Artificial intelligence in supply chain decision-making: an environmental, social, and governance triggering and technological inhibiting protocol

Journal of Modelling in Management, Год журнала: 2023, Номер 19(2), С. 605 - 629

Опубликована: Июль 13, 2023

Purpose Decision-making, reinforced by artificial intelligence (AI), is predicted to become potent tool within the domain of supply chain management. Considering importance this subject, purpose study explore triggers and technological inhibitors affecting adoption AI. This also aims identify three-dimensional triggers, notably those linked environmental, social, governance (ESG), as well inhibitors. Design/methodology/approach Drawing upon a six-step systematic review following preferred reporting items for reviews meta analysis (PRISMA) guidelines, broad range journal publications was recognized, with thematic under lens ESG framework, offering unique perspective on factors triggering inhibiting AI in chain. Findings In environmental dimension, include product waste reduction greenhouse gas emissions reduction, highlighting potential promoting sustainability responsibility. social encompass security quality, well-being, indicating how can contribute ensuring safe high-quality products enhancing societal welfare. involve agile lean practices, cost sustainable supplier selection, circular economy initiatives, risk management, knowledge sharing synergy between demand. The category present challenges, encompassing lack regulations rules, data privacy concerns, responsible ethical considerations, performance assessment difficulties, poor group bias need achieve human decision-makers. Research limitations/implications Despite use PRISMA guidelines ensure comprehensive search screening process, it possible that some relevant studies other databases industry reports may have been missed. light this, selected not fully captured diversity extraction themes from papers subjective nature relies interpretation researchers, which introduce bias. Originality/value research contributes field conducting diverse trigger or inhibit adoption, providing valuable insights into their impact. By incorporating protocol, offers holistic evaluation dimensions associated chain, presenting implications both professionals researchers. originality lies its in-depth examination multifaceted aspects making resource advancing area.

Язык: Английский

---

Exploring the Impact of Artificial Intelligence on Healthcare Management: A Combined Systematic Review and Machine-Learning Approach

Applied Sciences, Год журнала: 2024, Номер 14(22), С. 10144 - 10144

Опубликована: Ноя. 6, 2024

The integration of artificial intelligence (AI) in healthcare management marks a significant advance technological innovation, promising transformative effects on processes, patient care, and the efficacy emergency responses. scientific novelty study lies its integrated approach, combining systematic review predictive algorithms to provide comprehensive understanding AI’s role improving across different contexts. Covering period between 2019 2023, which includes global challenges posed by COVID-19 pandemic, this research investigates operational, strategic, response implications AI adoption sector. It further examines how impact varies temporal geographical addresses two main objectives: explore influences domains, identify variations based Utilizing an we compared various prediction algorithms, including logistic regression, interpreted results through SHAP (SHapley Additive exPlanations) analysis. findings reveal five key thematic areas: enhancing quality assurance, resource management, security, pandemic. highlights positive influence operational efficiency strategic decision making, while also identifying related data privacy, ethical considerations, need for ongoing integration. These insights opportunities targeted interventions optimize current future landscapes. In conclusion, work contributes deeper provides policymakers, professionals, researchers, offering roadmap addressing both

Язык: Английский

---

An interpretable machine learning model for predicting in-hospital mortality in ICU patients with ventilator-associated pneumonia

PLoS ONE, Год журнала: 2025, Номер 20(1), С. e0316526 - e0316526

Опубликована: Янв. 7, 2025

Background Ventilator-associated pneumonia (VAP) is a common nosocomial infection in ICU, significantly associated with poor outcomes. However, there currently lack of reliable and interpretable tools for assessing the risk in-hospital mortality VAP patients. This study aims to develop an machine learning (ML) prediction model enhance assessment Methods extracted patient data from versions 2.2 3.1 MIMIC-IV database, using version training validation, external testing. Feature selection was conducted Boruta algorithm, 14 ML models were constructed. The optimal identified based on area under receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity across both validation test cohorts. SHapley Additive exPlanations (SHAP) analysis applied global local interpretability. Results A total 1,894 patients included, 12 features ultimately selected construction: 24-hour urine output, blood urea nitrogen, age, diastolic pressure, platelet count, anion gap, body temperature, bicarbonate level, sodium mass index, whether combined congestive heart failure cerebrovascular disease. random forest (RF) showed best performance, achieving AUC 0.780 internal 0.724 testing, outperforming other clinical scoring systems. Conclusion RF demonstrated robust performance predicting developed online tool can assist clinicians efficiently risk, supporting decision-making.

Язык: Английский

---

An AI-based multiphase framework for improving the mechanical ventilation availability in emergency departments during respiratory disease seasons: a case study

International Journal of Emergency Medicine, Год журнала: 2024, Номер 17(1)

Опубликована: Апрель 1, 2024

Abstract Background Shortages of mechanical ventilation have become a constant problem in Emergency Departments (EDs), thereby affecting the timely deployment medical interventions that counteract severe health complications experienced during respiratory disease seasons. It is then necessary to count on agile and robust methodological approaches predicting expected demand loads EDs while supporting allocation ventilators. In this paper, we propose an integration Artificial Intelligence (AI) Discrete-event Simulation (DES) design effective ensuring high availability ventilators for patients needing these devices. Methods First, applied Random Forest (RF) estimate probability respiratory-affected entering emergency wards. Second, introduced RF predictions into DES model diagnose response terms ventilator availability. Lately, pretested two different suggested by decision-makers address scarcity resource. A case study European hospital group was used validate proposed methodology. Results The number training cohort 734, test comprised 315. sensitivity AI 93.08% (95% confidence interval, [88.46 − 96.26%]), whilst specificity 85.45% [77.45 91.45%]. On other hand, positive negative predictive values were 91.62% (86.75 95.13%) 87.85% (80.12 93.36%). Also, Receiver Operator Characteristic (ROC) curve plot 95.00% (89.25 100%). Finally, median waiting time decreased 17.48% after implementing new resource capacity strategy. Conclusions Combining helps healthcare elucidate shortening times epidemics pandemics.

Язык: Английский

---

Improving environmental sustainability of intensive care units: A mini-review

World Journal of Critical Care Medicine, Год журнала: 2023, Номер 12(4), С. 217 - 225

Опубликована: Сен. 5, 2023

The carbon footprint of healthcare is significantly impacted by intensive care units, which has implications for climate change and planetary health. Considering this, it crucial to implement widespread efforts promote environmental sustainability in these units. A literature search publications relevant units was done using PubMed. This mini-review seeks equip unit practitioners managers with the knowledge necessary measure mitigate cost critically ill patients. It will also provide an overview current progress this field its future direction.

Язык: Английский

---

Analysing the Balance of Human and Physical Resources in Outpatient Departments during the COVID-19 Pandemic

Production Engineering Archives, Год журнала: 2025, Номер 31(1), С. 65 - 72

Опубликована: Фев. 28, 2025

Abstract The article analyses studies on the impact of COVID-19 pandemic outpatient services in a large hospital, aiming to provide insights for resource management amidst disruptive events. objectives include identifying challenges and proposing solutions optimize service delivery address spatial constraints using discrete-event simulation. Utilizing case study approach, research employs simulation as key methodology analyse scenarios. Scenarios are generated by combining different probabilities patient return check-in with various team parameterizations. researchers analysed historical data performance indicators from focuses collaborative approach hospital ensure relevance applicability proposed solutions. identifies bottlenecks induced social distancing measures, particularly reception areas. Uneven distribution throughout day leads misallocation resources reduction available physical space. Telemedicine emerges significant response, effectively addressing both optimization physicians’ workload despite constraints. Additionally, underscores role crisis decision-making operations management. Practical applications emanating emphasize need healthcare institutions adopt adaptable strategies leverage tools effective during Hospital administrators can draw inform reallocation workflow optimization, focus negotiating flexible scheduling exploring telemedicine enhance delivery.

Язык: Английский

---

The Contributions of Artificial Intelligence to the Optimization of the Dynamics of Supply Chains 4.0

Lecture notes in networks and systems, Год журнала: 2025, Номер unknown, С. 89 - 97

Опубликована: Янв. 1, 2025

Язык: Английский

---

The paradigm of digital health: AI applications and transformative trends

Neural Computing and Applications, Год журнала: 2025, Номер unknown

Опубликована: Март 15, 2025

Язык: Английский

---

A literature review of supply chain analyses integrating discrete simulation modelling and machine learning

Journal of Simulation, Год журнала: 2025, Номер unknown, С. 1 - 25

Опубликована: Май 20, 2025

Язык: Английский

---

Transforming Disease Surveillance through Artificial Intelligence

Indian Journal of Community Medicine, Год журнала: 2024, Номер 49(5), С. 663 - 664

Опубликована: Авг. 13, 2024

Artificial intelligence (AI), or machine learning, is an ancient concept based on the assumption that human thought and reasoning can be mechanized. In era where rapid disease detection response are critical, Intelligence (AI) offers unique opportunities to enhance surveillance. Traditional surveillance methods, often limited by manual data collection slow reporting, significantly improved AI's ability analyze vast amounts of in real-time. AI-driven predict outbreaks early, monitor spread, provide timely information health authorities, improving public outcomes. ENHANCING OUTBREAK PREDICTION AI help outbreaks, identify high-risk areas progression. Predicting accurately promptly crucial for effective responses. methods outbreak prediction rely historical which reactive. transform this landscape with its capacity real-time from diverse sources such as social media, internet searches, Electronic Health Records (EHRs). These insights into trends, enabling detect early signs outbreaks. For instance, models flu one two weeks earlier than traditional combining search engines, sources.[1] Evidence suggests Twitter used establishing a strong correlation between tweet volumes related symptoms actual data, indicating potential media warning system.[2] also leverage Wikipedia global activity analyzing page views diseases valuable patterns, highlighting unconventional surveillance.[3] Utilizing capability allows preventive measures, reducing spread impact diseases. assist vaccine development predicting how virus other causative agents will evolve mutate over time. Researchers use develop targeted vaccines. MONITORING DISEASE SPREAD Once occurs, monitoring containment. track transmission patterns real-time, offering spreading. The recent COVID-19 pandemic infectious have highlighted importance technology. Predictions future developments include emerging technologies quantum computing, biosensors, augmented intelligence, large language models, unstructured text, streamline labor-intensive processes, trends tracking using multiple sources, including travel has already been proven.[4,5] This approach provided mapping virus's trajectory, aiding officials their efforts. Studies effectiveness hidden geometry contagion phenomena modeling network-driven providing deeper understanding propagate across different regions.[6] epidemiological incorporating advanced analytics. simulate various scenarios, helping make informed decisions. PROVIDING TIMELY ALERTS not only predicts monitors but disseminates critical healthcare providers basis. By systems anomalies, alerts about emergence new resurgence existing one. quickly relayed providers, them prepare respond more effectively. evidence shows system EHRs timeliness reporting reduce delays diseases, allowing quicker responses.[7] keyword surges web. Specialized queries correct false alarms, accuracy reliability web-based systems.[8] OPTIMIZING RESOURCE ALLOCATION optimize resource allocation prevalence, population demographics, infrastructure. optimization algorithms allocate resources vaccines, medications, medical equipment current projected needs. minimizes waste ensures they most impact. efficiency translates significant cost savings, especially resource-constrained settings. convergence algorithms, big analytics, learning techniques empowered care companies extract datasets, lead accurate diagnostics, personalized treatment plans, enhanced patient research become established academic discipline within philosophy, mathematics, engineering, physics, biological sciences, debate regarding uses hazards. Brandeau et al.[9] (2009) discussed disaster responses health. Their position paper recommended AI-based approaches optimizing during emergencies. forecast demand hospital beds ventilators pandemic.[10] CHALLENGES Although numerous benefits, it raises ethical privacy concerns. involves handling sensitive data. Protecting security paramount. Robust legal technical measures must place safeguard personal prevent misuse. Pieces challenges medicine need transparency, accountability, safeguards protect individual initiatives.[11] addition, depends quality trained on. Biases inaccurate predictions unequal outcomes.[12] Developing transparent unbiased essential reliable now technology all medicine. concerns should recognized addressed guidelines use. Therefore, complement human-curated ones, field clinical evolving. However, despite many limitations concerns, may bring apparent benefits diagnosis Thus, enhancing prediction, information, allocation. addressing fully realizing With careful implementation oversight, indispensable safeguarding worldwide.

Язык: Английский

---