Background: Lung cancer remains one of the leading causes of cancer-related deaths worldwide. Artificial intelligence (AI) holds significant potential roles in enhancing the detection of lung nodules through chest X-ray (CXR), enabling earlier diagnosis and improved outcomes. Methods: Papers were identified through a comprehensive search of the Web of Science (WOS), Scopus, and Ovid Medline databases for publications dated between 2020 and 2024. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 34 studies that met the inclusion criteria were selected for quality assessment and data extraction. Results: AI demonstrated sensitivity rates of 56.4–95.7% and specificities of 71.9–97.5%, with the area under the receiver operating characteristic (AUROC) values between 0.89 and 0.99, compared to radiologists’ mean area under the curve (AUC) of 0.81. AI performed better with larger nodules (>2 cm) and solid nodules, showing higher AUC values for calcified (0.71) compared to non-calcified nodules (0.55). Performance was lower in hilar areas (30%) and lower lung fields (43.8%). A combined AI-radiologist approach improved overall detection rates, particularly benefiting less experienced readers; however, AI showed limitations in detecting ground-glass opacities (GGOs). Conclusions: AI shows promise as a supplementary tool for radiologists in lung nodule detection. However, the variability in AI results across studies highlights the need for standardized assessment methods and diverse datasets for model training. Future studies should focus on developing more precise and applicable algorithms while evaluating the effectiveness and cost-efficiency of AI in lung cancer screening interventions.

We would like to sincerely thank you for your thoughtful and very helpful comments on our systematic review titled “A Systematic Review: The Role of Artificial Intelligence in Lung Cancer Screening in Detecting Lung Nodules on Chest X-Rays”

Objectives This study aimed to quantify how patient risk factors relate to COVID-19 severity across categories 1–5 in a prospective, hospital-based cohort. We hypothesised that greater severity would be associated with higher odds of intensive care unit (ICU) admission and in-hospital mortality. Secondary aims were to assess associations with age, viral variants, symptom clusters, lymphocyte count, fasting blood glucose and cytokine profiles. Design Prospective cohort study. Setting A secondary-care/tertiary-care hospital and linked community settings in Cheras, Kuala Lumpur, Malaysia. Participants This study was nested within the COVGEN project, a prospective COVID-19 cohort conducted at Hospital Canselor Tuanku Muhriz UKM (HCTM), Cheras Health Clinic and the Bandar Tun Razak COVID-19 Assessment Centre in Cheras, Kuala Lumpur, Malaysia, from 1 August 2021 to 31 October 2022. 2532 participants were enrolled at baseline. Eligible participants were Malaysian citizens aged 12–18 years (paediatric/adolescent) or ≥18 years who had reverse transcription-polymerase chain reaction–confirmed COVID-19 at recruitment and resided in Kuala Lumpur or Selangor. Patients who had a clinically unstable condition and those who declined participation (personally or via a next-of-kin or legal representative) were excluded. This analysis included 559 patients hospitalised at HCTM; after excluding five with incomplete questionnaires, 554 remained for analysis (413 admitted to general wards and 141 to ICUs). Categories 3–5 comprised hospitalised patients, whereas categories 1–2 included hospitalised individuals and a subset recruited from community settings. Primary and secondary outcome measures Primary outcomes included disease severity (categories 4–5 vs 1–3), ICU admission and in-hospital mortality. Secondary outcomes included associations with age strata, viral variant (delta vs omicron), symptom clusters, lymphocyte count, fasting blood glucose and cytokines: interferon gamma-inducible protein 10, interferon gamma, interleukins 8, 10, 2, 6 and 7 and tumour necrosis factor alpha. Results 141 of 554 (25.5%) patients required ICU care. Compared with milder categories, category 5 was associated with markedly higher odds of ICU admission (OR 204.50; 95% CI 37.54 to 1114.18; p<0.001) and death (OR 13.20, 95% CI 3.97 to 43.86; p55 versus <36 years for categories 3 (OR 4.575; 95% CI 1.472 to 14.218; p=0.009) and 5 (OR 18.003; 95% CI 1.139 to 284.601; p=0.040) and 36–55 versus <36 years for category 5 (OR 18.412; 95% CI 1.094 to 309.951; p=0.043). Delta accounted for 47.7% of infections compared with 17.9% for omicron, with a higher proportion of category 4 presentations among delta cases. Systemic, pulmonary/respiratory and gastrointestinal symptoms, lymphopenia, hyperglycaemia and elevated cytokines were each associated with increasing severity (p<0.05). Conclusions An increasing clinical severity category was strongly associated with ICU admission and mortality. Age, delta infection, specific symptom clusters, lymphopenia, hyperglycaemia and pro-inflammatory cytokines identified higher-risk patients, supporting risk-stratified management and prioritisation for enhanced monitoring.

Introduction Incidental pulmonary nodules (IPNs) are commonly encountered on chest radiographs (CXRs) performed for routine clinical indications and may represent early manifestations of significant pulmonary pathology, including lung cancer. While low-dose CT screening has mortality benefits in selected high-risk populations, its implementation remains limited in many healthcare settings. Artificial intelligence (AI)-assisted CXR interpretation has the potential to enhance pulmonary nodule detection. However, evidence from Malaysian clinical practice is scarce. This study aims to evaluate the diagnostic performance of AI-assisted CXR interpretation for detecting IPNs across healthcare facilities in the Klang Valley, Malaysia. Methods and analysis This prospective, multicentre study will include 2452 CXRs from patients aged ≥35 years over a 6-month period across four Klang Valley healthcare facilities. Each CXR will be independently interpreted by an experienced radiologist (>5 years of experience) and analysed separately using an AI system (qXR-LNMS). An independent thoracic radiologist will determine the final classification for analysis if there is IPN detection discordance. Diagnostic performance metrics (sensitivity, specificity, positive and negative predictive values, and overall accuracy) will be calculated using a 2×2 classification matrix. Agreement between AI-assisted interpretation and radiologist reports will be assessed using Cohen’s kappa statistic. The prevalence of IPNs detected by AI-assisted interpretation and radiologist reporting will be compared using a two-proportion z-test. AI discriminative performance will be evaluated using receiver operating characteristic curve analysis and area under the curve estimation. Statistical analyses will be conducted using Statistical Package for the Social Sciences V.29, with p<0.05 considered statistically significant. Ethics and dissemination Ethical approval has been obtained from the Universiti Kebangsaan Malaysia Research Ethics Committee and the Ministry of Health Malaysia Medical Research and Ethics Committee. Written informed consent will be obtained from all participants. The findings will be disseminated through peer-reviewed publications, scientific conferences and engagement with relevant stakeholders.