Feasibility and acceptability of a smart healthcare cloud platform based on a standardized discourse form in the postoperative follow-up of patients with non-small cell lung cancer

Introduction

Lung cancer is the leading cause of cancer and cancer-related death in China and around the world (1,2). Surgical resection remains the mainstay of treatment for lung cancer (3,4). Postoperative follow-up provides information on the health status of patients after surgery and is essential for long-term survival (5). Traditional outpatient follow-up has several disadvantages, including difficulties related to registration, long waiting time, and complex visit processes. To address these disadvantages and improve the efficiency of follow-up, our center has innovatively designed a standardized discourse form, which has achieved promising results. The standardized discourse form, which adopts a structured and appropriate language format, is designed according to patient characteristics and follow-up requirements.

In developing countries, the unbalanced economic development of various regions can lead to the uneven distribution of medical resources, leaving patients without access to high-quality medical services. For patients living long distances from hospitals, inconvenient transportation makes timely outpatient follow-up very difficult. Smart healthcare systems leverage emerging technologies, such as artificial intelligence, big data, blockchain, cloud/edge computing, and the internet of things, to connect healthcare participants and promote the quality of healthcare (6-8). These systems can process large volume of data much faster and more accurately than humans (9). Cloud platforms provide flexibility, scalability, and on-demand access to resources, and have been widely used in the field of medicine and healthcare (10-13). However, research on the use of smart healthcare cloud platforms in follow-up is limited.

With the help of computer technicians, a smart healthcare cloud platform has been developed at our center. This study aimed to assess the feasibility and acceptability of the smart healthcare cloud platform based on a standardized discourse form among postoperative patients with lung cancer. We present this article in accordance with the STROBE reporting checklist (available at https://jtd.amegroups.com/article/view/10.21037/jtd-2026-1-0241/rc).

Methods

Patients

This study included patients with non-small cell lung cancer (NSCLC) who underwent video-assisted thoracoscopic surgery (VATS) at The Affiliated Hospital of Qingdao University from June 2021 to June 2022. The inclusion criteria were as follows: (I) VATS with R0 resection; and (II) a pathologic diagnosis of NSCLC. The exclusion criteria were as follows: (I) a history of serious systemic diseases (e.g., severe cardiac diseases); (II) the presence of other malignant tumors; (III) psychiatric diseases; and/or (IV) incomplete data. Ultimately, a total of 608 patients were included in the analysis, including 306 patients in the intervention group and 302 patients in the control group.

The follow-up period was set at 3, 6, 9, and 12 months post discharge, and then once every 6 months thereafter (14). Patients underwent chest computed tomography (CT) scans and serum tumor marker tests at intervals of 3–6 months. Brain magnetic resonance imaging (MRI) scans, abdominal CT scans, and bone scans were performed if the patient showed any signs or symptoms of recurrence. Positron emission tomography (PET)-CT scans or biopsies were recommended to confirm any suspected recurrence or metastasis. The follow-up end time was July 2025.

The study was conducted in accordance with the Declaration of Helsinki and its subsequent amendments. The study was approved by the institutional ethics board of The Affiliated Hospital of Qingdao University (No. QYFYKYLL 930311921) and individual consent for this retrospective analysis was waived.

Establishment of the smart healthcare cloud platform

Construction of the follow-up database

A database was used to import the following electronic medical record information of patients from the hospital information system: medical record number, name, gender, age, phone number, discharge date, home address, main diagnosis, other diagnosis, pathological diagnosis, operation, operation date, and surgeon. The system interface comprised three modules: the search module, a not followed-up patient list, and a followed-up patient list. The search module could be used to conduct searches by name, medical record number, or discharge date. The not followed-up patient list was used to remind follow-up staff to conduct follow-up by the scheduled date. After follow-up, the patient information was moved from the not followed-up patient list to the followed-up patient list, awaiting the next follow-up period. The database stored the follow-up records of each patient.

Design of a standardized discourse form

Patient follow-up primarily included quality of life (e.g., abnormal and adverse reactions), treatment status (other treatments, treatment plan, timing, and cycles), life management (diet, sleep, exercise, smoking, and drinking), re-examination (timing, items, and most recent re-examination results), and tumor recurrence or metastasis (occurrence and time of detection). Additionally, the date of follow-up and the names of the follow-up staff were recorded. Based on the follow-up content, the experience of our follow-up team, and consideration of various possible situations, our center designed a standardized discourse form (Figure 1) with attention to tone, wording, and etiquette.

Figure 1 The standardized discourse form.

Construction of a health education platform

Various informative educational videos were uploaded to the health education platform, and patients or their family members could scan QR codes to access and watch these videos as necessary. The center also supported video calls, voice calls, image-based consultations, and text chats, allowing patients to communicate with doctors or nurses in real time. At the end of the follow-up period, the patients completed a satisfaction questionnaire and the Short-Form (SF)-36 Health Survey. The follow-up staff regularly collected the submitted surveys and issued reminders to patients who had not submitted the surveys on time. A schematic diagram of the smart healthcare cloud platform is shown in Figure 2.

Figure 2 The smart healthcare cloud platform.

Follow-up methods

Intervention group

The follow-up team for the intervention group comprised permanent, experienced, full-time doctors, who received standardized training, including training on the operation of the cloud platform, use of the standardized discourse form, and key points for follow-up. Once the cloud platform was established, the system reminded patients to undergo re-examination as scheduled. The follow-up staff logged in with their employee numbers, sent the standardized discourse form to the patients, collected the forms which were completed and returned by patients, sought and recorded feedback information from the forms and patients in real time, flagged any patients who had not complied with the doctors’ advice or those with abnormal results, and provided medical advice online. If necessary, the staff contacted the patients via video or voice calls to answer questions and provide health guidance. The patients could also access the educational videos, or contact the doctors by video or voice calls, image-based consultations, or text chats. At the end of the follow-up period, the patients completed the satisfaction survey and SF-36 Health Survey.

Control group

The follow-up team for the control group comprised other permanent, experienced, full-time doctors who conducted the outpatient follow-up with the same follow-up content and schedule as the intervention group. The follow-up staff inquired about the follow-up content and recorded patient feedback in real time, flagged patients who had not complied with the doctors’ advice and those with abnormal results, provided medical advice, answered questions, and offered health guidance in person. At the end of the follow-up period, the patients completed a satisfaction survey and the SF-36 Health Survey.

Evaluating indicators

Satisfaction with follow-up

The patients completed the satisfaction survey, which included four response options: strongly satisfied, satisfied, unsatisfied, and strongly unsatisfied. The number of patients selecting each option was recorded.

Quality of life

The patients also completed the SF-36 Health Survey, which comprises eight domains: physical functioning (PF), role-physical (RP), bodily pain (BP), general health (GH), vitality (VT), social functioning (SF), role-emotional (RE), and mental health (MH). The first four domains were combined into a physical component score (PCS), and the last four into a mental component score (MCS) (15,16). With the exception of the second item, all 36 items were categorized into these eight domains. The SF-36 Health Survey scores ranged from 0 to 100, with 100 representing the best state of health and 0 representing the worst (17).

Statistical analysis

The continuous variables were described as the mean ± standard deviation, and were compared using the two-sample Student’s t-test. The Pearson Chi-squared test or Fisher’s exact test was used to compare the unordered categorical variables. The Mann-Whitney U test was used to compare the ordered categorical variables. A two-sided P<0.05 was considered statistically significant. All the statistical analyses were performed using IBM SPSS Statistics, version 25.0 (IBM Corporation, Armonk, NY, USA).

Results

Baseline characteristics

A total of 711 patients underwent VATS by the same surgical team from June 2021 to June 2022. Of these, 16 patients with other malignant tumors, three with serious systemic diseases, three with psychiatric diseases, and 15 whose pathological diagnosis was not NSCLC were excluded from the study. During the follow-up period, seven of the remaining 674 patients were excluded due to newly diagnosed malignant tumors, four due to newly diagnosed serious systemic diseases, and 55 due to incomplete data. Ultimately, a total of 608 patients were included in the analysis, including 306 patients in the intervention group and 302 patients in the control group. The patient inclusion flow diagram is shown in Figure 3. The median follow-up time of the two groups was 43 months.

Figure 3 Flow diagram showing patient inclusion. NSCLC, non-small cell lung cancer; VATS, video-assisted thoracoscopic surgery.

The baseline characteristics of all 608 patients are summarized in Table 1. In the cohort, the average age of all patients was 60.60±10.01 years. Most patients were women (55.6%, 338/608) and underwent sublobar resection (77.1%, 469/608). The most common pathological type and pathological stage were lung adenocarcinoma (92.9%, 565/608) and stage Tis + I (90.6%, 551/608), respectively. The incidence of postoperative complications in all patients was 5.8% (35/608), and the average postoperative hospital stay was 4.38±1.53 days. There were no statistically significant differences in the baseline characteristics of the patients between the two groups.

Satisfaction of patients with follow-up

The satisfaction of patients with follow-up is summarized in Table 2. After 12 months of follow-up, 74.5%, 24.2%, 1.3% and 0.0% of patients in the intervention group were “strongly satisfied”, “satisfied”, “unsatisfied”, and “strongly unsatisfied”, respectively, compared with 61.3%, 35.1%, 2.6%, and 1.0% of patients in the control group. Satisfaction with follow-up was better in the intervention group than that in the control group (P<0.001). After 36 months of follow-up, 80.1%, 19.3%, 0.6% and 0.0% of patients in the intervention group were “strongly satisfied”, “satisfied”, “unsatisfied”, and “strongly unsatisfied”, respectively, compared with 68.9%, 29.1%, 1.7%, and 0.3% of patients in the control group. Thus, satisfaction with follow-up continued to be better in the intervention group than in the control group (P=0.001).

The quality of life of patients

The scores for each domain of the SF-36 Health Survey are set out in Table 3. Before surgery, there were no statistically significant differences between the two groups in any of the domain scores, including the PCS (78.80±11.52 vs. 78.93±11.37; P=0.89), MCS (74.66±11.15 vs. 74.85±11.28; P=0.84), and average score (76.73±10.91 vs. 76.89±10.86; P=0.85). After 12 months of follow-up, the RE score of the intervention group was better than that of the control group (67.11±27.53 vs. 62.36±27.59; P=0.03). However, the intervention group had similar results to the control group across all other domain scores, including the PCS (69.85±14.25 vs. 69.30±14.74; P=0.64), MCS (65.74±14.62 vs. 64.15±14.43; P=0.18), and average score (67.79±13.99 vs. 66.73±14.07; P=0.35). After 36 months of follow-up, the intervention group had similar results to the control group across all domain scores, including the PCS (76.27±13.72 vs. 75.34±14.73; P=0.42), MCS (71.25±14.34 vs. 70.38±14.80; P=0.46), and the average (73.76±13.65 vs. 72.86±14.36; P=0.43).

Discussion

Lung cancer places an enormous physical and emotional burden on patients (18). The main purposes of patient follow-up include recurrence detection to improve survival, symptom management, identification of any new health issues, and the provision of information and psychological support (19-21). The postoperative follow-up of lung cancer patients allows doctors to assess patients’ health status after discharge, conduct comprehensive assessments, and formulate individual treatment plans. This study showed that the smart healthcare cloud platform based on a standardized discourse form achieved positive satisfaction of patients with follow-up and did not affect the quality of life of patients.

At both 12 and 36 months of follow-up, patients’ satisfaction with follow-up was better in the intervention group than that in the control group. A small number of patients in the intervention group reported issues with network latency and unfamiliarity with the platform’s operation. Conversely, some patients in the control group reported problems such as difficulty with registration, long waiting time, and other issues. Notably, no patients in the intervention group reported being “strongly unsatisfied”. Compared with the outpatient follow-up, the smart healthcare cloud platform overcame time and space limitations, allowing follow-up staff to communicate with patients and provide professional medical advice at anytime, anywhere. This was particularly convenient for the patients who lived far away or did not have enough time. The cloud platform optimized the follow-up process, eliminating waiting time and registration difficulties associated with outpatient follow-up.

Kneuertz et al. showed that a mobile device platform improved patient confidence and reduced concerns in over 80% of patients, serving as an effective tool for recording perioperative patient reported outcomes and satisfaction (22). The application of the standardized discourse form ensured that the language used was natural, fluent, and professional. Additionally, the smart healthcare cloud platform provided access to various educational videos, and also supported video calls, voice calls, image-based consultations, and text chats, broadening the channels of communication between doctors and patients, improving doctor-patient communication, and thus improving the follow-up experience and the satisfaction of patients with follow-up.

Due to its brevity and comprehensiveness, the SF-36 Health Survey is the most widely used measure of health-related quality-of-life in research to date (23). Our study showed that the scores for each domain in the intervention group were similar to those in the control group before surgery. After 12 months of follow-up, the RE score of the intervention group was better than that of the control group (67.11±27.53 vs. 62.36±27.59; P=0.03). However, the scores of the intervention group were similar to those of the control group across the other domains. These results may be attributed to a number of factors. First, the smart healthcare cloud platform overcomes time and space limitations, allowing follow-up staff to communicate with patients at anytime and anywhere. It also eliminates waiting time and registration difficulties associated with outpatient follow-up, effectively reducing patient complaints and anxiety. These advantages may be particularly significant in the first year after surgery in which follow-up frequency is higher. Second, the smart healthcare cloud platform provides access to various educational videos, and supports video calls, voice calls, image-based consultations, and text chats, allowing the follow-up staff to answer patient questions, provide medical advice and health guidance, and correct any misunderstandings and unhealthy habits of the patients in a timely manner, thus improving the follow-up experience of patients, and enhancing their confidence.

Li et al. indicated that the psychological trajectories of surgical lung cancer patients were important in maintaining their quality of life (24). After 36 months of follow-up, the intervention group showed similar scores to the control group across all domains, and all the domain scores were higher than those recorded at 12 months of follow-up. Thus, as time went on, their quality of life improved to a certain extent. Sui et al. showed that a WeChat application-based education and rehabilitation program relieved anxiety and depression, and improved the quality of life of NSCLC patients who had undergone surgical resection (25).

The smart healthcare cloud platform included a comprehensive follow-up database that recorded the details of each patient follow-up visit, and used a standardized discourse form to ensure accurate and efficient follow-up. It assisted doctors to obtain complete patient information, and to track and monitor disease progression, which can also support clinical studies such as prognosis management. Recent evidence suggests that globally, intensive follow-up does not improve survival in all patients. In this regard, the systematic review by Stirling et al. (26) shows that although scheduled follow-up increases recurrence detection rates, there is no robust evidence of a universal survival benefit. Complementarily, recent multicenter studies have indicated that follow-up frequency does not have a homogeneous impact on oncologic outcomes and that benefits may concentrate in higher-risk subgroups (27). In this context, the value of the digital platforms may lie in facilitating personalized follow-up through risk stratification, adaptive follow-up protocols, and longitudinal symptom monitoring, rather than indiscriminately intensifying surveillance.

During the study period, the cloud platform operated without interruption. The patients were able to scan QR codes to access and use the cloud platform as necessary at any time. To address issues reported by the patients in the intervention group, the follow-up staff provided one-on-one guidance to familiarize them with the cloud platform, and computer technicians maintained the stability of the network. The cloud platform achieved promising results, but some issues remained. For example, the management burden increased due to incorrect entries on the cloud platform by patients without lung cancer. The login interface of the platform may need to be improved and patient information may need to be strictly reviewed to prevent such errors. When establishing the cloud platform, we contacted computer technicians to solve technical problems, and the platform was constantly tested and improved to ensure the normal operation. We organized standardized training for follow-up staff and guided patients to familiarize with the cloud platform. Of course, the establishment of the cloud platform was also inseparable from the support of money. As the number of patients using the cloud platform continues to increase, system maintenance could become a challenge. This may require additional computer technician support, more follow-up staff, and adequate funding.

There are some limitations in this study. First, as a retrospective single-center study, it is subject to a certain degree of bias. Multicenter prospective randomized controlled trials need to be conducted to validate the findings. Second, this study only included postoperative patients with lung cancer. It is unclear whether the smart healthcare cloud platform would be suitable for patients with other diseases. Third, this study only reported 3-year follow-up results. Longer-term follow-up results, such as 5-year and 10-year follow-up results, are needed for further evaluation.

Conclusions

The smart healthcare cloud platform based on a standardized discourse form can achieve positive satisfaction of patients with follow-up and does not affect the quality of life of patients. Thus, its application is feasible and acceptable in the postoperative follow-up of patients with NSCLC.

Acknowledgments

None.

Footnote

Reporting Checklist: The authors have completed the STROBE reporting checklist. Available at https://jtd.amegroups.com/article/view/10.21037/jtd-2026-1-0241/rc

Data Sharing Statement: Available at https://jtd.amegroups.com/article/view/10.21037/jtd-2026-1-0241/dss

Peer Review File: Available at https://jtd.amegroups.com/article/view/10.21037/jtd-2026-1-0241/prf

Funding: None.

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://jtd.amegroups.com/article/view/10.21037/jtd-2026-1-0241/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. The study was approved by the institutional ethics board of The Affiliated Hospital of Qingdao University (No. QYFYKYLL 930311921) and individual consent for this retrospective analysis was waived.

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. Sung H, Ferlay J, Siegel RL, et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin 2021;71:209-49. [Crossref] [PubMed]
2. Allemani C, Matsuda T, Di Carlo V, et al. Global surveillance of trends in cancer survival 2000-14 (CONCORD-3): analysis of individual records for 37 513 025 patients diagnosed with one of 18 cancers from 322 population-based registries in 71 countries. Lancet 2018;391:1023-75. [Crossref] [PubMed]
3. Zhao ZR, Situ DR, Lau RWH, et al. Comparison of Segmentectomy and Lobectomy in Stage IA Adenocarcinomas. J Thorac Oncol 2017;12:890-6. [Crossref] [PubMed]
4. Suzuki K, Saji H, Aokage K, et al. Comparison of pulmonary segmentectomy and lobectomy: Safety results of a randomized trial. J Thorac Cardiovasc Surg 2019;158:895-907. [Crossref] [PubMed]
5. Itasaka H, Matsumata T, Taketomi A, et al. Outpatient follow-up system using a personal computer for patients with hepatocellular carcinoma after surgery. J Med Syst 1994;18:329-33. [Crossref] [PubMed]
6. Zhou B, Yang G, Shi Z, et al. Natural Language Processing for Smart Healthcare. IEEE Rev Biomed Eng 2024;17:4-18. [Crossref] [PubMed]
7. Rani S, Kumar R, Panda BS, et al. Machine Learning-Powered Smart Healthcare Systems in the Era of Big Data: Applications, Diagnostic Insights, Challenges, and Ethical Implications. Diagnostics (Basel) 2025;15:1914. [Crossref] [PubMed]
8. Sivakumar TB, Hasan Hussain SH, Balamanigandan R. Internet of Things and Cloud Computing-based Disease Diagnosis using Optimized Improved Generative Adversarial Network in Smart Healthcare System. Network 2025;36:1752-75. [Crossref] [PubMed]
9. Sangaiah AK, Arumugam M, Bian GB. An intelligent learning approach for improving ECG signal classification and arrhythmia analysis. Artif Intell Med 2020;103:101788. [Crossref] [PubMed]
10. Zhu H, Liang X, Pan XF, et al. A prospective cohort study of home blood pressure monitoring based on an intelligent cloud platform (the HBPM-iCloud study): rationale and design. Ther Adv Chronic Dis 2020;11:2040622320933108. [Crossref] [PubMed]
11. Wang YE, Kutnetsov L, Partensky A, et al. WebMeV: A Cloud Platform for Analyzing and Visualizing Cancer Genomic Data. Cancer Res 2017;77:e11-4. [Crossref] [PubMed]
12. Saratto T, Visuri K, Lehtinen J, et al. Solu: a cloud platform for real-time genomic pathogen surveillance. BMC Bioinformatics 2025;26:12. [Crossref] [PubMed]
13. Peng W, Hong Y, Chen Y, et al. AIScholar: An OpenFaaS-enhanced cloud platform for intelligent medical data analytics. Comput Biol Med 2025;186:109648. [Crossref] [PubMed]
14. Watanabe K, Tsuboi M, Sakamaki K, et al. Postoperative follow-up strategy based on recurrence dynamics for non-small-cell lung cancer. Eur J Cardiothorac Surg 2016;49:1624-31. [Crossref] [PubMed]
15. Mörck B, Pullerits R, Geijer M, et al. Infliximab dose reduction sustains the clinical treatment effect in active HLAB27 positive ankylosing spondylitis: a two-year pilot study. Mediators Inflamm 2013;2013:289845. [Crossref] [PubMed]
16. Mishra GD, Gale CR, Sayer AA, et al. How useful are the SF-36 sub-scales in older people? Mokken scaling of data from the HALCyon programme. Qual Life Res 2011;20:1005-10. [Crossref] [PubMed]
17. Wang L, Shi H, Zhu Y, et al. Blood donation and health status based on SF-36: The mediating effect of cognition in blood donation. PLoS One 2019;14:e0223657. [Crossref] [PubMed]
18. Hirsch JK, Floyd AR, Duberstein PR. Perceived health in lung cancer patients: the role of positive and negative affect. Qual Life Res 2012;21:187-94. [Crossref] [PubMed]
19. Shargall Y, Vella ET, Del Giudice ME, et al. Systematic Review for the Follow-up of Curatively Treated Patients With Lung Cancer. Clin Lung Cancer 2025;26:e327-41. [Crossref] [PubMed]
20. Smith TJ. Evidence-based follow-up of lung cancer patients. Semin Oncol 2003;30:361-8. [Crossref] [PubMed]
21. Beaver K, Luker KA. Follow-up in breast cancer clinics: reassuring for patients rather than detecting recurrence. Psychooncology 2005;14:94-101. [Crossref] [PubMed]
22. Kneuertz PJ, Jagadesh N, Perkins A, et al. Improving patient engagement, adherence, and satisfaction in lung cancer surgery with implementation of a mobile device platform for patient reported outcomes. J Thorac Dis 2020;12:6883-91. [Crossref] [PubMed]
23. Laucis NC, Hays RD, Bhattacharyya T. Scoring the SF-36 in Orthopaedics: A Brief Guide. J Bone Joint Surg Am 2015;97:1628-34. [Crossref] [PubMed]
24. Li J, Yin C, Ye M, et al. Psychological Distress in Surgical Lung Cancer Patients: Trajectories, Influencing Factors and Impacts on Quality of Life. J Clin Nurs 2026;35:289-304. [Crossref] [PubMed]
25. Sui Y, Wang T, Wang X. The impact of WeChat app-based education and rehabilitation program on anxiety, depression, quality of life, loss of follow-up and survival in non-small cell lung cancer patients who underwent surgical resection. Eur J Oncol Nurs 2020;45:101707. [Crossref] [PubMed]
26. Stirling RG, Chau C, Shareh A, et al. Effect of Follow-Up Surveillance After Curative-Intent Treatment of NSCLC on Detection of New and Recurrent Disease, Retreatment, and Survival: A Systematic Review and Meta-Analysis. J Thorac Oncol 2021;16:784-97. [Crossref] [PubMed]
27. Fuentes-Martín Á, Martínez-Hernández NJ, Cabañero Sánchez A, et al. Impact of radiological follow-up frequency on resected lung cancer: a propensity score matching analysis. J Thorac Dis 2024;16:4275-85. [Crossref] [PubMed]

(English Language Editor: L. Huleatt)