Enhancing Efficiency in the Healthcare Sector Through Multi-Objective Optimization of Freight Cost and Delivery Time in the HIV Drug Supply Chain Using Machine Learning

Systems, Journal Year: 2025, Volume and Issue: 13(2), P. 91 - 91

Published: Jan. 31, 2025

The purpose of this paper is to examine the optimization HIV drug supply chain, with a dual focus on minimizing freight costs and delivery times. With help dataset containing 10,325 instances chain transactions, key variables, including “Country”, “Vendor INCO Term”, “Shipment Mode”, were examined in order develop predictive model using Artificial Neural Networks (ANN) employing Multi-Layer Perceptron (MLP) architecture. A set ANN models trained forecast “freight cost” “delivery time” based four principal design variables: “Line Item Quantity”, “Pack Price”, “Unit Measure (Per Pack)”, “Weight (Kilograms)”. According performance metrics analysis, these demonstrated accuracy following training. An algorithm, configured an “active-set” was then used minimize combined objective function cost time. Both times significantly reduced as result optimization. This study illustrates potent application machine learning algorithms enhancement efficiency. provides blueprint for reduction improved service critical medication chains methodology outcomes.

Language: Английский

---

Access Denied: Meaningful Data Access for Quantitative Algorithm Audits

Published: April 25, 2025

Independent algorithm audits hold the promise of bringing accountability to automated decision-making. However, third-party are often hindered by access restrictions, forcing auditors rely on limited, low-quality data. To study how these limitations impact research integrity, we conduct audit simulations two realistic case studies for recidivism and healthcare coverage prediction. We examine accuracy estimating group parity metrics across three levels access: (a) aggregated statistics, (b) individual-level data with model outputs, (c) without outputs. Despite selecting one simplest tasks algorithmic auditing, find that minimization anonymization practices can strongly increase error rates data, leading unreliable assessments. discuss implications independent auditors, as well potential avenues HCI researchers regulators improve enable both reliable holistic evaluations.

Language: Английский

---

Transforming the NHS through AI-driven solutions: a new era of digital health

Postgraduate Medical Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 30, 2025

Journal Article Transforming the NHS through AI-driven solutions: a new era of digital health Get access Mohamed A Imam, Imam Rowley Bristow Unit, Trauma & Orthopaedics, Ashford and St. Peter's Hospitals Foundation Trust, Guildford Rd, Lyne, Chertsey, KT16 0PZ, United KingdomSmart Health Centre, University East London, Way, E16 2RD, Kingdom Search for other works by this author on: Oxford Academic Google Scholar Ahmed Elgebaly, Elgebaly Smart Corresponding author. UK. E-mail: [email protected] https://orcid.org/0000-0002-8324-0960 Adam Zumla, Zumla Royal Bolton Hospital, Minerva Farnworth, Greater Manchester, BL4 0JR, Shyam Kolvekar, Kolvekar Barts Heart St Bartholomew's W Smithfield, City EC1A 7BE, Rizwan Ahmed, Alimuddin Department Infection, Centre Clinical Microbiology, Division Infection Immunity, College Gower St, WC1E 6BT, KingdomDepartment London Postgraduate Medical Journal, qgaf023, https://doi.org/10.1093/postmj/qgaf023 Published: 15 February 2025 history Received: 08 January Accepted: 29

Language: Английский

---

Evaluation of Large Language Models' Concordance With Guidelines on Olfaction

Laryngoscope Investigative Otolaryngology, Journal Year: 2025, Volume and Issue: 10(2)

Published: March 22, 2025

ABSTRACT Objective To assess the concordance of artificial intelligence (AI)‐generated information with 2022 International Consensus Statement on Allergy and Rhinology: Olfaction (ICAR‐O). Methods Forty‐two guidelines were extracted from ICAR‐O. Each guideline was converted into a question, which presented to ChatGPT version 4.o Google Gemini. Concordance deemed an agreement between AI response clinical recommendation. Credibility granted if platform provided credible resource. Accuracy graded Likert scale (0: entirely inaccurate information, 1: mix accurate 2: information). Statistical analysis performed. Results A total 84 responses generated. The mean accuracy Gemini 1.85 1.48 out 2, respectively, indicating that contained information. significantly more than ( p = 0.001). Of responses, 78.57% N 33) concordant ICAR‐O 100% 42) cited 66.67% 28) 97.62% 41) There no significant differences in 0.22) or credibility 0.31) platforms. Conclusion olfaction. However, overall, both platforms did not consistently align guidelines. require further evaluation before implementation use as educational adjuncts. Level Evidence N/A.

Language: Английский

---

Establishing Artificial Intelligence-Powered Virtual Tumor Board Meetings in Pakistan

Cancer Control, Journal Year: 2025, Volume and Issue: 32

Published: Feb. 1, 2025

Equitable cancer care in low- and middle-income countries is crucial as mortality rates continue to rise. Artificial intelligence (AI)-powered Virtual Tumor Board Meetings (VTBMs) offer an innovative solution that facilitates real-time collaboration between experts improve patient outcomes. By integrating AI-powered tools, VTBMs can diagnostic accuracy personalize treatment plans using various data sources such medical images genomic profiles. In Pakistan, with limited healthcare resources a high economic burden, the introduction of has potential revolutionize care. This strategic approach will not only address current challenges but also serve model for improving developing countries.

Language: Английский

---

Enhancing skin lesion classification: a CNN approach with human baseline comparison

PeerJ Computer Science, Journal Year: 2025, Volume and Issue: 11, P. e2795 - e2795

Published: April 15, 2025

This study presents an augmented hybrid approach for improving the diagnosis of malignant skin lesions by combining convolutional neural network (CNN) predictions with selective human interventions based on prediction confidence. The algorithm retains high-confidence CNN while replacing low-confidence outputs expert assessments to enhance diagnostic accuracy. A model utilizing EfficientNetB3 backbone is trained datasets from ISIC-2019 and ISIC-2020 SIIM-ISIC melanoma classification challenges evaluated a 150-image test set. model’s are compared against 69 experienced medical professionals. Performance assessed using receiver operating characteristic (ROC) curves area under curve (AUC) metrics, alongside analysis resource costs. baseline achieves AUC 0.822, slightly below performance experts. However, improves true positive rate 0.782 reduces false 0.182, delivering better minimal involvement. offers scalable, resource-efficient solution address variability in image analysis, effectively harnessing complementary strengths humans CNNs.

Language: Английский

---

Integrating Technology into Clinical Practice

Published: Jan. 1, 2025

Language: Английский

---

Unlocking the Potential of AI in Healthcare

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 467 - 492

Published: May 9, 2025

The infusion of artificial intelligence (AI) in healthcare is one the most far-reaching changes modern medicine. This chapter explore how AI-empowered technology has dramatically reshaped clinical decision making, diagnosis and treatment organization systems. It also looks at changing behaviors resulting from these advances, such as slow uptake on useful research findings that are difficult to translate into practice or widespread non-adoption evidence-based guidelines among poorer-performing hospitals. takes a comprehensive critical look key innovations have shaped AI, taking machine learning algorithms for disease prediction, natural language processing (NLP) extract data free text, AI-assisted robotic systems surgical operations.

Language: Английский

---

The Frontiers of Smart Healthcare Systems

Healthcare, Journal Year: 2024, Volume and Issue: 12(23), P. 2330 - 2330

Published: Nov. 21, 2024

Artificial Intelligence (AI) is poised to revolutionize numerous aspects of human life, with healthcare among the most critical fields set benefit from this transformation. Medicine remains one challenging, expensive, and impactful sectors, challenges such as information retrieval, data organization, diagnostic accuracy, cost reduction. AI uniquely suited address these challenges, ultimately improving quality life reducing costs for patients worldwide. Despite its potential, adoption in has been slower compared other industries, highlighting need understand specific obstacles hindering progress. This review identifies current shortcomings explores possibilities, realities, frontiers provide a roadmap future advancements.

Language: Английский

---

Structural Heart Disease in the Tropics: A Comprehensive Review

Current Problems in Cardiology, Journal Year: 2024, Volume and Issue: 50(3), P. 102975 - 102975

Published: Dec. 18, 2024

Language: Английский

---