aim of this research is to efficiently collect measurements from diverse positions using a fleet of sensing robots operating from a central depot, that is, developing an algorithm for robot decision-making that optimizes mission planning by minimizing an objective function. Initially, we explore our previous proposed solutions and we improve the system by integrating a navigational layer to manage collision avoidance between robots. Then, we delve into scenarios involving multiple homogeneous tasks distributed in a limited geographical environment. To demonstrate feasibility, extensive simulations, numerical experiments, and comparative analysis are conducted, showing the efficiency of the proposed approaches in terms of solution quality and computational complexity.

Novel distance measure for q-rung orthopair fuzzy sets and its application

In this paper, we explore the q-rung orthopair fuzzy set (q-ROFS) framework to effectively manage complex and uncertain information, particularly in scenarios where human opinions and preferences play a critical role. Recognizing the limitations of existing methods in capturing the inherent vagueness of such information, we propose a novel and robust distance measure tailored specifically for q-ROFS. To demonstrate the practical relevance of our proposed measure, we focus on its application to the selection of financial investment funds, a problem characterized by significant uncertainty and subjective evaluation criteria. Within this context, we develop a decision-making algorithm based on the q-ROFS framework. The algorithm leverages the new distance measure to identify an optimal fund from a set of alternatives by analyzing key financial and non-financial attributes. We further validate the effectiveness of our approach by presenting a detailed numerical example that simulates a real-world investment scenario. Comparative analyses with existing decision-making methods are conducted to underscore the improvements in accuracy, flexibility, and overall performance that our approach offers. The results suggest that the proposed q-ROFS-based algorithm is not only capable of handling uncertainty more effectively but also provides enhanced decision-making insights, making it a valuable tool for complex decision-making tasks in finance and beyond.

Matrix Theory Approach to Fuzzy Hypersoft Set in Multi-Criteria Airline Selection

When we talk about decision-making then it means we have to tackle the attributes and alternatives, and it becomes difficult when attributes are further subdivided. The hypersoft theory allows us to handle further bifurcated attributes. This paper is aim to provide the legal way to deal with multi-criteria decision-making (MCDM) problems in the sense of further subdividing attributes by applying the concept of fuzzy hypersoft matrices (FHSM’s). Since matrices provide us with a fast and reliable way to solve problems. In this paper, we have proposed the concept of FHSM with their operators, theorems, propositions, and decision-making (DM) algorithms. The proposed algorithms have been supported with real-life application of airline selection while you have to take any flight. The concept of further bifurcation gives more accurate and refined results than the existing techniques, along with the implication of FHSM. In the future, the proposed concept can be implemented in other hybrids of hypersoft set theory with DM algorithms. The challenges faced in implication can be dealt with machine learning algorithms for fast and more accurate results.

Innovative Research on Physical Data Management of Football Players Under the Background of Smart Medical Treatment

With the intensification of the competition for public medical resources and the rapid development of smart medical technology, the demand for in-depth analysis of athletes’ basic information and decision support is growing day by day. However, the practice of applying smart medicine to athletes’ physical information management is still relatively limited. This paper aims to explore how to use smart medical decision technology to build an integrated athlete physical information management and decision support platform. Taking football players as the research object, this paper integrates data mining technology into a smart medical decision-making model, to achieve accurate analysis and effective management of athletes’ physical fitness information. The core of the research is to develop a smart healthcare decision model that can identify key information and patterns on the platform through data mining technology. In the selection of the decision algorithm, this paper adopts cluster analysis and association rule mining algorithms, which can deeply dig into the potential rules and correlations in the data. Through the application of an algorithm, we can accurately evaluate the physical condition of football players, and provide scientific guidance and suggestions for their subsequent physical training. The algorithm in this study is not only innovative in theory, but also shows good adaptability and effectiveness in practical application.

The environmental impact of inhalers: a framework for sustainable prescription practices in Spain

BackgroundThe healthcare sector contributes significantly to global greenhouse emissions, with inhalers being major contributors.ObjectiveTo develop a framework for reducing the environmental footprint of inhalers in Spain by implementing greener prescription...

The use of a decision-making tool to optimise physiotherapy practice for patients following chest trauma: Impact on patient and hospital outcomes

Introduction Physiotherapy management for patients with blunt chest wall trauma is key for improving respiratory and functional status. Utilising a physiotherapy-specific treatment decision-making pathway, based on risk assessment, may optimise resource use and improve patient-based outcomes. Methods Patients with blunt chest trauma admitted to the trauma ward of a level 1 trauma centre were triaged utilising the STUMBL score (a risk assessment tool specific for blunt chest trauma) and managed as per a treatment algorithm whereby high-risk patients received intensive physiotherapy. Demographic data were described and analysis of patient and hospital outcomes was undertaken comparing the low and high risk groups. A regression analysis was completed to review the association between the groups and length of stay (LOS), taking into account confounding factors. Results Over the 10-month period beginning in November 2020, there were 539 patients admitted following chest trauma of which 333 (62%) were stratified as high-risk. These high-risk patients were older, more likely to be frail and live alone and more likely to have an ICU admission. There was a similar rate of discharge home across both groups ( p = 0.55) and there was no difference between groups in the hospital LOS of patients after accounting for the confounders. Conclusion Utilising a physiotherapy decision-making algorithm based on risk assessment can facilitate the targeting of high-risk patients to receive intensive physiotherapy. This high-risk group showed similar rates of discharge home despite being a more frail, elderly population with a greater ICU admission rate. The algorithm was easy to use and may be an avenue for improved resource utilisation.

Lower Extremity Soft Tissue Defect Reconstruction Using the SCIP Free Flap: A Comprehensive Review

The reconstruction of lower extremity soft tissue defects requires a flap capable of covering vital foot structures while withstanding the stresses of walking and shoe pressure. The Superficial Circumflex Iliac Artery Perforator (SCIP) flap provides finely detailed tissue and minimal donor site sequelae. Its surgical technique is safe, accessible, and benefits from preoperative echo-Doppler mapping for enhanced precision. The SCIP flap's numerous advantages make it an essential component in the plastic surgeon's decision-making algorithm for lower extremity soft tissue reconstruction, offering a renewed perspective on inguinal donor site management.