Exploring Artificial Intelligence Biases in Predictive Models for Cancer Diagnosis

Cancers, Journal Year: 2025, Volume and Issue: 17(3), P. 407 - 407

Published: Jan. 26, 2025

The American Society of Clinical Oncology (ASCO) has released the principles for responsible use artificial intelligence (AI) in oncology emphasizing fairness, accountability, oversight, equity, and transparency. However, extent to which these are followed is unknown. goal this study was assess presence biases quality studies on AI models according ASCO examine their potential impact through citation analysis subsequent research applications. A review original articles centered evaluation predictive cancer diagnosis published journal dedicated informatics data science clinical conducted. Seventeen bias criteria were used evaluate sources studies, aligned with ASCO’s oncology. CREMLS checklist applied quality, focusing reporting standards, performance metrics along counts included analyzed. Nine included. most common environmental life-course bias, contextual provider expertise implicit bias. Among principles, least adhered transparency, oversight privacy, human-centered application. Only 22% provided access data. revealed deficiencies methodology reporting. Most reported within moderate high ranges. Additionally, two replicated research. In conclusion, exhibited various types deficiencies, failure adhere oncology, limiting applicability reproducibility. Greater accessibility, compliance international guidelines recommended improve reliability AI-based

Language: Английский

---

Advances in Non-Small Cell Lung Cancer: Current Insights and Future Directions

Journal of Clinical Medicine, Journal Year: 2024, Volume and Issue: 13(14), P. 4189 - 4189

Published: July 18, 2024

The leading cause of cancer deaths worldwide is attributed to non-small cell lung (NSCLC), necessitating a continual focus on improving the diagnosis and treatment this disease. In review, latest breakthroughs emerging trends in managing NSCLC are highlighted. Major advancements diagnostic methods, including better imaging technologies utilization molecular biomarkers, discussed. These have greatly enhanced early detection personalized plans. Significant improvements patient outcomes been achieved by new targeted therapies immunotherapies, providing hope for individuals with advanced NSCLC. This review discusses persistent challenges accessing treatments their associated costs despite recent progress. Promising research into therapies, such as CAR-T therapy oncolytic viruses, which could further revolutionize treatment, also aims inform inspire continued efforts improve patients globally, offering comprehensive overview current state future possibilities.

Language: Английский

---

A Holistic Approach to Implementing Artificial Intelligence in Lung Cancer

Indian Journal of Surgical Oncology, Journal Year: 2024, Volume and Issue: 16(1), P. 257 - 278

Published: Sept. 5, 2024

Language: Английский

---

Technology and Future of Multi-Cancer Early Detection

Life, Journal Year: 2024, Volume and Issue: 14(7), P. 833 - 833

Published: June 29, 2024

Cancer remains a significant global health challenge due to its high morbidity and mortality rates. Early detection is essential for improving patient outcomes, yet current diagnostic methods lack the sensitivity specificity needed identifying early-stage cancers. Here, we explore potential of multi-omics approaches, which integrate genomic, transcriptomic, proteomic, metabolomic data, enhance early cancer detection. We highlight challenges benefits data integration from these diverse sources discuss successful examples applications in other fields. By leveraging advanced technologies, can significantly improve diagnostics, leading better outcomes more personalized care. underscore transformative approaches revolutionizing need continued research clinical integration.

Language: Английский

---

Inteligencia Artificial en la detección del cáncer de pulmón

LATAM Revista Latinoamericana de Ciencias Sociales y Humanidades, Journal Year: 2025, Volume and Issue: 6(1)

Published: Jan. 16, 2025

El cáncer de pulmón en la actualidad se ha convertido patología oncológica diagnosticada con mayor frecuencia, y además figura como una las principales causas muerte. Esta enfermedad tiene tasa elevada mortalidad que relaciona falta síntomas etapas tempranas, lo ocasiona confirmación del diagnóstico suceda avanzadas, dando resultado opciones tratamiento disminuyan ocasiones estos pacientes no lleguen a tener curación. En el caso administre manera oportuna supervivencia 10 años es 88%. Con anteriormente mencionado buscado maneras mejorar detección temprana pulmón, entre estas mejoras menciona uso inteligencia artificial esta enfermedad. Se realizó revisión bibliográfica diversas bases datos científicas objetivo identificar sintetizar información relevante sobre mediante artificial. La conjunto tomografía computarizada dosis baja mejora tanto sensibilidad especificidad oportuno proporcionan un análisis más preciso reducir los falsos positivos negativos. Sin embargo, al ser nueva herramienta existe control regularizaciones adecuadas para este tipo tecnologías.

---

Predictive performance of risk prediction models for lung cancer incidence in Western and Asian countries: a systematic review and meta-analysis

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 4, 2025

Numerous prediction models have been developed to identify high-risk individuals for lung cancer screening, with the aim of improving early detection and survival rates. However, no comprehensive review or meta-analysis has assessed performance these across different sociocultural contexts. Therefore, this systematically examines risk in Western Asian populations. PubMed EMBASE were searched from inception through January 2023. Studies published English that proposed a validated model on human populations well-defined predictive performances included. Two reviewers independently screened titles abstracts, Prediction Model Risk Bias Assessment Tool (PROBAST) was used assess study quality. A random-effects performed, 95% confidence interval (CI) reported. Between-study heterogeneity adjusted using Hartung-Knapp-Sidik-Honkman test. total 54 studies included, 42 countries 12 countries. Most focused ever-smokers (19/42; 45.2%) general population (17/42; 40.5%), only two exclusively never-smokers. Across both models, three most consistently included factors age, sex, family history. In 45.2% (19/42) 50.0% (6/12) studies, incorporated traditional biomarkers. addition, 14.8% (8/54) directly compared biomarker-based those incorporating factors, demonstrating improved discrimination. Machine-learning algorithms applied eight models. External validation PLCOM2012 (AUC = 0.748; CI: 0.719-0.777) outperformed other such as Bach 0.710; 0.674-0.745) Spitz 0.698; 0.640-0.755). Despite showing promising results, majority our lack external validation. Our also highlights significant gap Future research should focus externally validating existing relevant into widely (PLCOM2012) better account unique profiles progression patterns

Language: Английский

---

AI in Healthcare

Published: Jan. 1, 2025

Language: Английский

---

Methodological and reporting quality of machine learning studies on cancer diagnosis, treatment, and prognosis

Frontiers in Oncology, Journal Year: 2025, Volume and Issue: 15

Published: April 14, 2025

This study aimed to evaluate the quality and transparency of reporting in studies using machine learning (ML) oncology, focusing on adherence Consolidated Reporting Guidelines for Prognostic Diagnostic Machine Learning Models (CREMLS), TRIPOD-AI (Transparent a Multivariable Prediction Model Individual Prognosis or Diagnosis), PROBAST (Prediction Risk Bias Assessment Tool). The literature search included primary published between February 1, 2024, January 31, 2025, that developed tested ML models cancer diagnosis, treatment, prognosis. To reflect current state rapidly evolving landscape applications fifteen most recent articles each category were selected evaluation. Two independent reviewers screened extracted data characteristics, (CREMLS TRIPOD+AI), risk bias (PROBAST), performance metrics. frequently studied types breast (n=7/45; 15.6%), lung liver (n=5/45; 11.1%). findings indicate several deficiencies quality, as assessed by CREMLS TRIPOD+AI. These primarily relate sample size calculation, strategies handling outliers, documentation model predictors, access training validation data, heterogeneity. methodological assessment revealed 89% exhibited low overall bias, all have shown terms applicability. Regarding specific AI identified best-performing, Random Forest (RF) XGBoost reported, used 17.8% (n = 8). Additionally, our outlines areas where is deficient, providing researchers with guidance improve these sections and, consequently, reduce their studies.

Language: Английский

---

The Application of Artificial Intelligence in Lung Cancer Research

Cancer Control, Journal Year: 2024, Volume and Issue: 31

Published: Jan. 1, 2024

The advent of artificial intelligence in healthcare is transforming medical research and clinical practice, with significant advancements the areas oncology. This commentary explores pivotal role plays lung cancer research, offering insights into its current applications future potential.

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

---