Detection Of Lung Cancer Research Articles

Optimization of fusion detection in non-small cell lung cancer by amplicon-based RNA sequencing.

e20042 Background: In non-small cell lung cancer (NSCLC), more and more driver fusions are suitable for targeted therapy. Sequential or parallel DNA and RNA sequencing is an option, but it is costly and requires sufficiently high quality biopsy material. The purpose of this study was to confirm the consistency of fusion genes detected by DNA-based NGS and RNA-based NGS in the same sample, and to validate the performance of FFPE samples for RNA-based NGS. Methods: In this study, we evaluated the benefits of capture-based DNA sequencing and amplicon-based RNA sequencing in identifying gene fusion and exon-skipping events in 98 NSCLC patients. All cases were FFPE samples stored for 1-5 years. In addition, we investigated the limiting performance of RNA-based NGS for RNA initiation. Results: In the cases of positive DNA sequencing fusion samples, the fusion consistency detection rate of RNA sequencing was 95% (38/40). Two cases were not detected by RNA-based NGS, one was a five-year FFPE sample and the other was due to a probe not covered problem. In patients with negative DNA fusion genes, RNA sequencing could detect 12.07% more fusion-positive cases involving ALK (n = 1), ROS (n = 3), MET 14 exon skipping (n = 1), RET (n = 1), and BRAF (n = 1). Moreover, the FFPE samples stored for 3-5 years inevitably degrade the RNA, but could still be used for RNA-based sequencing. Among 66 FFPE samples stored for 3-5 years, the detection rate of fusion consistency between DNA sequencing fusion samples and RNA sequencing was 96.77%(30/31). In patients with negative DNA fusion genes, RNA sequencing was able to detect 14.29% (5/35) more fusion-positive cases. The performance verification of the other 8 samples with different RNA input amounts found that 87.5% (7/8) of the samples could meet the quality control of RNA sequencing and accurately detect fusion mutations as low as 1 ng. Conclusions: Molecular profiling based on mixed DNA and RNA sequencing improves the effectiveness of detection of fusion-driven NSCLC. The method was feasible on small tissue samples as well as FFPE samples stored for 3-5 years, and could greatly reduce the complexity and cost of molecular examination.

Economic analysis of combined multi-cancer detection blood test and usual care.

e23055 Background: A previous multi-cancer detection blood test (MCDBT) in six prevalent and deadly cancers including colorectal, esophageal, liver, lung, ovarian, and pancreatic cancers, has been reported to decrease late-stage incidence and increase 5-year survival rate. However, the economic cost-effectiveness of integrating the MCDBT with usual care and the factors influencing it have not been investigated. Methods: An interception model was utilized to estimate the stage distribution at the time of cancer diagnosis, while a decision-tree model was developed to assess the clinical and economic outcomes of annual MCDBT for individuals aged 50 to 79 in the United States. The performance metrics for the MCDBT were based on the findings of a previous study called THUNDER. The incidence data were derived from the Surveillance, Epidemiology, and End Results Program (SEER), and the associated costs were obtained from SEER-Medicare. Other input data was estimated based on information available in the published literature. Results: In addition to the usual care, the integration of the MCDBT resulted in a shift of 27.9% in cancer cases from stage III-IV to stage I-II, which led to a decrease in per-cancer treatment cost by $5971 and an increase in quality-adjusted life-years by 0.10 per cancer case. The major factors that influenced the incremental cost-effectiveness ratio (ICER) included price, incidence, specificity, and sensitivity. The MCDBT with a price less than $800 showed cost-effectiveness with an ICER below three times the per capita GDP of the United States in the average-risk population. In a high-risk population with the incidence two-fold higher than the average-risk population, the ICER decreased by 58.3%. When compared the influence of specificity and sensitivity on the ICER of the MCDBT, a 5% increase in specificity resulted a decrease in ICER by 48.8%, while a 5% increase in sensitivity only reduced the ICER by 12.7%, suggesting the importance of high specificity in MCDBT. Conclusions: The MCDBT with a price less than $800 showed cost-effectiveness in the detection of colorectal, esophageal, liver, lung, ovarian, and pancreatic cancers. Price, incidence of the intended-use population, specificity and sensitivity were the major factors that influenced the cost-effectiveness.

Tongue image feature correlation analysis in benign lung nodules and lung cancer

ObjectiveTo analyze the differences in the correlation of tongue image indicators among patients with benign lung nodules and lung cancer. MethodsFrom July 1, 2020 to March 31, 2022, clinical information of lung cancer patients and benign lung nodules patients was collected at the Oncology Department of Longhua Hospital Affiliated to Shanghai University of Traditional Chinese Medicine and the Physical Examination Center of Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, respectively. We obtained tongue images from patients with benign lung nodules and lung cancer using the TFDA-1 digital tongue diagnosis instrument, and analyzed these images with the TDAS V2.0 software. The extracted indicators included color space parameters in the Lab system for both the tongue body (TB) and tongue coating (TC) (TB/TC-L, TB/TC-a, and TB/TC-b), textural parameters [TB/TC-contrast (CON), TB/TC-angular second moment (ASM), TB/TC-entropy (ENT), and TB/TC-MEAN], as well as TC parameters (perAll and perPart). The bivariate correlation of TB and TC features was analyzed using Pearson’s or Spearman’s correlation analysis, and the overall correlation was analyzed using canonical correlation analysis (CCA). ResultsSamples from 307 patients with benign lung nodules and 276 lung cancer patients were included after excluding outliers and extreme values. Simple correlation analysis indicated that the correlation of TB-L with TC-L, TB-b with TC-b, and TB-b with perAll in lung cancer group was higher than that in benign nodules group. Moreover, the correlation of TB-a with TC-a, TB-a with perAll, and the texture parameters of the TB (TB-CON, TB-ASM, TB-ENT, and TB-MEAN) with the texture parameters of the TC (TC-CON, TC-ASM, TC-ENT, and TC-MEAN) in benign nodules group was higher than lung cancer group. CCA further demonstrated a strong correlation between the TB and TC parameters in lung cancer group, with the first and second pairs of typical variables in benign nodules and lung cancer groups indicating correlation coefficients of 0.918 and 0.817 (P < 0.05), and 0.940 and 0.822 (P < 0.05), respectively. ConclusionBenign lung nodules and lung cancer patients exhibited differences in correlation in the L, a, and b values of the TB and TC, as well as the perAll value of the TC, and the texture parameters (TB/TC-CON, TB/TC-ASM, TB/TC-ENT, and TB/TC-MEAN) between the TB and TC. Additionally, there were differences in the overall correlation of the TB and TC between the two groups. Objective tongue diagnosis indicators can effectively assist in the diagnosis of benign lung nodules and lung cancer, thereby providing a scientific basis for the early detection, diagnosis, and treatment of lung cancer.

Comparative analysis of explainable AI models for predicting lung cancer using diverse datasets

Lung cancer prediction is crucial for early detec-tion and treatment, and explainable AI models have gained attention for their interpretability. This study aims to compare various explainable AI models using diverse datasets for lung cancer prediction. Clinical, genomic, and imaging data from multiple sources were collected, prepro-cessed, and used to train models such as Logistic Regression, SVC-Linear, SVC-rbf, Decision Tree, Random Forest, AdaBoost Classifier, and XGBoost Classifier. Preliminary results indicate that Random Forest achieved the highest accuracy of 98.9% across multiple datasets. Evaluation metrics such as accuracy, precision, recall, and F1 score were utilized, along with interpretability techniques like feature importance rankings and rule extraction methods. The study's findings will aid in identifying effective and interpretable AI models, facilitating early detection and treatment decisions for lung cancer.

Lung cancer among patients with secondhand smoke exposure: A systematic review.

e22506 Background: Smoking tobacco is recognized as the leading cause of lung cancer. However, it is imperative to note that 10–15% of lung cancer patients have no history of smoking, and that lung cancer remains the leading cause of cancer deaths among non-smokers. Since passive smokers are exposed to many carcinogenic compounds in the exhaled smoke, it is naturally plausible that secondhand smoking (SHS) is a risk factor for lung cancer. However, current USPSTF screening guidelines for lung cancer with low dose CT (LDCT) do not include patients exposed to SHS. We performed a systematic review to highlight SHS as an etiology of lung cancer and insights for inclusion in cancer screening criteria. Methods: We utilized the PubMed, Medline, Science Direct, and ClinicalTrials.gov databases to search for relevant literature using keywords ('low Dose CT,' 'secondhand smoke,' 'lung cancer'). The search strategy was designed to ensure a comprehensive retrieval of pertinent literature, minimizing the possibility of omitting articles due to insignificant spelling and/or semantic variations. Eligible studies had to be published between 2010 and 2023 and focused on examining the effect of SHS in populations at risk of lung cancer or those undergoing lung cancer screening. Articles not available in English were excluded from this systematic review. In total, 239 relevant articles were retrieved from all databases, narrowing down to 14 articles after the initial screening and further reducing to 4 articles after the second round of screening. Results: Three of the four articles included in our systemic review were conducted in Asia. A study by He et al. showed a substantial increase in the relative risk of lung cancer among SHS (RR 2.00; 95% CI, 0.62-6.40), with significant dose-response relationships between cumulative SHS exposure at home and work and the increased risk of cause-specific and total mortality. Another observational study on the use of LDCT in Japan has interestingly shown a shifting landscape of lung cancer demographics, with 49.6% of patients identified as never-smokers and 70.0% of the never-smoker lung cancer patients having SHS exposure. Secondhand smoking has also been reported to increase the risk of pulmonary nodules (HR 1.17; 95% CI, 1.01-1.35) and pulmonary emphysema (OR 13.6; 95% CI, 1.70-106.1) in those with moderate-to-high SHS exposure, which was the population where lung cancer was more prevalent. Conclusions: Our findings suggest a critical gap in current healthcare recommendations, specifically addressing the absence of guidelines for LDCT screening in individuals with moderate-to-high SHS exposure despite established evidence linking SHS to a significant increase in the risk of lung cancer development. More studies are needed to formulate evidence-based guidelines for lung cancer screening and detection in this population, given the expected mortality reduction benefit.

Enhancing early detection of lung cancer: A strategic initiative to boost screening rates among patients.

e22512 Background: Lung cancer is the top cause of cancer death in the U.S. Despite LDCT screenings reducing mortality, uptake is low in Alabama and nationally (6% vs. 4.5%). The U.S. Preventive Services Task Force recommends annual LDCT for certain high-risk adults, but factors like awareness, access, and policy affect screening rates. Alabama's situation is worsened by rural disparities and socioeconomic issues. Infirmary Health is the largest private, not for profit health care system in the state of Alabama. This study focuses on evaluating LDCT screening in a selected clinic of our health care system, pinpointing obstacles to adherence, and seeking ways to boost screenings to lower lung cancer mortality through early detection. Methods: As part of the Summer 2023 ASCO Quality Training Program we adopted a QI approach to increase LDCT lung cancer screening. It began by assessing baseline screening rates and staff knowledge, then created problem and aim statements. The team conducted root cause analysis, used a Pareto chart for issue prioritization, and employed a Priority Pay-off Matrix to focus on impactful, feasible issues. The Plan-Do-Study-Act (PDSA) cycle was then used to develop, test, and implement interventions, ensuring strategic alignment and effective monitoring of outcomes to enhance screening rates. Results: From January to July 2023, the Infirmary Health -Hillcrest clinic had a low 10.53% LDCT screening rate (system wide 6%, this clinic was selected due to it's highest screening rate), leading to late-stage lung cancer diagnoses and higher mortality. To address this, a goal was set to triple the screening rate to 30% by December 2023. Key barriers identified were staff and patient knowledge about lung cancer screening and a cumbersome LDCT ordering process. A PDSA cycle initiated between September and December 2023, firstly focused on Patient/Clinic Education, increasing screening rates by simplifying the process—removing doctor signature requirements and enhancing staff knowledge through meetings and informative flyers. The subsequent phase introduced a Nurse Navigator, who further increased screenings through prescreening, staff reminders, and on-site visits. By December of 2023 the LDCT screening rate was increased from baseline 10.53% to 33.3%. Conclusions: Through identifying and addressing key issues like education, faulty process and nurse navigation we successfully elevated LDCT screening rates. This study highlights the benefit of participating in a structured quality training program. [Table: see text]

Country-specific differences in the lung tumour microbiome.

e20044 Background: Sputum examination for the early detection of lung cancer continues to be explored ( Thunnissen 2003 ), however has so far resulted in a low diagnostic yield. An increasing number of studies have evidenced a mechanistic role of the lung microbiome in the induction of lung cancer ( Liu et al., 2020 ), and the presence of bacterial biomarkers in bronchoalveolar lavage and sputum have been proposed ( Cheng et al., 2020 ). It is currently unknown whether the sputum microbiome can appropriately capture the lung tumour microbiome. Given that the lung microbiome may vary by geography, this analysis was considered over two populations: China and Italy. Methods: Microbiome analysis was performed using BioCorteX’s industry-leading knowledge graph and integrated proprietary engines v20240126_153156. Data from 9 studies was used. In total, 461 samples from lung cancer patients in China (250 sputum, 211 tumour) and 60 from Italy (34 sputum, 26 tumour) were considered. Shannon’s diversity was used to consider within-sample diversity, and dimensional scaling based (MDS) on Bray-Curtis diversity was used to consider between-sample diversity. Results: All sample were checked to have a library size greater than 100, and more than 10 unique species. Only those species present in over 1% of samples were considered to reduce noise. In both China and Italy, tumour samples had a lower diversity than sputum samples (p = 0.00016 and p &lt; 2.2e-16, respectively). Samples from Italy had a lower diversity than samples from China (p &lt; 2.22e-16). In the MDS analysis, the tumour samples from China and Italy formed two distinct, non-overlapping clusters. A third cluster was formed from the union of sputum samples from both countries. These results were independent of any study-specific effects. Conclusions: These results indicate that the sputum microbiome is not representative of the tumour microbiome, and that the divergence of the tumour microbiome away from the sputum microbiome is country specific. The results of this analysis highlight that further work into differences in the lung tumour microbiome by country is warranted, especially in light of the growing body of evidence suggesting a causative role of the microbiome in lung cancer. It is also possible that lung cancer treatments may be impacted by the country-specific nature of the lung tumour microbiome.

A variety of inflammatory shadows caused by COVID-19 on chest CT that closely resembled lung cancer in annual lung cancer screening.

e23122 Background: Chest X ray (CXR) has been the most common screen test procedure for detection of lung cancer. Before COVID-19, we have shown that repeat visitors (R) had a significantly lower proportion of CXR abnormalities requiring medication than the first-time visitors (F) at annual lung cancer screening. (Kimura T. Health Prim Car, 2021). During COVID-19, we reported that the influence of large waves of COVID-19 in annual lung cancer screening. (Kimura T. abstract No. e18596, ASCO annual meeting 2023) Because of the widespread use of vaccines, the XBB variants, derived from Omicron BA.2, has mainly cold-like symptoms. These variants spreads more easily than the original or the Delta variants. In Japan, since May 2023, COVID-19 has been made less dangerous under the Infectious Disease Control Law, which loosens the restrictions on wearing masks and having close contacts. No longer visits the hospital unless there is a high fever or dyspnea. Hypothesis is that there is a difference in lung cancer screening after a COVID-19 infestation compared to during and before COVID-19. Methods: Our clinic “MedCity21” is a university outpatient clinic for medical check-ups as a part of private health screening programs. Our facility allows COVID-19 diagnosed participants (pts) 5 days after onset or 24 hours after symptoms have abated. When the abnormalities were detected on CXR, pts were notified in a week by telephone request and invited to our specialty clinic for chest CT scan as further examination. By year from 2018 to 2023, we examined the varieties of abnormal shadows on CXR and CT and compared the differences using the chi-squared tests. Results: In 2023, there were 15072pts were visited our clinic for private health screening, among them, 13451pts (F:23.8%, R:75.2%) had chest X-rays performed. The January 2022, percentage of pts with a history of COVID was 1.68%, gradually increased, reaching 46.6% in December 2023. There were 226pts (1.68%) with CXR abnormalities requiring further investigation. The rates in F and R were 3.06% and 1.23%, respectively. The distributions of CXR and CT variations on R group were consistent with our previous report. However, significantly increased rate of inflammatory changes in CT findings (16.3%) in F group compared to each previous year (3.2-6.9%). (p = 0.014) We experienced a variety of inflammatory shadows on chest CT that closely resembled lung cancer. Such shadows were confirmed to have shrunk or disappeared on CT scan 1-2 months later. Conclusions: The pts who had ever had COVID-19 gradually increased. This was accompanied by an increase in the number of inflammatory shadows that were difficult to differentiate from lung cancer. It is better to follow up patients with CT or CXR for a month instead of immediately examining them. COVID-19 may cause concomitant bacterial or viral pneumonia; COVID-19 may affect the immune mechanisms of healthy individuals.

Effect on patient empowerment through the EPEP program.

e21009 Background: There is a critical need to support oncology providers seeking to empower their patients and care partners by connecting them to trusted resources. To fill this gap, the Patient Empowerment Network (PEN) created the Empowering Providers to Empower Patients (EPEP) program to improve physician-patient communication and shared decision-making by creating a clear path to support providers in empowering their patients and care partners. Methods: The EPEP program, developed by an interdisciplinary team of experts for oncology health care professionals, launched in March 2023 with a focus on lung cancer resources. The program includes digital resources such as Roundtables (30-minute webinars + segments with leading experts, clinicians, and peers), an HCP Portal (a system that informs and collates vetted resources), a Resource Guide (resource guide for HCPs), and a Roundup Blog (article with key takeaways summarizing program). Following two roundtables in March 2023, we assessed initial provider engagement with EPEP using digital engagement metrics and a five-item questionnaire. Results: Since the launch, 212 oncology providers have access to the suite of digital resources. The content has been viewed and downloaded almost 13,595 times. Surveys conducted following the roundtables indicated that the program was well-received. Of 21 respondents, n=18 (86%) rated their experience as very positive; agreed or strongly agreed that the program gave them the confidence to better facilitate shared decision-making with their patients; and said they found relevant resources to share with their patients and their families. Sample feedback included, “I would say it gave me the confidence to raise the flag on timing. Sometimes we test and are not doing this in a timely way. Thanks for this program.” And “These conversations are so critical. Thank you for a great program.” And, “I thought the conversation was excellent; we need more of this. I thought the tips were spot-on and very helpful.” Providers wanted communication tools focused on the “timing of testing following the initial workup,” “pathology conversations” and “anxiety and fear after the cancer diagnosis, long-term side effects, screening and early detection of lung cancer.” Conclusions: The EPEP program serves as a trusted digital space for providers to objectively share and recommend resources to their oncology patients. The program now includes removing practice barriers that may be caused by a lack of awareness and outdated practices. The long-term goal is to improve physician-patient communication and shared decision-making while also empowering cancer patients and family members to ask informed questions based on where they are in their cancer journey.

An optimized convolutional neural network architecture for lung cancer detection.

Lung cancer, the treacherous malignancy affecting the respiratory system of a human body, has a devastating impact on the health and well-being of an individual. Due to the lack of automated and noninvasive diagnostic tools, healthcare professionals look forward toward biopsy as a gold standard for diagnosis. However, biopsy could be traumatizing and expensive process. Additionally, the limited availability of dataset and inaccuracy in diagnosis is a major drawback experienced by researchers. The objective of the proposed research is to develop an automated diagnostic tool for screening of lung cancer using optimized hyperparameters such that convolutional neural network (CNN) model generalizes well for universally obtained computerized tomography (CT) slices of lung pathologies. The aforementioned objective is achieved in the following ways: (i) Initially, a preprocessing methodology specific to lung CT scans is formulated to avoid the loss of information due to random image smoothing, and (ii) a sine cosine algorithm optimization algorithm (SCA) is integrated in the CNN model, to optimally select the tuning parameters of CNN. The error rate is used as an objective function, and the SCA algorithm tries to minimize. The proposed method successfully achieved an average classification accuracy of 99% in classification of lung scans in normal, benign, and malignant classes. Further, the generalization ability of the proposed model is tested on unseen dataset, thereby achieving promising results. The quantitative results prove the efficacy of the system to be used by radiologists in a clinical scenario.

Implementing fragmentomics into real world screening interventions to evaluate clinical utility among individuals with elevated risk for lung cancer (FIRSTLUNG) L301.

TPS11189 Background: To optimize the impact of lung cancer screening at the healthcare system level, additional tools are needed to increase the benefits of screening. While low-dose computed tomography (LDCT) has been shown to improve lung cancer detection and reduce mortality, it is not without its risks, such as radiation exposure, false-positive results, and unnecessary interventions often leading to complications. The additional complexity of lung cancer screening is the subpar adherence to LDCT for eligible individuals, which undermines the benefits of screening. Therefore, there is a need for alternative non-invasive methodologies that exploit our understanding of the biology of cancer pathogenesis. This clinical utility study aims to observe how a non–invasive blood-based test impacts physician behavior and LDCT utilization. Methods: FIRSTLUNG 301 (NCT06145750) is a prospective, cluster randomized controlled trial (RCT) to observe the impact of the DELFI Lung cancer screening test on lung cancer screening utilization in primary care practices. Enrolled practices must meet the eligibility criteria of having a minimum of 50 actively engaged individuals in the practice eligible for lung cancer screening per the 2021 USPSTF criteria. These practices will be randomized 1:1:2 to Arm A1 (control), Arm A2 (control), or Arm B (intervention). Arm A practices will be randomized 1:1 into two groups (A1:A2) to observe the standard of care for lung cancer screening. Practices in A1 will be observed; practices in A2 will receive standard education on lung cancer screening for CME credit. Randomizing within Arms A1 and A2 aims to delineate the impact standard lung cancer screening education may have on utilization. Arm B (intervention) practices will receive education and have access to order the blood-based test for screen-eligible individuals that remained unscreened. The primary study endpoint is the proportion of practice-identified lung cancer screen-eligible individuals receiving a screening CT order and scan during the study period in the entirety of Arm A (control) versus Arm B (intervention). This RCT aims to understand the utilization and impact on lung cancer screening uptake after the DELFI blood-based test intended to inform clinical guidelines and policies focused on improving patient care and health outcomes. Progress: The study was initiated on October 31, 2023, with practice randomization. As of February 2024, the study is open for enrollment with an estimated primary study completion date of December 2025. Clinical trial information: NCT06145750 .

Taiwan national lung cancer early detection program for heavy smokers and non-smokers with family history of lung cancer.

8009 Background: Lung cancer incidence in Taiwan has been rising with the epidemiological profiles distinct from Western country. Notably, nonsmoking lung cancers accounts for more than 60% and half of lung cancers were diagnosed in advanced stages. For early detection, a national program is therefore initiated to offer biennial low-dose computed tomography (LDCT) screening for heavy smokers and subjects with lung cancer family history (LCFH). Here, we report basic screening findings, analyze relevant effectiveness in reducing advanced lung cancer, and project the potential benefit of mortality reduction. Methods: Taiwan National Lung Cancer Early Detection Program was launched on July 1, 2022 to offer heavy smokers (30 pack-years) and nonsmokers (including light smokers) with a LCFH aged 45-74 years for female and aged 50-74 years for male. This is a continuous screening program using before and after study design for evaluation. We provided the overall first-year basic screening findings until Dec 31, 2023 and did per protocol analysis of stage II+ cancer reduction in comparison with tumor stage distribution in the year preceding the introduction of the national program. The corresponding findings were presented for subjects with LCFH and heavy smokers. The result for heavy smoker was compared with those per-protocol findings from previous randomized controlled trials. The potential mortality reduction was further projected. Results: A total of 78,000 individuals participated in this program, male 44,381 (56.9%) female 33,619 (43.1%); 31,111 participants (39.9%) were heavy smokers, 43,853 (56.2%) nonsmokers but with a LCFH, and 3,036 (3.9%) had both risk factors. Lung cancer confirmed in 956 subjects by surgery or biopsy, 85.0% were stage 0-1. The lung cancer detection rate was 1.2%. Subjects with a LCFH exhibited a higher detection rate (overall: 1.6%, nonsmokers: 1.7% and light smokers 0.9%) compared to heavy smokers (0.7%) and both (1.1%). Early detection of LDCT led to a statistically significant 77% (51%-89%) of reducing advanced stage of lung cancer, 53% (-3%-78%) reduction for heavy smokers, consistent with the corresponding 36%-64% reduction derived from the NLST trial and the Nelson trial, and 85% (67%-93%) reduction for nonsmokers with a LCFH. The benefit of reducing stage II or severe in conjunction with five-year stage-specific survival rate further projected 55% (10%-78%) of mortality reduction from lung cancer. Conclusions: This is the first large-scale LC screening service enrolling 40% heavy smokers and 60% non-smoker with a LCFH. The potential effectiveness of early detection was demonstrated for both targets. As the results based on per-protocol analysis for heavy smoker were consistent with those of previous evidence-based studies the similar and significant intention-to-treat results as before while waiting for the subsequent follow-up would be expected.

An Enhanced Lung Cancer Identification and Classification Based on Advanced Deep Learning and Convolutional Neural Network

In this research, a fast, accurate, and stable system of lung cancer detection based on novel deep learning techniques is proposed. Lung cancer continues to be one of the most monumental global health concerns, which is why there is an urgent need for low-cost and non-invasive screening. Though the diagnostic methods that are most commonly in use include CTscan, X-ray etc. The interpretation by the human eye varies and errors are bound to occur. In response to this challenge, we outline a more automated approach that is based on deep learning models and can be used to classify lung pictures with high levels of accuracy. This research makes use of a large data set of lung scans categorised as normal, malignant, and benign. The first look what the data had in store threw up some correlation with picture size and what seemed to be category differences. Realizing that live feed requires constant input, each picture underwent grayscale conversion and dimensionality reduction. In order to effectively deal with the unbalanced nature of the dataset that was discovered in the study, the Synthetic Minority Oversampling Technique (SMOTE) was applied as a technique. In this presentation, three new designs were introduced: Model I, Model 2, and Model 3. Additionally, one architecture was developed with the purpose of merging the predictions of all three models. Furthermore, out of all the models created, the best model emerged as model 1 with approximately an accuracy of 84%. 7%. But the ensemble strategy which was intended to make the best of each of the models, produced an astounding 82. 5% accuracy. The specific advantages and misclassification behaviors of Model 2 and 3, although less accurate than Model 1 but are currently under evaluation for future Model ensemble improvements. The technique developed using deep learning addresses the challenges at a faster, efficient, and contactless approach to lung cancer analysis. The fact that it is capable of operating in tandem with others diagnostic instruments may help reduce diagnostic errors and enhance patient care. We have addressed this issue so that the various practitioners would be able to read this paper and we can go to the next generation of diagnostic technologies.

Clinical Application of Exhaled Breath Condensate in Diagnosis of Diseases.

Respiratory diseases are highly prevalent in the general population, and the morbidity, mortality, and healthcare burden on society at large have been on the rise worldwide. For example, lung cancer is a major contributor to cancer-related mortality around the globe, and identifying clinically relevant biomarkers for lung cancer detection at both early and metastatic stages has been a pressing need. Human metabolism is complicated and may vary with different individuals. Despite advances in the treatment and the early screening of respiratory diseases, most diagnoses are established at a late stage, i.e., when genetic and epigenetic changes have developed. A promising source of biomarkers indicative of the pathogenesis of respiratory diseases is exhaled breath condensate (EBC), a biological fluid and a natural matrix of the respiratory tract. Molecules, such as DNAs, RNAs, proteins, metabolites, and others, are found in EBC, and their presence/absence or changes in concentrations can serve as biomarkers. This review discusses the exhaled breath composition, candidate EBC biomarkers, and the potential to use EBC for diagnosing diseases, therapeutic monitoring, and screening high-risk individuals.

AI-based approach to enable proactive identification of early lung cancer: A retrospective population health study and economic model.

10536 Background: Approximately 48,500 new cases of lung cancer are diagnosed each year in the UK with a five-year survival rate which lags behind other European countries. Most patients are diagnosed at stage III or IV disease, which has a significantly worse prognosis. The integration of real-world data and AI techniques presents a promising avenue for improvement, using novel solutions not achievable through traditional care models. This study explores proactive patient identification at scale, aligning with the "left shift" paradigm in population health. The approach uses innovative technologies and novel data sources to identify patients with early-stage disease, enhancing both clinical and economic outcomes. Importantly, these interventions should be feasible on a large scale without overburdening already stretched clinical services. Methods: A retrospective study of real-world data for an urban population with high socioeconomic disadvantage and health needs was undertaken. Two endpoints were determined: detection potential and health economic impact. For detection potential (DP), patients aged 40 and above who underwent chest X-rays (CXR) at a large academic medical centre between 2016-2022 were included. Natural Language Processing (NLP) analysed unstructured free-text data from Electronic Health Records, combined with ICD-10 codes, for predictive model (PM) development using Machine Learning (ML) classification techniques. The PM's performance was assessed using the area under the receiver operating characteristic curve (AUCROC). Health economic impact was evaluated through a theoretical extrapolation of DP. Assuming a 9% left shift from late (stage III or IV) to early (stage I or II) disease, a health economic model (HEM) compared the impact of the current care model to a potential future state facilitated by the digital medicine care model (DMCM). Results: 75,342 patients were included, with 755 lung cancer diagnoses occurring within 6 months of CXR. The PM achieved a peak AUROC of 0.75, exceeding the performance of currently used risk prediction models (Q Cancer Risk, Risk Assessment Tools). A 9% left shift equated to 4.5 years mean increase in survival. The DMCM was associated with a net healthcare cost benefit of £6k per patient diagnosed with lung cancer, improved quality-adjusted life years of £21M for the year 1 cohort over 10 years and increased economic productivity (from additional years in workforce) of £2.4M. Conclusions: The study demonstrates the practical utility of AI-supported early lung cancer detection at population scale. Real-world evidence is needed to prospectively validate the model as cost-effective, scalable, and efficient. Future work will seek to improve the model's performance against a broader at-risk patient population and explore its applicability to other late-presenting tumours.

Can Tumour Antigens Act as Biomarkers for the Early Detection of Non-Small Cell Lung Cancer?

Lung cancer (LC) is one of the leading causes of cancer-related deaths. Pulmonary nodules are one of the risk factors, and their discovery rate has been increasing due to enhanced performance of chest CT scans, but more than 90% are non-malignant, causing unnecessary stress to patients and costs to healthcare providers. Early diagnosis of LC is associated with a 5-year survival rate of up to 75% following surgical resection, but LC is often diagnosed late due to a lack of symptoms and poor 5-year survival rates as low as 10%. The cost of LC diagnosis is high, with 40% of it associated with benign lesions, which are difficult to differentiate from malignant lesions. Tumour-associated antigens (TAAs) may provide one way in which LC could be diagnosed early using minimally-invasive techniques, under their association with immune responses and specificity for disease. Here we discuss the potential of cancer-testis antigens (CTAs) to act as non-invasive biomarkers for the early detection of non-small cell lung cancer.

Detection of Lung Cancer in CT image using Image Processing

Detection of Lung Cancer in CT image using Image Processing

The utility of artificial intelligence in identifying radiological evidence of lung cancer and pulmonary tuberculosis in a high-burden tuberculosis setting.

Artificial intelligence (AI), using deep learning (DL) systems, can be utilised to detect radiological changes of various pulmonary diseases. Settings with a high burden of tuberculosis (TB) and people living with HIV can potentially benefit from the use of AI to augment resource-constrained healthcare systems. To assess the utility of qXR software (AI) in detecting radiological changes compatible with lung cancer or pulmonary TB (PTB). We performed an observational study in a tertiary institution that serves a population with a high burden of lung cancer and PTB. In total, 382 chest radiographs that had a confirmed diagnosis were assessed: 127 with lung cancer, 144 with PTB and 111 normal. These chest radiographs were de-identified and randomly uploaded by a blinded investigator into qXR software. The output was generated as probability scores from predefined threshold values. The overall sensitivity of the qXR in detecting lung cancer was 84% (95% confidence interval (CI) 80 - 87%), specificity 91% (95% CI 84 - 96%) and positive predictive value of 97% (95% CI 95 - 99%). For PTB, it had a sensitivity of 90% (95% CI 87 - 93%) and specificity of 79% (95% CI 73 - 84%) and negative predictive value of 85% (95% CI 79 - 91%). The qXR software was sensitive and specific in categorising chest radiographs as consistent with lung cancer or TB, and can potentially aid in the earlier detection and management of these diseases.

Lung Cancer Detection

Abstract: This paper presents a comprehensive approach to lung cancer detection utilizing state-of-the-art machine learning techniques, specifically Convolutional Neural Networks (CNNs). Using CNN[1] the model is trained and it can detect whether the given lung cancer cell image contains cancerous cells or not. The first component of the proposed approach involves high-resolution medical imaging, such as computed tomography (CT) scans, to capture detailed anatomical information about the lungs. Image processing algorithms are applied to enhance the quality of the images and extract relevant features. Additionally, innovative three-dimensional reconstruction techniques are employed to visualize the lung tissue at a microscopic level, facilitating the identification of subtle abnormalities.

Predictive Modeling for Lung Cancer Detection: Unveiling Insights through Machine Learning Techniques

Abstract: Lung cancer stands as a formidable global health challenge, characterized by its widespread prevalence and high mortality rates, placing significant burdens on both public health systems and clinical practitioners. Despite notable advancements in diagnostic and therapeutic modalities, early detection remains paramount in improving patient outcomes and enhancing survival rates. In response to this imperative, the integration of predictive modelling techniques within healthcare has garnered substantial attention in recent years, offering promising avenues for bolstering early detection strategies and optimizing patient care pathways.