The development and application of a novel precise health management model for pulmonary nodules population: a prospective cohort study

Introduction

It was estimated that there were 20 million new cases of cancer and nearly 10 million cancer-related deaths in 2022 (1). Lung cancer is the leading cause of cancer-related mortality, and accounts for 18.0% of all cancer deaths (1). Studies such as the National Lung Screening Trial in the United States of America and Nederlands Leuvens Screening Onderzoek in The Netherlands have shown that early lung cancer screening is a crucial step in reducing the morbidity and mortality of lung cancer, as well as in improving cure rates and survival rates (2-5). With advancements in medical imaging technology, low-dose computed tomography (LDCT) has been extensively applied to early lung cancer screening. During this screening process, the detection rate of pulmonary nodules (PNs) has been continuously increasing, but so too has the false-positive rate, making the management of PNs a focal point of clinical work. Differentiating between benign and malignant PNs is a challenge. The accurate assessment of the risk of malignancy in PNs and the implementation of appropriate management strategies are significant challenges in the field of population health management (6).

Traditional management approaches for PNs often rely on frequent radiologic surveillance and physician experience-based judgments that lack personalization and precision. Further, poor patient adherence initiates a pathogenic cascade comprising data fragmentation, diagnostic bias, and defensive medicine, which elevates the risks of misdiagnosis, missed diagnosis, overtreatment, and delayed treatment, as well as causing psychological harm to patients. Therefore, establishing a more precise and personalized model for the health management of the population affected by PNs would be of great importance to improve the quality of life of patients in terms of follow-up efficiency and enhancement of medical experience, saving economic resources.

The aim of the study was to explore management models, formulate personalized follow-up plans, build a novel follow-up script system for lung nodules, and apply a multidisciplinary team (MDT) approach to evaluate the PNs. The study hypothesize that the proposed model will establish a scientifically rigorous and resource-efficient clinical management framework for PN patients, potentially serving as a guideline for optimizing future clinical workflows. We present this article in accordance with the TREND reporting checklist (available at https://jtd.amegroups.com/article/view/10.21037/jtd-2025-906/rc).

Methods

Research subjects

From May to December 2021, 2,816 patients who underwent early lung cancer screening with LDCT at the Health Management Center of The Affiliated Hospital of Qingdao University were consecutively enrolled in this study. The inclusion criteria were: (I) PNs detected for the first time during a physical examination; (II) aged ≥18 years; (III) initial examination using 64-slice LDCT. Patients were excluded from the study if they met any of the following exclusion criteria: (I) PNs previously detected during lung screening, or history of PNs or other tumors; (II) lung surgery due to pulmonary diseases; (III) indicated at the initial diagnosis that they could not complete the follow-up visits for various reasons; and/or (IV) initial Psychological Evaluation Module-D (PEM-D) results highlighting anxiety (i.e., an anxiety score ≥50 points). The study was conducted in accordance with the Declaration of Helsinki and its subsequent amendments, and was approved by the Ethics Committee of The Affiliated Hospital of Qingdao University (number: QYFYWZLL29241, date: April 23, 2021). All patients provided informed consent.

Intervention method

The patients were allocated to the following two groups: the intervention group (Group A), which was managed using the intervention, and the control group (Group B), which was managed using a traditional model.

The following implementation method was employed under the prospectively designed precision-based management model for PN patients:

• Establishment of a special work group. A precise health management work group for PNs was established that comprised internal medical staff from the Health Management Center, Laoshan Ward of The Affiliated Hospital of Qingdao University, including physician, surgeon, radiologist, psychologist, and several nurses. All the physicians and nurses participated in the follow-up work. A group leader was selected, who was responsible for the overall work and coordinating cooperation among the various specialties.
• Implementation of the workflow design.
• After each patient underwent an LDCT scan, the lung images were submitted to the imaging diagnosis center, and a preliminary diagnosis was made by a radiologist. The diagnosis was then transmitted to the chief physician at the Health Management Center, who made diagnosis.
• The nursing team summarized the diagnostic results of the chief physician, compiled information on the PN patient, and provided it to the PN health management work group for refined management.

Three specialist physicians in the group conducted a comprehensive risk assessment using the patient’s clinical information (e.g., age, smoking history, family history, and occupational exposure history), imaging characteristics (e.g., nodule size, shape, edge, and density), and biomarker and genetic information. Referring to the Lung Imaging Reporting And Data System (Lung-RADS) version 1.1 [2019] (7) and the Chinese guidelines for lung cancer screening (Beijing, 2021) (8), the risk level of the PNs for the patients was assessed as follows: extremely high risk (patients who were clinically diagnosed with malignant tumors upon initial imaging diagnosis); high risk (patients who needed immediate further examination to clarify the nature of the lesion and required interventions by the relevant departments); moderate risk [patients who needed to be re-examined in the short term (i.e., less than 6 months) to closely observe changes in the lesion, and who did not currently require interventions by relevant departments]; and low-risk [patients who did not require interventions and only required long-term (i.e., 12 months or more) follow-up].

If an extreme high-risk PN was discovered by the radiologist based on the LDCT scan, the radiologist notified the work group immediately. The group leader then contacted the patient the same day, and an MDT consultation was arranged for further diagnosis and treatment.

The high-risk patients were followed by physicians from the management group, who professionally informed the patients of and answered questions about the subsequent management plan, the importance of the standardized diagnosis and treatment of PNs, and the necessity of timely follow-up visits to ensure the cooperation of the patient or their family members. The moderate-risk patients were followed by professional nurses from the management group by telephone, ensuring that the follow-up information was successfully conveyed to the patient or their family members. The low-risk patients were notified by text message. The continuous follow-up work for the three risk levels of patients was completed by the nursing team.

We have summarized hundreds of follow-up call recordings and derived the most efficient and accurate script system (Figure 1) from them. Then all the personnel engaged in the follow-up work were trained. All follow-up telephone calls were based on a script system to achieve unified standards and effects. The questions frequently asked by patients during the telephone follow-up process were recorded, organized, and standardized answers were formulated. A database was established that was regularly updated to improve the script system.

Figure 1 Flow chart of the follow-up procedure. CT, computed tomography.

The work group held an MDT meeting for PN patients every Wednesday. The high-risk patients underwent to MDT consultations by physicians from the radiology, respiratory medicine, thoracic surgery, and oncology departments after completing their first follow-up visit. A treatment or follow-up plan was then formulated. Patients who needed further treatment were referred to the relevant department; while those who needed continued observation were downgraded to the moderate-risk level for continued follow-up. Multiple disease patients were managed by a hospital-wide MDT that formulated a comprehensive treatment plan and a full-course management plan.

For the high- and medium-risk PN patients, the nurses reminded them of their follow-up appointments via phone calls and text messages within one week before the follow-up date. The follow-up time, results, and management plans were recorded. The manual phone follow-up endpoint was when the patient received the appropriate clinical treatment (e.g., surgery, chemotherapy, or radiotherapy), or when the PN was downgraded to low risk after timely follow-up. The endpoint of the text message follow-up was when the PN disappeared, or the risk level of the nodule increased to medium, high, or extremely high.

This study employed a triple-reading mechanism for PN evaluation to ensure diagnostic reliability and consistency. Specifically, the imaging analysis in Group A was independently performed by board-certified radiologists, each with over 10 years of experience in thoracic imaging. During the initial phase, two radiologists conducted blinded assessments using a double-blind method to evaluate nodule morphological characteristics (including size, margin, calcification patterns) and malignancy risk stratification (high/low risk), with findings documented through standardized scoring sheets. A systematic arbitration protocol was automatically activated when discrepancies occurred in either risk categorization (e.g., high-risk vs. low-risk) or ≥2 critical morphological descriptors. The third senior radiologist (15+ years of experience) then performed adjudication, incorporating consensus principles from the Fleischner Society guidelines for final determination.

The Self-rating Anxiety Scale (SAS) was used to evaluate the anxiety status of the patients during the first screening and each follow-up visit. The psychological physicians within the work group summarized the results of the patients’ psychological status. For patients with severe anxiety during the follow-up process (i.e., an anxiety score ≥70 points), timely psychological counseling and re-evaluation were provided to reduce the occurrence of psychological harm.

Under the traditional management method for PNs, the chief physician made a diagnosis based on the results of the chest LDCT and provided corresponding guidance, such as further diagnosis and treatment in the respiratory medicine or thoracic surgery department, continued observation, and regular re-examination. The follow-up nurse summarized the information of those who needed to be re-examined in the short term (less than 6 months) and notified the patient of the follow-up time, and the patient sought medical treatment on their own.

Evaluation methods and indicators

The baseline data of the two groups was recorded, including gender, age, location of PNs, types of PNs, and PN size.

The follow-up time after the detection of PNs, post-examination management plan, and the PN outcomes in the two groups were determined. The types of computed tomography (CT) examinations, including chest LDCT, conventional chest CT, chest CT enhanced, chest high-resolution CT, PN three-dimensional CT, and positron emission tomography/CT, were recorded in the follow-up process. The dose length product (DLP) was recorded in the radiation dose report for each CT examination, and the effective dose (ED) was calculated as follows: ED = DLP × weight factor κ (0.014 mSv·mGy⁻¹ cm⁻¹) (9). The time, location, and postoperative pathological diagnosis for each patient’s surgical treatment were recorded.

Timely follow-up visits, the average cumulative ED, the percentage of patients who have surgery at the hospital, the percentage of benign nodules in the surgical patients, the percentage of patients diagnosed with malignant tumors in Tumor Node Metastasis (TNM) stage I after surgery, and the follow-up interval for the low-risk PN patients were evaluated. The outcomes for PNs were defined as follows: enlargement, no change, reduction, disappearance, and surgery. Follow-up visits were classified as follows: timely (a subsequent visit within the suggested follow-up time of one month); delayed (a subsequent visit after the recommended time of more than one month); and loss to follow up (a loss of contact or no re-examination after the first follow-up). The rate of patients who had surgery in the hospital was defined as the percentage of patients who underwent surgery at The Affiliated Hospital of Qingdao University among all the patients who underwent surgical treatment. The rate of benign nodules in the surgical patients was defined as the percentage of patients diagnosed with benign nodules among all the patients who underwent surgical treatment. The 8^th edition of the Staging Manual of the American Joint Committee on Cancer was used to determine the postoperative pathological TNM stage of the lung cancer patients.

Psychological status evaluation: the SAS was used to assess the anxiety status of the patients in both groups at the initial screening and each subsequent visit. Anxiety score was defined; score of 0–49 indicated no anxiety, while score of 50 or above indicated anxiety. The psychological anxiety status was compared between the two groups up to January 2024, or until the follow-up endpoint.

Up to January 2024, or until the endpoint of follow-up was reached, a questionnaire survey was used to compare the satisfaction levels of the two groups. The outcomes were categorized across the following five levels: very satisfied, satisfied, somewhat satisfied, dissatisfied, and very dissatisfied.

A pos-hoc power analysis confirmed 80% power to detect a ≥15% difference in the main outcome between groups (α =0.05).

Statistical analysis

The statistical analysis was conducted using SPSS 27.0 software (IBM). The quantitative data are expressed as the mean ± standard deviation, and inter-group comparisons were made using the independent samples t-test. The categorical data are expressed as the number of cases (percentage), and inter-group comparisons were made using the chi-square test. All the statistical tests were two-tailed. A P value <0.05 was considered statistically significant. Missing values were systematically documented across variables. For variables with <10% missing data, a complete case analysis was applied.

Results

Baseline data

From May to December 2021, a total of 2,816 patients were consecutively enrolled in this study. The intervention group (Group A) included 1,178 patients (624 males, 554 females), with an average age of 50.72±13.406 years; no missing data were observed in any variables of interest, including gender, age, nodule characteristics, follow-up outcomes, and CT radiation dose parameters. The control group (Group B) included 1,638 patients (912 males, 726 females), with an average age of 50.909±14.032 years (Figure 2).

Figure 2 Participant flow diagram according to CONSORT guidelines.

A further statistical analysis was done classifying PNs into three subgroups based on size and type: non-solid nodules (NS) <8 mm; solid (S) or part-solid (PS) nodules <6 mm; NS 8 mm to <15 mm; S or NS 6 mm to <15 mm; NS, S, or PS ≥15 mm. No significant difference in the percentage of the same subgroups was observed considering the Group A and the Group B in terms of nodule size grading. In relation to the risk grading of the PNs, no significant difference was observed between the two Groups within the same risk category. The average time of follow-up was 22.61±0.25 months in the intervention group and 21.92±0.223 months in the control group up to January 2024, or until the follow-up endpoint. There were no significant differences between the two Groups in terms of age, gender, nodule location, or nodule type. The central characteristic data of the patients can be found in Table 1.

Comparison of patient adherence

Group A demonstrated significantly lower loss-to-follow-up rates and superior adherence to scheduled visits compared to Group B across all follow-up metrics (all P<0.05). The characteristics of the follow-up between the two Groups were described in Table 2.

Radiation exposure situation

The average cumulative ED of the intervention group was significantly lower than that of the control group. The average follow-up interval for the low-risk PN patients was much longer in the Group A than the Group B (see Table 2).

Postoperative pathological diagnosis situation

The percentage of benign nodules in surgical patients in the intervention group was significantly lower than that in the control group (χ²=4.771, P=0.044). The two groups showed no statistically significant difference in TNM stage I patient counts (χ²=2.601, P=0.11) (see Table 2).

Patient psychological status evaluation

By the follow-up deadline of January 1, 2024, or upon reaching the endpoint, Group A had a lower average anxiety score than the Group B. Additionally, Group A exhibited a significantly lower incidence of anxiety compared to Group B (χ²=11.843, P<0.001) (see Table 2).

Patient satisfaction evaluation

By the follow-up endpoint, Group A exhibited a significantly lower incidence of anxiety compared to Group B (χ²=17.176, P<0.001) (see Table 2).

Discussion

The field of population health management has rapidly developed, and early lung cancer screening has become a hot topic in medical research in recent years. Many countries adopt LDCT for early lung cancer screening (2,3,10-14), and the detection rate of PNs is high; however, the handling of these nodules still leaves doubts (15-18). Therefore, to improve the quality and efficiency of nodule management, we proposed a precise health way intervention for PN patients.

Lim et al. (19) developed a customized application and business process for radiologists that significantly improved the follow-up rate of patients with PNs. However, such processes still faced barriers in gaining the cooperation of clinical doctors. In our experience, MDT allowed systemic interventions to promote the consistency of guidelines applying it to the early screening stage of lung cancer, while also providing a multidisciplinary basis for deviating from the guidelines to formulate personalized monitoring and treatment plans and addressing the needs of heterogeneous patient populations (20-24). Based on the operation mode of The Affiliated Hospital of Qingdao University Health Management Center, the PN MDT comprised fixed experts from various specialties at The Affiliated Hospital of Qingdao University Health Management Center, ensuring the timeliness and convenience of the MDT approach. If the MDT team at the center could not provide a clear management plan, the case was upgraded to an in-hospital MDT to further clarify the diagnosis. The level-to-level MDT approach in the intervention provided a comprehensive clinical management strategy for PN populations, saving patients the trouble of visiting various specialist clinics such as thoracic surgery, respiratory medicine, and oncology, and reducing consultation difficulties. Standardized protocols, predefined outcomes, uniform staging criteria, explicit follow-up definitions, and data collection by experienced physicians were implemented to address potential sources of bias.

In the follow-up phase of this study, to ensure the effectiveness of the precise management of PNs, we conceived a unified follow-up script system, unified standards, and unified content for communication, ensuring the effectiveness of information exchange between doctors and patients, and facilitating the quality control of the follow-up process. To our knowledge, this is the first description of a follow-up script system that could be employed in the health management of PN populations worldwide. Our script system has a follow-up link that can provide science and health education to patients, improving their knowledge of PNs, enabling them to better understand the lung screening results, without attending other medical institutions for additional checks to confirm the medical findings. This allowed patients to actively cooperate with timely re-examination, increasing the likelihood of their choosing to undergo surgical treatment at The Affiliated Hospital of Qingdao University.

Langan et al. (25) found that high-quality doctor-patient communication, clinical decision support tools, and radiological reports, including guideline templates, can improve adherence with guidelines. The construction and application of the novel model in this study provided strong evidence in support of this theory. Further, patient adherence with the management strategy was greatly improved, and the percentage of patients with benign nodules (according to the postoperative pathology results) was significantly lower in the intervention group than the control group. Thus, the intervention was more accurate in the early identification and risk assessment of PNs, reducing unnecessary surgical interventions. The visit interval time of patients with low-risk PNs in the intervention group was significantly increased, indicating that as a result of the intervention, patients with low-risk PNs, who should be observed for a long time, did not undergo overly frequent imaging examinations to repeatedly assess the status of the lesion. The average cumulative ED was significantly lower in the intervention group than the control group, indicating that the intervention effectively reduced the radiation exposure of patients with PNs; thus, after the precise health management intervention, patients with PNs may choose lower radiation dose approaches for re-examination. Standardized protocols, predefined outcomes, uniform staging criteria, explicit follow-up definitions, and data collection by experienced physicians were implemented to address potential sources of bias.

Overdiagnosis is also an important issue in the process of early lung cancer screening (26-28). Due to the application of a level-to-level MDT approach and the ease of follow-up using the script system, our model avoided overdiagnosis bias as much as possible. The new model resulted in more appropriate treatment strategy selection and better medical resource allocation. The significant reduction in the psychological anxiety of the intervention group and the improvement in their satisfaction with the PN management services indicate that the model improved patients’ quality of life and trust in medical institutions.

Our intervention had many advantages, but it also had some limitations. In this study, in terms of the postoperative TNM staging of the lung cancer patients, the proportion of TNM stage I in patients with malignant tumors who underwent surgical treatment was higher in the intervention group than the control group, but the difference between the two groups was not statistically significant. This may be because the follow-up period was relatively short, and the sample size of surgical patients was relatively small. The outcome for the entire population has not yet been determined. As the follow-up study continues, there might be more valuable findings. The exclusion of structured smoking cessation protocols from the intervention represents another limitation, as tobacco use is a risk modifier for PN progression. Future iterations of this model must incorporate evidence-based cessation strategies. At present, most of the intervention work needs to be completed manually, relying on the health management center of a large-scale medical institution, and has high labor costs. Artificial intelligence (AI) technology has been widely studied and applied in the field of imaging diagnosis (29-31). In our future research, we will seek to save human resources in the follow-up process of PNs with the help of AI technology. Currently, an active follow-up management system for PN patients has been established by our research group based on the concept of open-source large language models and Self-Consistency with Chain of Thought to improve efficiency and accuracy of follow-up management.

Conclusions

Our novel model for the precise health management of PNs provided more rational and effective management strategies for patients, simplified the consultation process, reduced radiation exposure, avoided excessive diagnosis and treatment, reduced psychological harm, and improved medical service quality. The standardized and modular design of this model enables its seamless adaptation to diverse healthcare settings, facilitating scalable implementation in resource-varying institutions. Additionally, we also discussed the challenges encountered in the implementation of the intervention and suggested possible solutions, providing a foundation for future research.

Acknowledgments

An earlier version of this work was presented as a poster at the 2024 World Conference on Lung Cancer (WCLC) [location, San Diego, CA, USA], [September 7–10, 2024], under the title “The Construction and Application of a Novel Precise Health Management Model for Lung Nodule Population” (Abstract #1193).

We would like to express our appreciation to the Pulmonary Nodule Management Team of the Health Management Center at The Affiliated Hospital of Qingdao University, who collaborated in the patient follow up, particularly Dr. Fenglei Xu, who provided technical assistance in radiological evaluations. We would like to express our deep gratitude to all the pulmonary nodule patients and their families for entrusting us with their clinical data. Finally, we would like to thank our families for their unwavering support throughout this research endeavor. All acknowledged individuals/institutions have consented to being listed herein.

Footnote

Reporting Checklist: The authors have completed the TREND reporting checklist. Available at https://jtd.amegroups.com/article/view/10.21037/jtd-2025-906/rc

Data Sharing Statement: Available at https://jtd.amegroups.com/article/view/10.21037/jtd-2025-906/dss

Peer Review File: Available at https://jtd.amegroups.com/article/view/10.21037/jtd-2025-906/prf

Funding: This work was supported by the “Clinical Medicine +X” research project of The Affiliated Hospital of Qingdao University (No. QDFY-X2023130).

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://jtd.amegroups.com/article/view/10.21037/jtd-2025-906/coif). The authors have no conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved. The study was conducted in accordance with the Declaration of Helsinki and its subsequent amendments, and was approved by the Ethics Committee of The Affiliated Hospital of Qingdao University (number: QYFYWZLL29241, date: April 23, 2021). All patients provided informed consent.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

References

1. Jokhadze N, Das A, Dizon DS. Global cancer statistics: A healthy population relies on population health. CA Cancer J Clin 2024;74:224-6. [Crossref] [PubMed]
2. National Lung Screening Trial Research Team. Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 2011;365:395-409. [Crossref] [PubMed]
3. de Koning HJ, van der Aalst CM, de Jong PA, et al. Reduced Lung-Cancer Mortality with Volume CT Screening in a Randomized Trial. N Engl J Med 2020;382:503-13. [Crossref] [PubMed]
4. Potter AL, Rosenstein AL, Kiang MV, et al. Association of computed tomography screening with lung cancer stage shift and survival in the United States: quasi-experimental study. BMJ 2022;376:e069008. [Crossref] [PubMed]
5. Oudkerk M, Liu S, Heuvelmans MA, et al. Lung cancer LDCT screening and mortality reduction - evidence, pitfalls and future perspectives. Nat Rev Clin Oncol 2021;18:135-51. [Crossref] [PubMed]
6. Adams SJ, Stone E, Baldwin DR, et al. Lung cancer screening. Lancet 2023;401:390-408. [Crossref] [PubMed]
7. American College of Radiology Committee on Lung-RADS website. Lung-RADS assessment categories version1.1. 2020. Available online: https://www.acr.org/-/media/ACR/Files/RADS/Lung-RADS/LungRADSAssessmentCategoriesv1-1.pdf
8. He J, Li N, Chen WQ, et al. China guideline for the screening and early detection of lung cancer(2021, Beijing). Zhonghua Zhong Liu Za Zhi 2021;43:243-68. [Crossref] [PubMed]
9. Lee C. How to estimate effective dose for CT patients. Eur Radiol 2020;30:1825-7. [Crossref] [PubMed]
10. Ghimire B, Maroni R, Vulkan D, et al. Evaluation of a health service adopting proactive approach to reduce high risk of lung cancer: The Liverpool Healthy Lung Programme. Lung Cancer 2019;134:66-71. [Crossref] [PubMed]
11. Crosbie PAJ, Gabe R, Simmonds I, et al. Participation in community-based lung cancer screening: the Yorkshire Lung Screening Trial. Eur Respir J 2022;60:2200483. [Crossref] [PubMed]
12. Bartlett EC, Kemp SV, Ridge CA, et al. Baseline Results of the West London lung cancer screening pilot study - Impact of mobile scanners and dual risk model utilisation. Lung Cancer 2020;148:12-9. [Crossref] [PubMed]
13. Crosbie PA, Balata H, Evison M, et al. Implementing lung cancer screening: baseline results from a community-based 'Lung Health Check' pilot in deprived areas of Manchester. Thorax 2019;74:405-9. [Crossref] [PubMed]
14. Cheng YI, Davies MPA, Liu D, et al. Implementation planning for lung cancer screening in China. Precis Clin Med 2019;2:13-44. [Crossref] [PubMed]
15. Smith RA, Andrews KS, Brooks D, et al. Cancer screening in the United States, 2019: A review of current American Cancer Society guidelines and current issues in cancer screening. CA Cancer J Clin 2019;69:184-210. [Crossref] [PubMed]
16. US Preventive Services Task Force. Screening for Lung Cancer: US Preventive Services Task Force Recommendation Statement. JAMA 2021;325:962-70. [Crossref] [PubMed]
17. Doubeni CA, Gabler NB, Wheeler CM, et al. Timely follow-up of positive cancer screening results: A systematic review and recommendations from the PROSPR Consortium. CA Cancer J Clin 2018;68:199-216. [Crossref] [PubMed]
18. Fillon M. Medical centers tout benefits of lung cancer screening, but rarely address potential harms. CA Cancer J Clin 2020;70:319-20. [Crossref] [PubMed]
19. Lim PS, Schneider D, Sternlieb J, et al. Process improvement for follow-up radiology report recommendations of lung nodules. BMJ Open Qual 2019;8:e000370. [Crossref] [PubMed]
20. Verdial FC, Madtes DK, Cheng GS, et al. Multidisciplinary Team-Based Management of Incidentally Detected Lung Nodules. Chest 2020;157:985-93. [Crossref] [PubMed]
21. Roberts TJ, Lennes IT, Hawari S, et al. Integrated, Multidisciplinary Management of Pulmonary Nodules Can Streamline Care and Improve Adherence to Recommendations. Oncologist 2020;25:431-7. [Crossref] [PubMed]
22. Subramanian MP. Commentary: Much to do about nodules-Improving care with a multidisciplinary pulmonary nodule clinic. J Thorac Cardiovasc Surg 2020;159:1569-70. [Crossref] [PubMed]
23. Polanco D, González J, Gracia-Lavedan E, et al. Multidisciplinary virtual management of pulmonary nodules. Pulmonology 2024;30:239-46. [Crossref] [PubMed]
24. Cubillos L, Brenner AT, Birchard K, et al. Multidisciplinary quality improvement initiative to standardize reporting of lung cancer screening. Transl Lung Cancer Res 2018;7:S297-301. [Crossref] [PubMed]
25. Langan RC, Goodbred AJ. Pulmonary Nodules: Common Questions and Answers. Am Fam Physician 2023;107:282-91.
26. Yankelevitz DF, Henschke CI. Overdiagnosis in lung cancer screening. Transl Lung Cancer Res 2021;10:1136-40. [Crossref] [PubMed]
27. Patz EF Jr, Pinsky P, Gatsonis C, et al. Overdiagnosis in low-dose computed tomography screening for lung cancer. JAMA Intern Med 2014;174:269-74. [Crossref] [PubMed]
28. Carter JL, Coletti RJ, Harris RP. Quantifying and monitoring overdiagnosis in cancer screening: a systematic review of methods. BMJ 2015;350:g7773. [Crossref] [PubMed]
29. Silvestri GA, Jett JR. The Intersection of Lung Cancer Screening, Radiomics, and Artificial Intelligence: Can One Scan Really Predict the Future Development of Lung Cancer? J Clin Oncol 2023;41:2141-3. [Crossref] [PubMed]
30. Grossi F, Le VK, Baudot P, et al. 919P Artificial intelligence supporting lung cancer screening: Computer aided diagnosis of lung lesions driven by morphological feature extraction. Ann Oncol 2022;33:S967.
31. Santos RSd. MA11.09 Artificial Intelligence in Lung Cancer Screening: Accuracy and Predictive Value. J Thorac Oncol 2022;17:S83-4.

(English Language Editor: L. Huleatt)