cancers

Systematic Review
AI-Driven Models for Diagnosing and Predicting Outcomes in
Lung Cancer: A Systematic Review and Meta-Analysis
Mohammed Kanan 1, * , Hajar Alharbi 2 , Nawaf Alotaibi 3 , Lubna Almasuood 4 , Shahad Aljoaid 5 , Tuqa Alharbi 6 ,
Leen Albraik 7 , Wojod Alothman 8 , Hadeel Aljohani 9 , Aghnar Alzahrani 10 , Sadeem Alqahtani 11 ,
Razan Kalantan 9 , Raghad Althomali 12 , Maram Alameen 12 and Ahdab Mufti 13

1 Department of Clinical Pharmacy, King Fahad Medical City, Riyadh 12211, Saudi Arabia
2 Department of Medicine, Gdansk Medical University, 80210 Gdansk, Poland
3 Department of Clinical Pharmacy, Northern Border University, Rafha 73213, Saudi Arabia
4 Department of Pharmacy, Qassim University, Buraydah 52571, Saudi Arabia
5 Department of Medicine, University of Tabuk, Tabuk 47911, Saudi Arabia
6 Department of Medicine, Qassim University, Buraydah 52571, Saudi Arabia
7 Department of Medicine, Al-Faisal University, Riyadh 12385, Saudi Arabia; [email protected]
8 Department of Medicine, Imam Abdulrahman Bin Faisal University, Dammam 31411, Saudi Arabia
9 Department of Medicine and Surgery, King Abdulaziz University, Jeddah 22230, Saudi Arabia
10 Department of Medicine, Al-Baha University, Al Bahah 65964, Saudi Arabia
11 Department of Pharmacy, King Khalid University, Abha 62217, Saudi Arabia
12 Department of Medicine, Taif University, Taif 26311, Saudi Arabia
13 Department of Medicine, Ibn Sina National College, Jeddah 22230, Saudi Arabia
* Correspondence: [email protected]

Simple Summary: This research explores the transformative potential of artificial intelligence (AI) in
the early detection of lung cancer. Through a comprehensive systematic review and meta-analysis,
this study evaluates the effectiveness of AI models, emphasizing a promising avenue for improving
diagnostic accuracy. Among 1024 identified records, 39 studies were meticulously selected and
Citation: Kanan, M.; Alharbi, H.; analyzed following the PRISMA guidelines. The findings highlight significant strides in AI’s role,
Alotaibi, N.; Almasuood, L.; Aljoaid, S.; emphasizing the need for standardized protocols. Despite the observed heterogeneity, this study
Alharbi, T.; Albraik, L.; Alothman, W.; underscores AI’s promising impact on lung cancer screening, laying the groundwork for future ad-
Aljohani, H.; Alzahrani, A.; et al. vancements in clinical practice. This research contributes crucial insights for healthcare professionals
AI-Driven Models for Diagnosing and
and researchers alike, aiming to enhance the early diagnosis and management of lung cancer.
Predicting Outcomes in Lung Cancer: A
Systematic Review and Meta-Analysis.
Abstract: (1) Background: Lung cancer’s high mortality due to late diagnosis highlights a need
Cancers 2024, 16, 674. https://
for early detection strategies. Artificial intelligence (AI) in healthcare, particularly for lung cancer,
doi.org/10.3390/cancers16030674
offers promise by analyzing medical data for early identification and personalized treatment. This
Academic Editors: Athanasia Pataka, systematic review evaluates AI’s performance in early lung cancer detection, analyzing its techniques,
Serafeim Chrysovalantis Kotoulas and strengths, limitations, and comparative edge over traditional methods. (2) Methods: This systematic
Dionisios G. Spyratos
review and meta-analysis followed the PRISMA guidelines rigorously, outlining a comprehensive
Received: 19 November 2023 protocol and employing tailored search strategies across diverse databases. Two reviewers inde-
Revised: 20 January 2024 pendently screened studies based on predefined criteria, ensuring the selection of high-quality data
Accepted: 25 January 2024 relevant to AI’s role in lung cancer detection. The extraction of key study details and performance
Published: 5 February 2024 metrics, followed by quality assessment, facilitated a robust analysis using R software (Version
4.3.0). The process, depicted via a PRISMA flow diagram, allowed for the meticulous evaluation
and synthesis of the findings in this review. (3) Results: From 1024 records, 39 studies met the
inclusion criteria, showcasing diverse AI model applications for lung cancer detection, emphasizing
Copyright: © 2024 by the authors.
varying strengths among the studies. These findings underscore AI’s potential for early lung cancer
Licensee MDPI, Basel, Switzerland.
diagnosis but highlight the need for standardization amidst study variations. The results demonstrate
This article is an open access article
distributed under the terms and
promising pooled sensitivity and specificity of 0.87, signifying AI’s accuracy in identifying true
conditions of the Creative Commons positives and negatives, despite the observed heterogeneity attributed to diverse study parameters.
Attribution (CC BY) license (https:// (4) Conclusions: AI demonstrates promise in early lung cancer detection, showing high accuracy
creativecommons.org/licenses/by/ levels in this systematic review. However, study variations underline the need for standardized
4.0/). protocols to fully leverage AI’s potential in revolutionizing early diagnosis, ultimately benefiting

Cancers 2024, 16, 674. https://doi.org/10.3390/cancers16030674 https://www.mdpi.com/journal/cancers

Cancers 2024, 16, 674 2 of 18

patients and healthcare professionals. As the field progresses, validated AI models from large-scale
perspective studies will greatly benefit clinical practice and patient care in the future.

Keywords: AI-driven models; diagnosing; predicting; outcomes; lung cancer; systematic review;
meta-analysis

1. Introduction
Lung cancer remains a formidable global health challenge, claiming the lives of
millions of individuals each year [1]. The high mortality rate associated with lung cancer is
primarily attributed to the advanced stage at which it is often diagnosed [2]. Lung cancer
is notorious for its asymptomatic early stages, making it extremely difficult to diagnose
until it has reached an advanced, often incurable, stage. The later the diagnosis, the more
limited the treatment options, and the grimmer the prognosis for patients. In contrast,
when lung cancer is detected at an early stage, the chances of successful treatment and long-
term survival increase significantly. Consequently, there is a pressing need for innovative
strategies to enable early detection, as this could significantly improve the prognosis and
overall survival rates of lung cancer patients [3]. In recent years, the field of artificial
intelligence (AI) has emerged as a promising avenue for achieving this goal. In the field
of healthcare, AI has shown promise in improving diagnostic accuracy, predicting disease
outcomes, and personalizing treatment plans [4]. In the context of lung cancer, AI systems
can analyze vast datasets of medical images, patient records, and genetic information to
identify patterns and abnormalities that may elude human perception. These systems can
not only detect lung cancer at earlier stages, but also assist in risk assessment and treatment
planning [5].
Current methods for early lung cancer detection include screening programs such
as low-dose computed tomography (LDCT) and the analysis of biomarkers. While these
approaches have demonstrated some success, they are not without limitations [6]. LDCT,
for instance, may lead to overdiagnosis and increased healthcare costs. AI systems can
potentially enhance the effectiveness of these methods by providing more precise and
efficient analysis, reducing false positives and false negatives, and offering a complemen-
tary approach to existing techniques. Despite the potential benefits of AI in early lung
cancer detection, several challenges and considerations must be addressed [7,8]. The perfor-
mance of AI models can vary depending on the quality and diversity of the data used for
training [9,10]. Therefore, the selection and curation of data are fundamental to the success
of AI-based systems in this context.
This systematic review and metanalysis endeavors to provide a comprehensive evalu-
ation of the performance of AI systems for the early detection of lung cancer. This paper
analyzed the current state of AI applications in lung cancer detection, including the various
techniques and approaches being utilized. Furthermore, the study critically assessed the
advantages and limitations of AI-based methods compared to traditional approaches.

2. Materials and Methods

In conducting this systematic review and meta-analysis evaluating the performance of
AI systems for the early detection of lung cancer, we meticulously adhered to the Preferred
Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. The
following detailed Method Section outlines the steps taken in this comprehensive review.

2.1. Protocol Development

The research question was formulated to assess the performance of AI systems in
early lung cancer detection. A detailed protocol was developed, outlining the inclusion
and exclusion criteria, search strategy, and methods for data extraction and analysis. In
accordance with the journal’s guidelines, this systematic review was not registered in
Cancers 2024, 16, 674 3 of 18

any specific database prior to its initiation. While the journals encourage registration for
systematic reviews, it is not a mandatory requirement universally practiced in the field.
This decision was aligned with established practices within this domain, considering the
extensive body of previously published systematic reviews without prior registration in
reputable peer-reviewed journals.

2.2. Literature Search

Comprehensive searches were conducted in electronic databases, including PubMed,
Google Scholar, Science direct, and Embase, to identify relevant studies published up to
October 2023. The inclusion of Google Scholar helped us to identify the grey literature,
conference papers, and other non-traditional sources of information.

2.3. Search Strategy

The search strategy included a combination of keywords and Medical Subject Heading
(MeSH) terms related to lung cancer, artificial intelligence, and early detection. The search
strategy was tailored to each database to account for variations in syntax and indexing.
This ensured that no relevant studies were missed.

2.4. Study Selection

Two independent reviewers screened titles and abstracts for eligibility based on pre-
defined criteria. The initial screening of titles and abstracts helped in rapidly identifying
studies that met the inclusion criteria and eliminating those that did not. Full-text articles
of potentially relevant studies were retrieved for further assessment. A full-text review was
conducted on potentially relevant studies to ensure that the selection process was rigorous,
and that the final dataset was of high quality.

2.5. Eligibility Criteria

2.5.1. Inclusion Criteria
Studies evaluating the performance of AI systems for the early detection of lung
cancer.
Original research articles published in English.
Studies reporting sensitivity, specificity, and other relevant diagnostic performance
metrics.

2.5.2. Exclusion Criteria

Studies lacking sufficient data on AI system performance.
Reviews, commentaries, and conference abstracts without primary data.

2.6. Data Extraction

Relevant data, including study characteristics, AI system details, validation methods,
and diagnostic performance metrics, were extracted using a standardized data extraction
form. Two reviewers independently extracted data from selected studies. Discrepancies
were resolved through discussion or consultation with a third reviewer.

2.7. Quality Assessment

The quality of the included studies was assessed using appropriate tools, considering
factors such as study design, patient selection, and AI system evaluation. A risk-of-bias
graph and summary were generated to visually represent the methodological quality of
the included studies.

2.8. Data Synthesis and Analysis

The meta-analysis was carried out using R software (Version 4.3.0, Vienna, Austria)
along with the RStudio interface (Version 2023.03.0, Boston, MA, USA). Packages and
libraries such as meta and metafor were utilized to calculate key performance metrics,
Cancers 2024, 16, 674 4 of 18

including pooled sensitivity and specificity, along with their associated confidence inter-
vals, i.e., 95%. Moreover, the presence of heterogeneity among the included studies was
evaluated using a chi-square test and I2 index statistics.

2.9. Reporting
A PRISMA flow diagram was used to illustrate the study selection process, including
the number of studies identified, screened, assessed for eligibility, and included in the
final analysis.

3. Results
The flow diagram in Figure 1 shows that the researchers identified 1024 records from
the databases, but only 116 records were assessed for eligibility. At the identification stage,
326 records were excluded due to duplication. During the screening stage, 28 records were
excluded because they were not in English. Some records lacked the essential data required
for the systematic review. Records that did not have full-text versions available for review
were excluded. Review articles, which summarize and analyze existing research, were
excluded during the screening stage. After completing the identification and screening
stages, the research team identified 39 studies that met the inclusion criteria and were
relevant to the systematic review. These studies formed the basis for the subsequent data
extraction and analysis, contributing to the comprehensive evaluation of AI systems for
early lung cancer detection in the systematic review.
In Table 1, we present an overview of the characteristics of the included studies
in our systematic review, each focusing on the application of AI models for the early
detection of lung cancer. The table encompasses a diverse range of studies conducted across
different countries and utilizing various AI models and data sources. When comparing
and contrasting the results of these studies, several key insights emerge. While studies
such as Wu et al. (2022) and Alexander et al. (2020) achieved notably high specificity
levels, suggesting the potential for reducing false positives in clinical settings, Baldwin
et al. (2020) achieved exceptionally high sensitivity, minimizing the risk of missing cancer
cases [4,7,10]. On the other hand, the study by Chen (2022) showcases the effectiveness
of AI models, specifically CNN and RNN, in improving the overall accuracy of lung
cancer prediction [8]. Notably, Huang et al. (2018) integrated sensor array technology
with machine learning, demonstrating its promise in the precise identification of lung
cancer, especially when compared to traditional models [11]. Li et al. (2019) conducted a
retrospective study in China using 3D deep learning technology on CT scans [9]. Their AI
system achieved a sensitivity of 75% and specificity of 82%, resulting in an overall accuracy
of 88.8%. This research emphasized the potential of AI as a diagnostic tool capable of
providing more precise and unbiased outcomes in the diagnosis of pulmonary nodules,
ultimately reducing the interpretation time for radiologists. Choi et al. (2018), from the
USA, conducted a retrospective study using Support Vector Machine (SVM) and LASSO
on LIDC-IDRI data [5]. Their AI model achieved an accuracy of 84.6%, which was notably
12.4% higher than the accuracy for Lung-RADS. This result demonstrated the potential of
AI in substantially improving the accuracy of lung cancer detection. In another study from
China employed a 3D CMixNet model on LUNA-16 and LIDC-IDRI datasets. Their system
achieved a sensitivity of 94.0% and specificity of 91.0%, showcasing better results compared
to existing methods for lung cancer detection. These variations in results highlight the
trade-offs between sensitivity and specificity, as well as the distinct strengths of different AI
models and approaches. While some studies emphasize the potential of AI in overcoming
specific challenges, such as PD-L1 assessment or eligibility assessment, others underscore
the efficiency and reliability of AI in lung cancer screening. Collectively, these findings
underscore the transformative potential of AI in enhancing the accuracy and efficiency
of lung cancer diagnosis, promising significant benefits to both patients and healthcare
professionals. Collectively, these results underscore the transformative role AI can play
in improving the accuracy, efficiency, and reliability of lung cancer diagnosis, ultimately
 Cancers 2024, 16, 674 5 of 18

x FOR PEER REVIEW benefiting patients and healthcare professionals. Our systematic review incorporates
6 of 15
these findings to offer a holistic understanding of the state of AI in lung cancer detection,
shedding light on the remarkable potential of these technologies in the field of oncology.

Figure 1. Flowchart of included

Figure studies.
1. Flowchart of included studies.
Cancers 2024, 16, 674 6 of 18

Table 1. Characteristics of included studies.

Source of Key Performance Metrics of AI Models Validation

Author and Year Country Study Design AI Models Used Outcomes
Dataset Sensitivity Specificity Accuracy Method

AI-assisted system can be an

Wu et al., 2022 Retrospective Whole slide effective and valuable tool to
China DL 86% 96.4% 93.2% NA
[7] study images overcome the challenges of
PD-L1 assessment.
AI-based approach using CNN
H-E stained
Chen 2022 Retrospective and RCN could be very effective
China CNN and RNN pathological 95.1% 34.4% 92% NA
[8] study for improving the accuracy of
slices
predicting lung cancer.
AI may represent a valuable
diagnostic tool that shows more
3D deep precise and unbiased outcomes
Li et al., 2019 Retrospective Internal
China learning CT scans 75% 82% 88.8% in the diagnosis of pulmonary
[9] study validation
technology nodules, thus minimizing the
time required for interpretation
of results by radiologists.
The AI-assisted system enables
Alexander efficient and reliable screening of
Retrospective Internal
et al., 2020 Australia ML and NLP TMC 83.3% 93.8% 91.6% cancer patients, with an accuracy
study validation
[10] of 91.6% for overall
eligibility assessment.
The LCP-CNN approach
Baldwin
Retrospective External minimizes the risk of missing
et al., 2020 UK LCP-CNN EDC 99.5% 28% -
study validation cancer cases when compared to
[4]
the Brock model.
The proposed AI model achieved
Choi et al., 2018 Retrospective Cross- 84.6% accuracy, which was 12.4%
USA SVM-LASSO LIDC-IDRI 87.2% 81.2% 84.6%
[5] study validation higher than accuracy for
Lung-RADS.
Cancers 2024, 16, 674 7 of 18

Table 1. Cont.

Source of Key Performance Metrics of AI Models Validation

Author and Year Country Study Design AI Models Used Outcomes
Dataset Sensitivity Specificity Accuracy Method

For internal For internal For internal

The integration of the sensor
validation validation validation External
array technique and machine
Huang et al., 2018 Prospective 92.3% 92.9% 92.7% validation/
Taiwan ML - learning enables the precise
[11] study For external For external For external internal
identification of lung cancer with
validation validation validation validation
high accuracy.
83.3% 86.2% 85.4%
The proposed fusion algorithm
Li et al., 2019 Retrospective 3D deep CNN Cross- achieved the highest specificity,
China LIDC_IDRI 82.6% 91.3% 93.0%
[12] study (SS-OLHF) validation sensitivity, and accuracy scores
among all classification models.
The proposed system, evaluated
Nasrullah
Retrospective LUNA-16 and on LIDC-IDRI datasets, showed
et al., 2019 China 3D CMixNet 94.0% 91.0% - -
study LIDC-IDRI better results compared to the
[13]
existing methods.
Microarray data GLCM features predicted lung
Reddy et al., 2018 Retrospective Cross-
India GLCM clustering 95.3% 100% 97.6% tumor with higher accuracy than
[14] study validation
mechanisms histogram features.
ML algorithms may help in fully
Schwyzer
Retrospective Cross- automated lung cancer detection
et al., 2018 Switzerland ANN Internal 93.6% 95.5% 94.7%
study validation even at a low effective
[15]
radiation doses.
DL models have the potential to
increase consistency and
Ardila et al., 2019 Retrospective LUNA, LIDC Internal
USA 3D CNN 64.7% 95.2% - accuracy and enable the
[16] study and NLST validation
adoption of lung
cancer screening.
Cancers 2024, 16, 674 8 of 18

Table 1. Cont.

Source of Key Performance Metrics of AI Models Validation

Author and Year Country Study Design AI Models Used Outcomes
Dataset Sensitivity Specificity Accuracy Method

The outcomes suggest that DL

Coudray
Retrospective Internal can assist healthcare
et al., 2018 USA CNN TCGA 89% 93% -
study validation professionals in the detection
[17]
of cancer.
Hussein The proposed approach achieved
Internal
et al., 2017 USA - 3D CNN LIDC-IDRI - - 91.2% cutting-edge outcomes in
validation
[18] regressing malignancy scores.
This algorithm has the potential
to provide reliable and
For subset A:
Venkadesh reproducible malignancy risk
Retrospective NLST and 91% Cross-
et al., 2021 Denmark DL 90% - scores for experts, which could
study DLCST For subset B: validation
[19] contribute to promoting the
54%
effectiveness of lung cancer
screening management.
The performance of the proposed
DL model in classifying nodule
Ciompi et al., 2017 The Retrospective MILD and Internal
CNN - - 72.9% type surpassed that of
[20] Netherlands study DLCST validation
conventional machine
learning approaches.
The lung cancer screening DBNs
Petousis were reported to have high
Retrospective Cross-
et al., 2016 USA DBN NLST - - - discrimination and predictive
study validation
[21] power with most of the cancer as
well as non-cancer cases.
The 3D CNN with a DL
Zhang et al., 2019 Retrospective LUNA and Cross- algorithm may assist experts by
China 3D CNN 84.4% 83% -
[22] study Kaggle validation providing accurate data for
diagnosing pulmonary nodules.
Cancers 2024, 16, 674 9 of 18

Table 1. Cont.

Source of Key Performance Metrics of AI Models Validation

Author and Year Country Study Design AI Models Used Outcomes
Dataset Sensitivity Specificity Accuracy Method

The proposed model reduced the

Petousis
Retrospective Cross- FPR while maintaining TPR, and
et al., 2019 USA ML and DBN NLST - - -
study validation improved early prediction of
[23]
cancer cases.
Huang et al., 2019 Retrospective NLST and External DL scores could be used for early
USA DL 88% 60% -
[24] study PanCan validation detection of cancer cases.
The DL system had better
Cui et al., 2020 Retrospective External identification sensitivity and
China DL LUNA 90% 85% -
[25] study validation performance than that of
the experts.
The utilization of visual analysis
Chauvie
Retrospective Cross- along with NN could help
et al., 2020 Italy Neural network - 90% 100% 100%
study validation experts to reduce the number of
[26]
false positive cases.
The proposed AI resulted in a
NHS Cancer
Tam et al., 2021 Retrospective reduction in radiologist errors
UK DNN Registry 80% 93% 87% -
[27] study and improved clinician reporting
Database
performance.
For BSREM For BSREM
Schwyzer AI performed substantially better
Retrospective 69.2% 84.5% Cross-
et al., 2020 Switzerland DL - - on images with BSREM
study For OSEM For OSEM validation
[28] than OSEM.
66.7% 79.0%
CNN technique can be very
Teramoto
Retrospective Cross- effective for the early detection
et al., 2010 Japan CNN - 90.1% - -
study validation of pulmonary nodules in
[29]
PET/CT images.
Kirienko CNNs can be used as a reliable
Retrospective Independent Cross-
et al., 2018 Italy CNN - 67% 69% tool to assist in the staging of
study dataset validation
[30] lung cancer patients.
Cancers 2024, 16, 674 10 of 18

Table 1. Cont.

Source of Key Performance Metrics of AI Models Validation

Author and Year Country Study Design AI Models Used Outcomes
Dataset Sensitivity Specificity Accuracy Method

Independent CNN achieved high diagnostic

Sibille et al., 2020 US and Retrospective Independent
Deep CNN 81.0% 97.3% - internal performance when both PET and
[31] Germany study dataset
validation CT images were utilized.
ANNs can provide more
Toney et al., 2014 Prospective Independent accurate and consistent
USA ANN - - 99.2% -
[32] study dataset assessment of nodal stage in lung
cancer patients.
ANNs have potential to improve
Scott et al., 2019 Retrospective Independent External diagnostic certainty and can be
USA ANN 100% 93.1% -
[33] study dataset validation useful to help direct clinical and
imaging follow-up.
SVM SVM
52.6% 67.1%
RF RF
52.6% 67.1%
An ML approach with PET-based
Hyun et al., 2019 Retrospective RF, NN, NBS, Independent NN NN Internal
Korea - radiomics aids in early detection
[34] study LL, SVM dataset 52.6% 67.1% validation
of lung cancer.
NBS NBS
52.6% 67.1%
LL LL
52.6% 67.1%
BN models are better at handling
Jayasurya Belgium and
Retrospective Independent External missing data as compared to
et al., 2010 the BN - - -
study dataset validation SVM models and are more
[35] Netherlands
suitable for the medical domain.
Cancers 2024, 16, 674 11 of 18

Table 1. Cont.

Source of Key Performance Metrics of AI Models Validation

Author and Year Country Study Design AI Models Used Outcomes
Dataset Sensitivity Specificity Accuracy Method

The proposed BN model is stable

and can identify hierarchical
Luo et al., 2018 Retrospective Independent Cross-
USA BN - - - relationships among biophysical
[36] study dataset validation
features for the prediction of
lung cancer.
AI software strongly agrees with
Chamberlin USA,
Retrospective Independent Internal expert radiologist determination
et al., 2021 Europe, and CNN 100% 70.8% -
study data set validation of detection of both lung nodules
[37] Asia
and CACV.
This study reported that ANN
Hsu et al., 2020 Retrospective Hospital-based Cross- had better sensitivity for the
Taiwan ANN 75.0% 85.0% -
[6] study cancer registry validation detection of lung cancer than
Lung-RADS.
C5.0-1 C5.0-1
61.8% 73.4% These AI models can be utilized
Decision tree
Duan et al., 2020 Retrospective SVM SVM for the on-site screening and
China C5.0, ANN, - - -
[38] study 59.2% 68.7% clinical diagnosis of the
SVM
ANN ANN high-risk population.
81.5% 65.6%
The proposed DL models
demonstrated promising
Silva et al., 2017 Retrospective Internal
Brazil Deep CNN LIDC-IDRI 94.6% 95.1% 94.7% performance and avoided the
[39] study validation
need for feature extraction and
selection steps.
The proposed DL had a better
Trajanovski
Retrospective Kaggle, NLST, External sensitivity of 93% and can be
et al., 2021 USA CNN 93% - -
study and UCM validation used for the screening of
[40]
lung cancer.
Cancers 2024, 16, 674 12 of 18

Table 1. Cont.

Source of Key Performance Metrics of AI Models Validation

Author and Year Country Study Design AI Models Used Outcomes
Dataset Sensitivity Specificity Accuracy Method

The DL-based AI film reading

Chen et al., 2022 Retrospective Self-built data External system has higher sensitivity for
China CNN 94.1% 77.7% 87.1%
[41] study from hospital validation the diagnosis of NSCLC than
radiologists.
The performance of the
observers in evaluating the risk
Coruch et al., 2021 Retrospective Cross-
Turkey CNN Hospital records 92.2% 58.7% 75.2% of malignancy was slightly
[42] study validation
higher than the performance of
fusion AI algorithms.
PD-L1 = programmed death-ligand 1, CNN = convolutional neural network, RNN = recurrent neural network, ML = machine learning, NLP = natural language processing,
TMC = thoracic malignancies cohort, SVM-LASSO = support vector machine–least absolute linkage and selection operator, EDC = electronic data capture, RADS = Reporting and
Data System, CMixNet = customized mixed link network, LIDC = lung image database consortium, IDRI = image database resource initiative. GLCM = gray level co-event matrix,
NLST = National Lung Cancer Screening Trial, LUNA = lung nodule analysis, TCGA = the Cancer Genome Atlas, DLCST = Danish lung cancer screening trial, MILD = multicenter
Italian lung detection, RF = random Forest, BN = Bayesian network, DNN = deep neural network, BSREM = block-sequential regularized expectation maximization, OSEM = ordered
subset expectation maximization, ANN = artificial neural network, GGO = ground-glass opacities, LL = logistic regression, NBS = naïve Bayesian system, NN = neural network,
UCM = University of Chicago.
Cancers 2024,16,
Cancers2024, 16,674
x FOR PEER REVIEW 10
13 of 18
15

Figures
Figures 22 and
and 33 present
present forest
forest plots
plots of
of the
the pooled
pooled sensitivity
sensitivity and
and sensitivity
sensitivity of
of AI
AI
models for the early diagnosis of lung cancer. The pooled sensitivity and specificity
models for the early diagnosis of lung cancer. The pooled sensitivity and specificity of AI of
AI models across the included studies were 0.87 (95% CI: 0.82–0.90) and 0.87
models across the included studies were 0.87 (95% CI: 0.82–0.90) and 0.87 (95% CI: 0.80– (95% CI:
0.80–0.91), respectively.
0.91), respectively. These These results
results indicate
indicate thatthat AI models
AI models demonstrated
demonstrated a high
a high level
level of
of accuracy in correctly identifying true positives and true negatives, showing
accuracy in correctly identifying true positives and true negatives, showing promising promising
results for the early diagnosis of lung cancer. However, heterogeneity was observed
results for the early diagnosis of lung cancer. However, heterogeneity was observed
among the included studies. This heterogeneity may be attributed to variations in study
among the included studies. This heterogeneity may be attributed to variations in study
populations, data sources, and model specifications. The results of quality assessments are
populations, data sources, and model specifications. The results of quality assessments
presented in Figure 4.
are presented in Figure 4.

Figure 2.
Figure 2. Forest
Forest plot
plot of
of pooled
pooled sensitivity
sensitivity of
of AI
AI models
models [4,5,7–42].
[4,5,7–42].
Cancers 2024, 16, 674 14 of
Cancers 2024, 16, x FOR PEER REVIEW 11 of 18
15
Cancers 2024, 16, x FOR PEER REVIEW 11 of 15

Figure
Figure3.3.3.Forest
Figure Forest plot
Forestplot of
plotof pooled
ofpooled specificity
specificityofof
pooledspecificity AI
ofAI models
AImodels [4,5,7–42].
models[4,5,7–42].
[4,5,7–42].

Figure
Figure4.4.Quality
Qualityassessment
assessmentof
ofincluded
includedstudies
studiesusing
usingQUADAS-2
QUADAS-2tool
tool[43]
[43]. .
Figure 4. Quality assessment of included studies using QUADAS-2 tool [43].

4.4.4.Discussion
Discussion
Discussion
Lung
Lung cancer
cancerisisis
Lungcancer one
one
oneofof
of the
the most
most
the prevalent
prevalent
most prevalent diseases
diseases worldwide
worldwide
diseases worldwideandand
thethe
and leading
leading
the cause
cause
leading of
cause
of cancer-associated
cancer-associated
of cancer-associated deaths,deaths, with
with with
deaths, an estimated
an estimated 2.2
2.2 million
an estimated million new
new cases
2.2 million cases
newand and 1.8
1.8 million
cases million
and 1.8 deaths
million
deaths
in deaths in
in2020
2020 [44].
2020 [44].
[44].Currently,
Currently, a CT scan
Currently, aaCT
of scan
CTthe of
ofthe
chest
scan chest
is the
the isisthe
most
chest most
mostfrequent
frequent
the methodmethod
frequent of of
oflung
lung cancer
method lung
cancer
cancer screening.
screening. Its Its high
high resolution
resolution can
can elucidate
elucidate the
the association
association among
among surrounding
surrounding
Cancers 2024, 16, 674 15 of 18

screening. Its high resolution can elucidate the association among surrounding organs
and blood vessels more clearly, and it plays a significant role in the early detection of lung
cancer [45]. However, the accuracy of this method can be influenced by benign lesions
such as necrosis, inflammation, tuberculosis, various textures in lung images, and several
other factors like the experience of radiologists, potentially leading to misdiagnosis and
omissions [46]. With the implementation of AI-assisted diagnostic systems into clinical
practice, a new era has dawned in the field of lung cancer diagnosis. Recent studies have
documented the growing and widespread utilization of AI models in clinical diagnosis and
treatment, respectively [47–49]. AI models primarily focus on diagnosing and evaluating
various medical images, including skin lesions, pathological microscopic images, and
radiological data. AI models are remarkable in their ability to enhance diagnostic accuracy,
stability, and work efficiency.
This review documented promising results, indicating that AI models for the early
diagnosis of lung cancer demonstrated a high level of accuracy, with pooled sensitivity
and specificity values of 0.87 (95% CI: 0.82–0.90) and 0.87 (95% CI: 0.80–0.91), respectively.
These findings suggest that AI models exhibit significant capability in correctly identifying
true positives and true negatives. Liu et al. recently conducted a systematic review and
meta-analysis in which they also demonstrated the commendable performance of AI
models in predicting lung cancer, with a pooled sensitivity and specificity of 89% and 87%,
respectively [46]. Robust performance is sometimes crucial in terms of lung cancer, where
early detections substantially impact patient outcomes. High accuracy of more than 90%
was observed in this study, which aligns with the broader trend in the medical literature
supporting the effectiveness of AI in diagnostic settings [7,8,10,12,14,15,26,32]. However,
a lower pooled accuracy was also reported in studies mainly focused on lung cancer
screening, specifically considering the results obtained across all studies [20,30,34,42] and
those in which a CNN model was employed [20,30,42], ranging from 67–75%, respectively.
Despite these consolidated findings, we are confident that AI models are a valuable resource
for radiologists to detect lung cancer.
AI-assisted diagnostic systems result in different diagnostic outcomes. A study re-
ported that a 3D CNN model exhibited greater advantages in detecting lung cancer as
compared to improvements seen with other AI models [18]. However, in two studies,
ANN achieved high diagnostic performance that could be useful for the detection of lung
cancer [32,33]. Distinct algorithms demonstrate diverse diagnostic capabilities, notably in
radionics and deep learning, which not only assist in predicting the benign or malignant
nature of lung nodules, but also identify the prognosis of small-cell lung cancer [50,51]. The
utilization of AI models in clinical practice is promising; however, validity remains a critical
step for generalizability. Among 39 articles, 15 articles performed cross-validation to assess
the effectiveness and reliability of AI models [5,6,12,14,15,19,21,23,26,28–30,36,42,50].
Despite the overall positive outcomes, observed heterogeneity among the included
studies was identified. Therefore, future research should focus on refining AI models, con-
sidering the identified heterogeneity challenges. Collaborative efforts among researchers,
clinicians, and policymakers are essential to establish guidelines and standards for the
development and evaluation of AI systems in lung cancer screening. By addressing these
challenges collectively, the field can progress toward the implementation of AI technolo-
gies in clinical settings, ultimately improving the early diagnosis and management of
lung cancer.
The current study has certain limitations that should be addressed: (1) The exclusion
of the studies lacking complete diagnostic data may have altered the results. (2) While
conducting this comprehensive search, only English language articles were included, po-
tentially introducing language bias. (3) The high heterogeneity among all included studies
may be attributed to variations in study populations, data sources, and model specifica-
tions, and these results warrant further investigation. (4) The included studies were mainly
designed retrospectively, which may have affected the overall quality of the systematic
review and meta-analysis. Despite the initial verification of AI models’ effectiveness in lung
Cancers 2024, 16, 674 16 of 18

cancer screening, most of the AI-based approaches are still in the laboratory research stage
and have not yet been implemented into clinical practice. Limitations are evident in data
integration, image data quality, legal liability definition, complex pathology diagnosis and
cost of use. However, a huge volume of experienced healthcare professionals, especially
radiologists and pathologists, are getting involved in AI-assisted lung cancer detection. It is
anticipated that AI models will play a significant role in the early detection of lung cancer.

5. Conclusions
This systematic review and meta-analysis reported the promising outcomes of AI
models in the early detection of lung cancer. The pooled sensitivity and specificity values
of 0.87 (95% CI: 0.82–0.90) and 0.87 (95% CI: 0.80–0.91) showed the potential of AI models
in identifying true positives and true negatives. Regarding the observed heterogeneity
among the included studies, these findings highlight the need for standardized protocols in
the development of AI models for lung cancer screening. As the medical field continues to
grow, healthcare professionals and patients will benefit from the integration of AI models in
clinical practice once these models have been validated in large-scale prospective studies.

Author Contributions: Conceptualization, M.K., L.A. (Leen Albraik) and H.A. (Hajar Alharbi);
methodology, N.A. and L.A. (Lubna Almasuood); validation, S.A. (Shahad Aljoaid) and T.A.; formal
analysis, L.A. (Lubna Almasuood) and W.A.; investigation, H.A. (Hajar Alharbi) and A.A.; resources,
S.A. (Shahad Aljoaid), R.K., and R.A.; data curation, R.K., R.A. and M.A.; writing—original draft
preparation, M.K., L.A. (Leen Albraik), H.A. (Hadeel Aljohani) and N.A.; writing—review and editing,
S.A. (Sadeem Alqahtani), A.A. and R.K.; visualization, R.A., M.A. and A.M.; project administration,
M.K., S.A. (Sadeem Alqahtani) and H.A. (Hadeel Aljohani). All authors have read and agreed to the
published version of the manuscript.
Funding: This research received no external funding.
Conflicts of Interest: The authors declare no conflicts of interest.

References
1. Wang, Z.; Hu, L.; Li, J.; Wei, L.; Zhang, J.; Zhou, J. Magnitude, temporal trends and inequality in global burden of tracheal,
bronchus and lung cancer: Findings from the Global Burden of Disease Study 2017. BMJ Glob. Health 2020, 5, e002788. [CrossRef]
[PubMed]
2. Chaft, J.E.; Rimner, A.; Weder, W.; Azzoli, C.G.; Kris, M.G.; Cascone, T. Evolution of systemic therapy for stages I–III non-metastatic
non-small-cell lung cancer. Nat. Rev. Clin. Oncol. 2021, 18, 547–557. [CrossRef] [PubMed]
3. Roointan, A.; Mir, T.A.; Wani, S.I.; Hussain, K.K.; Ahmed, B.; Abrahim, S.; Savardashtaki, A.; Gandomani, G.; Gandomani, M.;
Chinnappan, R. Early detection of lung cancer biomarkers through biosensor technology: A review. J. Pharm. Biomed. Anal. 2019,
164, 93–103. [CrossRef]
4. Baldwin, D.R.; Gustafson, J.; Pickup, L.; Arteta, C.; Novotny, P.; Declerck, J.; Kadir, T.; Figueiras, C.; Sterba, A.; Exell, A. External
validation of a convolutional neural network artificial intelligence tool to predict malignancy in pulmonary nodules. Thorax 2020,
75, 306–312. [CrossRef]
5. Choi, W.; Oh, J.H.; Riyahi, S.; Liu, C.J.; Jiang, F.; Chen, W.; White, C.; Rimner, A.; Mechalakos, J.G.; Deasy, J.O. Radiomics analysis
of pulmonary nodules in low-dose CT for early detection of lung cancer. Med. Phys. 2018, 45, 1537–1549. [CrossRef]
6. Hsu, Y.-C.; Tsai, Y.-H.; Weng, H.-H.; Hsu, L.-S.; Tsai, Y.-H.; Lin, Y.-C.; Hung, M.-S.; Fang, Y.-H.; Chen, C.-W. Artificial neural
networks improve LDCT lung cancer screening: A comparative validation study. BMC Cancer 2020, 20, 1023. [CrossRef]
7. Wu, J.; Liu, C.; Liu, X.; Sun, W.; Li, L.; Gao, N.; Zhang, Y.; Yang, X.; Zhang, J.; Wang, H. Artificial intelligence-assisted system for
precision diagnosis of PD-L1 expression in non-small cell lung cancer. Mod. Pathol. 2022, 35, 403–411. [CrossRef]
8. Chen, S. Models of artificial intelligence-assisted diagnosis of lung cancer pathology based on deep learning algorithms. J. Healthc.
Eng. 2022, 2022, 3972298. [CrossRef]
9. Li, X.; Hu, B.; Li, H.; You, B. Application of artificial intelligence in the diagnosis of multiple primary lung cancer. Thorac. Cancer
2019, 10, 2168–2174. [CrossRef]
10. Alexander, M.; Solomon, B.; Ball, D.L.; Sheerin, M.; Dankwa-Mullan, I.; Preininger, A.M.; Jackson, G.P.; Herath, D.M. Evaluation of
an artificial intelligence clinical trial matching system in Australian lung cancer patients. JAMIA Open 2020, 3, 209–215. [CrossRef]
11. Huang, C.-H.; Zeng, C.; Wang, Y.-C.; Peng, H.-Y.; Lin, C.-S.; Chang, C.-J.; Yang, H.-Y. A study of diagnostic accuracy using a
chemical sensor array and a machine learning technique to detect lung cancer. Sensors 2018, 18, 2845. [CrossRef]
12. Li, S.; Xu, P.; Li, B.; Chen, L.; Zhou, Z.; Hao, H.; Duan, Y.; Folkert, M.; Ma, J.; Huang, S. Predicting lung nodule malignancies by
combining deep convolutional neural network and handcrafted features. Phys. Med. Biol. 2019, 64, 175012. [CrossRef]
Cancers 2024, 16, 674 17 of 18

13. Nasrullah, N.; Sang, J.; Alam, M.S.; Mateen, M.; Cai, B.; Hu, H. Automated lung nodule detection and classification using deep
learning combined with multiple strategies. Sensors 2019, 19, 3722. [CrossRef]
14. Reddy, U.J.; Ramana Reddy, B.V.; Reddy, B.E. Categorization & recognition of lung tumor using machine learning representations.
Curr. Med. Imaging 2019, 15, 405–413.
15. Schwyzer, M.; Ferraro, D.A.; Muehlematter, U.J.; Curioni-Fontecedro, A.; Huellner, M.W.; von Schulthess, G.K.; Kaufmann, P.A.;
Burger, I.A.; Messerli, M. Automated detection of lung cancer at ultralow dose PET/CT by deep neural networks—Initial results.
Lung Cancer 2018, 126, 170–173. [CrossRef]
16. Ardila, D.; Kiraly, A.P.; Bharadwaj, S.; Choi, B.; Reicher, J.J.; Peng, L.; Tse, D.; Etemadi, M.; Ye, W.; Corrado, G. End-to-end lung
cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat. Med. 2019, 25, 954–961.
[CrossRef]
17. Coudray, N.; Ocampo, P.S.; Sakellaropoulos, T.; Narula, N.; Snuderl, M.; Fenyö, D.; Moreira, A.L.; Razavian, N.; Tsirigos, A.
Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nat. Med.
2018, 24, 1559–1567. [CrossRef]
18. Hussein, S.; Cao, K.; Song, Q.; Bagci, U. Risk Stratification of Lung Nodules Using 3D CNN-Based Multi-Task Learning; Springer
International Publishing: Berlin/Heidelberg, Germany, 2017; pp. 249–260.
19. Venkadesh, K.V.; Setio, A.A.A.; Schreuder, A.; Scholten, E.T.; Chung, K.; Wille, W.M.M.; Saghir, Z.; van Ginneken, B.; Prokop, M.;
Jacobs, C. Deep learning for malignancy risk estimation of pulmonary nodules detected at low-dose screening CT. Radiology 2021,
300, 438–447. [CrossRef]
20. Ciompi, F.; Chung, K.; Van Riel, S.J.; Setio, A.A.A.; Gerke, P.K.; Jacobs, C.; Scholten, E.T.; Schaefer-Prokop, C.; Wille, M.M.W.;
Marchiano, A. Towards automatic pulmonary nodule management in lung cancer screening with deep learning. Sci. Rep. 2017, 7,
46479. [CrossRef] [PubMed]
21. Petousis, P.; Han, S.X.; Aberle, D.; Bui, A.A.T. Prediction of lung cancer incidence on the low-dose computed tomography arm of
the National Lung Screening Trial: A dynamic Bayesian network. Artif. Intell. Med. 2016, 72, 42–55. [CrossRef] [PubMed]
22. Zhang, C.; Sun, X.; Dang, K.; Li, K.; Guo, X.w.; Chang, J.; Yu, Z.Q.; Huang, F.Y.; Wu, Y.S.; Liang, Z. Toward an expert level of lung
cancer detection and classification using a deep convolutional neural network. Oncologist 2019, 24, 1159–1165. [CrossRef]
23. Petousis, P.; Winter, A.; Speier, W.; Aberle, D.R.; Hsu, W.; Bui, A.A.T. Using sequential decision making to improve lung cancer
screening performance. Ieee Access 2019, 7, 119403–119419. [CrossRef]
24. Huang, P.; Lin, C.T.; Li, Y.; Tammemagi, M.C.; Brock, M.V.; Atkar-Khattra, S.; Xu, Y.; Hu, P.; Mayo, J.R.; Schmidt, H. Prediction of
lung cancer risk at follow-up screening with low-dose CT: A training and validation study of a deep learning method. Lancet
Digit. Health 2019, 1, e353–e362. [CrossRef] [PubMed]
25. Cui, S.; Ming, S.; Lin, Y.; Chen, F.; Shen, Q.; Li, H.; Chen, G.; Gong, X.; Wang, H. Development and clinical application of deep
learning model for lung nodules screening on CT images. Sci. Rep. 2020, 10, 13657. [CrossRef] [PubMed]
26. Chauvie, S.; De Maggi, A.; Baralis, I.; Dalmasso, F.; Berchialla, P.; Priotto, R.; Violino, P.; Mazza, F.; Melloni, G.; Grosso, M.
Artificial intelligence and radiomics enhance the positive predictive value of digital chest tomosynthesis for lung cancer detection
within SOS clinical trial. Eur. Radiol. 2020, 30, 4134–4140. [CrossRef]
27. Tam, M.D.B.S.; Dyer, T.; Dissez, G.; Morgan, T.N.; Hughes, M.; Illes, J.; Rasalingham, R.; Rasalingham, S. Augmenting lung cancer
diagnosis on chest radiographs: Positioning artificial intelligence to improve radiologist performance. Clin. Radiol. 2021, 76,
607–614. [CrossRef]
28. Schwyzer, M.; Martini, K.; Benz, D.C.; Burger, I.A.; Ferraro, D.A.; Kudura, K.; Treyer, V.; von Schulthess, G.K.; Kaufmann, P.A.;
Huellner, M.W.; et al. Artificial intelligence for detecting small FDG-positive lung nodules in digital PET/CT: Impact of image
reconstructions on diagnostic performance. Eur. Radiol. 2020, 30, 2031–2040. [CrossRef]
29. Teramoto, A.; Fujita, H.; Yamamuro, O.; Tamaki, T. Automated detection of pulmonary nodules in PET/CT images: Ensemble
false-positive reduction using a convolutional neural network technique. Med. Phys. 2016, 43, 2821–2827. [CrossRef]
30. Kirienko, M.; Sollini, M.; Silvestri, G.; Mognetti, S.; Voulaz, E.; Antunovic, L.; Rossi, A.; Antiga, L.; Chiti, A. Convolutional neural
networks promising in lung cancer T-parameter assessment on baseline FDG-PET/CT. Contrast Media Mol. Imaging 2018, 2018,
1382309. [CrossRef]
31. Sibille, L.; Seifert, R.; Avramovic, N.; Vehren, T.; Spottiswoode, B.; Zuehlsdorff, S.; Schäfers, M. 18F-FDG PET/CT uptake
classification in lymphoma and lung cancer by using deep convolutional neural networks. Radiology 2020, 294, 445–452.
[CrossRef]
32. Toney, L.K.; Vesselle, H.J. Neural networks for nodal staging of non–small cell lung cancer with FDG PET and CT: Importance of
combining uptake values and sizes of nodes and primary tumor. Radiology 2014, 270, 91–98. [CrossRef] [PubMed]
33. Scott, J.A.; McDermott, S.; Kilcoyne, A.; Wang, Y.; Halpern, E.F.; Ackman, J.B. Comparison of 18F-FDG avidity at PET of benign
and malignant pure ground-glass opacities: A paradox? Part II: Artificial neural network integration of the PET/CT characteristics
of ground-glass opacities to predict their likelihood of malignancy. Clin. Radiol. 2019, 74, 692–696. [CrossRef]
34. Hyun, S.H.; Ahn, M.S.; Koh, Y.W.; Lee, S.J. A machine-learning approach using PET-based radiomics to predict the histological
subtypes of lung cancer. Clin. Nucl. Med. 2019, 44, 956–960. [CrossRef]
35. Jayasurya, K.; Fung, G.; Yu, S.; Dehing-Oberije, C.; De Ruysscher, D.; Hope, A.; De Neve, W.; Lievens, Y.; Lambin, P.; Dekker, A.
Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients
treated with radiotherapy. Med. Phys. 2010, 37, 1401–1407. [CrossRef]
Cancers 2024, 16, 674 18 of 18

36. Luo, Y.; McShan, D.; Ray, D.; Matuszak, M.; Jolly, S.; Lawrence, T.; Kong, F.-M.; Ten Haken, R.; El Naqa, I. Development of a fully
cross-validated Bayesian network approach for local control prediction in lung cancer. IEEE Trans. Radiat. Plasma Med. Sci. 2018,
3, 232–241. [CrossRef]
37. Chamberlin, J.; Kocher, M.R.; Waltz, J.; Snoddy, M.; Stringer, N.F.C.; Stephenson, J.; Sahbaee, P.; Sharma, P.; Rapaka, S.; Schoepf,
U.J.; et al. Automated detection of lung nodules and coronary artery calcium using artificial intelligence on low-dose CT scans for
lung cancer screening: Accuracy and prognostic value. BMC Med. 2021, 19, 55. [CrossRef]
38. Duan, S.; Cao, H.; Liu, H.; Miao, L.; Wang, J.; Zhou, X.; Wang, W.; Hu, P.; Qu, L.; Wu, Y. Development of a machine learning-based
multimode diagnosis system for lung cancer. Aging 2020, 12, 9840. [CrossRef]
39. da Silva, G.L.F.; da Silva Neto, O.P.; Silva, A.C.; de Paiva, A.C.; Gattass, M. Lung nodules diagnosis based on evolutionary
convolutional neural network. Multimed. Tools Appl. 2017, 76, 19039–19055. [CrossRef]
40. Trajanovski, S.; Mavroeidis, D.; Swisher, C.L.; Gebre, B.G.; Veeling, B.S.; Wiemker, R.; Klinder, T.; Tahmasebi, A.; Regis, S.M.;
Wald, C.; et al. Towards radiologist-level cancer risk assessment in CT lung screening using deep learning. Comput. Med. Imaging
Graph. 2021, 90, 101883. [CrossRef]
41. Chen, Y.; Tian, X.; Fan, K.; Zheng, Y.; Tian, N.; Fan, K. The value of artificial intelligence film reading system based on deep
learning in the diagnosis of non-Small-Cell lung cancer and the significance of efficacy monitoring: A retrospective, clinical,
nonrandomized, controlled study. Comput. Math. Methods Med. 2022, 2022, 2864170. [CrossRef]
42. Gürsoy Çoruh, A.; Yenigün, B.; Uzun, Ç.; Kahya, Y.; Büyükceran, E.U.; Elhan, A.; Orhan, K.; Kayı Cangır, A. A comparison of the
fusion model of deep learning neural networks with human observation for lung nodule detection and classification. Br. J. Radiol.
2021, 94, 20210222. [CrossRef]
43. Whiting, P.F.; Rutjes, A.W.S.; Westwood, M.E.; Mallett, S.; Deeks, J.J.; Reitsma, J.B.; Leeflang, M.M.G.; Sterne, J.A.C.; Bossuyt,
P.M.M.; QUADAS-2 Group. QUADAS-2: A revised tool for the quality assessment of diagnostic accuracy studies. Ann. Intern.
Med. 2011, 155, 529–536. [CrossRef]
44. Leiter, A.; Veluswamy, R.R.; Wisnivesky, J.P. The global burden of lung cancer: Current status and future trends. Nat. Rev. Clin.
Oncol. 2023, 20, 624–639. [CrossRef]
45. Lauri, H. High-resolution CT of the lungs: Indications and diagnosis. Duodecim Laaketieteellinen Aikakauskirja 2017, 133, 549–556.
46. Liu, M.; Wu, J.; Wang, N.; Zhang, X.; Bai, Y.; Guo, J.; Zhang, L.; Liu, S.; Tao, K. The value of artificial intelligence in the diagnosis
of lung cancer: A systematic review and meta-analysis. PLoS ONE 2023, 18, e0273445. [CrossRef]
47. Binczyk, F.; Prazuch, W.; Bozek, P.; Polanska, J. Radiomics and artificial intelligence in lung cancer screening. Transl. Lung Cancer
Res. 2021, 10, 1186. [CrossRef]
48. Rabbani, M.; Kanevsky, J.; Kafi, K.; Chandelier, F.; Giles, F.J. Role of artificial intelligence in the care of patients with nonsmall cell
lung cancer. Eur. J. Clin. Investig. 2018, 48, e12901. [CrossRef]
49. Espinoza, J.L.; Dong, L.T. Artificial intelligence tools for refining lung cancer screening. J. Clin. Med. 2020, 9, 3860. [CrossRef]
50. Zhang, X.; Zhang, Y.; Zhang, G.; Qiu, X.; Tan, W.; Yin, X.; Liao, L. Deep Learning With Radiomics for Disease Diagnosis and
Treatment: Challenges and Potential. Front. Oncol. 2022, 12, 773840. [CrossRef] [PubMed]
51. Braghetto, A.; Marturano, F.; Paiusco, M.; Baiesi, M.; Bettinelli, A. Radiomics and deep learning methods for the prediction of
2-year overall survival in LUNG1 dataset. Sci. Rep. 2022, 12, 14132. [CrossRef] [PubMed]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.