Abstract: Real-world studies (RWSs) have emerged as a transformative force in oncology research, complementing traditional randomized controlled trials (RCTs) by providing comprehensive insights into cancer care within routine clinical settings. This review examines the evolving landscape of RWSs in oncology, focusing on their implementation, methodological considerations, and impact on precision medicine. We systematically analyze how RWSs leverage diverse data sources, including electronic health records (EHRs), insurance claims, and patient registries, to generate evidence that bridges the gap between controlled clinical trials and real-world clinical practice. The review underscores the key contributions of RWSs, including capturing therapeutic outcomes in traditionally underrepresented populations, expanding drug indications, and evaluating long-term safety and effectiveness in routine clinical settings. While acknowledging significant challenges, including data quality variability and privacy concerns, we discuss how emerging technologies like artificial intelligence are helping to address these limitations. The integration of RWSs with traditional clinical research is revolutionizing the paradigm of precision oncology and enabling more personalized treatment approaches based on real-world evidence.

真实世界数据与证据：精准肿瘤学的革新领域

[1]AgiroA, DeVriesA, MalinJ, et al., 2018. Real-world impact of a decision support tool on colony-stimulating factor use and chemotherapy-induced febrile neutropenia among patients with breast cancer. J Natl Compr Canc Netw, 16(2):162-169.

[2]AnwarM, ChenQT, OuyangDJ, et al., 2021. Pyrotinib treatment in patients with HER2-positive metastatic breast cancer and brain metastasis: exploratory final analysis of real-world, multicenter data. Clin Cancer Res, 27(16):4634-4641.

[3]ArlettP, KjærJ, BroichK, et al., 2022. Real-world evidence in EU medicines regulation: enabling use and establishing value. Clin Pharmacol Ther, 111(1):21-23.

[4]ArondekarB, DuhMS, BhakRH, et al., 2022. Real-world evidence in support of oncology product registration: a systematic review of new drug application and biologics license application approvals from 2015-2020. Clin Cancer Res, 28(1):27-35.

[5]BankheadP, LoughreyMB, FernándezJA, et al., 2017. QuPath: open source software for digital pathology image analysis. Sci Rep, 7:16878.

[6]BasulaimanB, AwanAA, FergussonD, et al., 2019. Creating a pragmatic trials program for breast cancer patients: rethinking clinical trials (REaCT). Breast Cancer Res Treat, 177(1):93-101.

[7]Baumfeld AndreE, ReynoldsR, CaubelP, et al., 2020. Trial designs using real-world data: the changing landscape of the regulatory approval process. Pharmacoepidemiol Drug Saf, 29(10):1201-1212.

[8]BergerM, DanielG, FrankK, et al., 2017. A Framework for Regulatory Use of Real-World Evidence. Duke Margolis Center for Health Policy, Washington, DC, USA.

[9]BlackN, 1996. Why we need observational studies to evaluate the effectiveness of health care. BMJ, 312(7040):1215-1218.

[10]BoothCM, KarimS, MackillopWJ, 2019. Real-world data: towards achieving the achievable in cancer care. Nat Rev Clin Oncol, 16(5):312-325.

[11]ChakiryanNH, JiangDD, GillisKA, et al., 2021. Real-world survival outcomes associated with first-line immunotherapy, targeted therapy, and combination therapy for metastatic clear cell renal cell carcinoma. JAMA Netw Open, 4(5):e2111329.

[12]ChenXX, WangXM, ZhangK, et al., 2022. Recent advances and clinical applications of deep learning in medical image analysis. Med Image Anal, 79:102444.

[13]ChlebowskiRT, HendrixSL, LangerRD, et al., 2003. Influence of estrogen plus progestin on breast cancer and mammography in healthy postmenopausal women: the women’s health initiative randomized trial. JAMA, 289(24):3243-3253.

[14]CluzeC, ReyD, HuiartL, et al., 2012. Adjuvant endocrine therapy with tamoxifen in young women with breast cancer: determinants of interruptions vary over time. Ann Oncol, 23(4):882-890.

[15]Collaborative Group on Hormonal Factors in Breast Cancer, 1997. Breast cancer and hormone replacement therapy: collaborative reanalysis of data from 51 epidemiological studies of 52 705 women with breast cancer and 108 411 women without breast cancer. Lancet, 350(9084):1047-1059.

[16]CollinsR, BowmanL, LandrayM, et al., 2020. The magic of randomization versus the myth of real-world evidence. N Engl J Med, 382(7):674-678.

[17]CookJA, CollinsGS, 2015. The rise of big clinical databases. Br J Surg, 102(2):e93-e101.

[18]Corrigan-CurayJ, 2018. Framework for FDA’s Real-World Evidence Program. U.S. Food and Drug Administration, Silver Spring. https://www.fda.gov/media/123160/download[accessed on Nov. 25, 2024].

[19]DaiWF, BecaJM, NagamuthuC, et al., 2022a. Comparative effectiveness and safety of pertuzumab and trastuzumab plus chemotherapy vs trastuzumab plus chemotherapy for treatment of metastatic breast cancer. JAMA Netw Open, 5(2):e2145460.

[20]DaiWF, BecaJM, NagamuthuC, et al., 2022b. Cost-effectiveness analysis of pertuzumab with trastuzumab in patients with metastatic breast cancer. JAMA Oncol, 8(4):597-606.

[21]DerksenJWG, MayAM, KoopmanM, 2019. The era of alternative designs to connect randomized clinical trials and real-world data. Nat Rev Clin Oncol, 16(9):589.

[22]DiérasV, MilesD, VermaS, et al., 2017. Trastuzumab emtansine versus capecitabine plus lapatinib in patients with previously treated HER2-positive advanced breast cancer (EMILIA): a descriptive analysis of final overall survival results from a randomised, open-label, phase 3 trial. Lancet Oncol, 18(6):732-742.

[23]DinanMA, WilsonLE, ReedSD, 2019. Chemotherapy costs and 21-gene recurrence score genomic testing among medicare beneficiaries with early-stage breast cancer, 2005 to 2011. J Natl Compr Canc Netw, 17(3):245-254.

[24]DuggentoA, ContiA, MaurielloA, et al., 2021. Deep computational pathology in breast cancer. Semin Cancer Biol, 72:226-237.

[25]EggermontAMM, ApoloneG, BaumannM, et al., 2019. Cancer Core Europe: a translational research infrastructure for a European mission on cancer. Mol Oncol, 13(3):521-527.

[26]EthierJL, DesautelsD, RobinsonA, et al., 2021. Practice patterns and outcomes of novel targeted agents for the treatment of ERBB2-positive metastatic breast cancer. JAMA Oncol, 7(9):e212140.

[27]FarkasAH, NattingerAB, 2023. Breast cancer screening and prevention. Ann Intern Med, 176(11):ITC161-ITC176.

[28]FlynnR, PlueschkeK, QuintenC, et al., 2022. Marketing authorization applications made to the European medicines agency in 2018‒2019: what was the contribution of real-world evidence? Clin Pharmacol Ther, 111(1):90-97.

[29]FranklinJM, SchneeweissS, 2017. When and how can real world data analyses substitute for randomized controlled trials? Clin Pharmacol Ther, 102(6):924-933.

[30]GennaroG, BucchiL, RavaioliA, et al., 2024. The risk-based breast screening (RIBBS) study protocol: a personalized screening model for young women. Radiol Med, 129(5):727-736.

[31]Global Burden of Disease Cancer Collaboration, 2019. Global, regional, and national cancer incidence, mortality, years of life lost, years lived with disability, and disability-adjusted life-years for 29 cancer groups, 1990 to 2017: a systematic analysis for the global burden of disease study. JAMA Oncol, 5(12):1749-1768.

[32]Global Burden of Disease 2019 Cancer Collaboration, 2022. Cancer incidence, mortality, years of life lost, years lived with disability, and disability-adjusted life years for 29 cancer groups from 2010 to 2019: a systematic analysis for the global burden of disease study 2019. JAMA Oncol, 8(3):420-444.

[33]GrossAJ, PisanoCE, KhunsriraksakulC, et al., 2023. Real-world data: applications and relevance to cancer clinical trials. Semin Radiat Oncol, 33(4):374-385.

[34]HripcsakG, DukeJD, ShahNH, et al., 2015. Observational health data sciences and informatics (OHDSI): opportunities for observational researchers. Stud Health Technol Inform, 216:574-578.

[35]HsuWH, KoAT, WengCS, et al., 2023. Explainable machine learning model for predicting skeletal muscle loss during surgery and adjuvant chemotherapy in ovarian cancer. J Cachexia Sarcopenia Muscle, 14(5):2044-2053.

[36]JarowJP, LaVangeL, WoodcockJ, 2017. Multidimensional evidence generation and FDA regulatory decision making: defining and using “real-world” data. JAMA, 318(8):703-704.

[37]JaziehAR, OnalHC, TanDSW, et al., 2021. Real-world treatment patterns and clinical outcomes in patients with stage III NSCLC: results of KINDLE, a multicountry observational study. J Thorac Oncol, 16(10):1733-1744.

[38]JiangXY, HuZJ, WangSH, et al., 2023. Deep learning for medical image-based cancer diagnosis. Cancers, 15(14):3608.

[39]KantarjianH, SteinA, GökbugetN, et al., 2017. Blinatumomab versus chemotherapy for advanced acute lymphoblastic leukemia. N Engl J Med, 376(9):836-847.

[40]KarakatsanisA, MarkopoulosC, 2020. The challenge of avoiding over- and under-treatment in older women with ductal cancer in situ: a scoping review of existing knowledge gaps and a meta-analysis of real-world practice patterns. J Geriatr Oncol, 11(6):917-925.

[41]Kennedy-MartinT, CurtisS, FariesD, et al., 2015. A literature review on the representativeness of randomized controlled trial samples and implications for the external validity of trial results. Trials, 16:495.

[42]KhozinS, BlumenthalGM, PazdurR, 2017. Real-world data for clinical evidence generation in oncology. J Natl Cancer Inst, 109(11):djx187.

[43]KimHS, 2024. Dark data in real-world evidence: challenges, implications, and the imperative of data literacy in medical research. J Korean Med Sci, 39(9):e92.

[44]KirkhamAA, BlandKA, WollmannH, et al., 2019. Maintenance of fitness and quality-of-life benefits from supervised exercise offered as supportive care for breast cancer. J Natl Compr Canc Netw, 17(6):695-702.

[45]KleppeA, SkredeOJ, de RaedtS, et al., 2021. Designing deep learning studies in cancer diagnostics. Nat Rev Cancer, 21(3):199-211.

[46]KovačevićA, BašaraginB, MiloševićN, et al., 2024. De-identification of clinical free text using natural language processing: a systematic review of current approaches. Artif Intell Med, 151:102845.

[47]LiXC, ZhangS, ZhangQ, et al., 2019. Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study. Lancet Oncol, 20(2):193-201.

[48]LiaoWQ, CouplandCAC, BurchardtJ, et al., 2023. Predicting the future risk of lung cancer: development, and internal and external validation of the CanPredict (lung) model in 19.67 million people and evaluation of model performance against seven other risk prediction models. Lancet Respir Med, 11(8):685-697.

[49]LinAP, HuangTW, TamKW, 2021. Treatment of male breast cancer: meta-analysis of real-world evidence. Br J Surg, 108(9):1034-1042.

[50]LuYT, ChuQ, LiZ, et al., 2024. Deep reinforcement learning identifies personalized intermittent androgen deprivation therapy for prostate cancer. Brief Bioinform, 25(2):bbae071.

[51]LuZH, SimJA, WangJX, et al., 2021. Natural language processing and machine learning methods to characterize unstructured patient-reported outcomes: validation study. J Med Internet Res, 23(11):e26777.

[52]MalmbergR, ZietseM, DumoulinDW, et al., 2022. Alternative dosing strategies for immune checkpoint inhibitors to improve cost-effectiveness: a special focus on nivolumab and pembrolizumab. Lancet Oncol, 23(12):e552-e561.

[53]MaloneDC, BrownM, HurwitzJT, et al., 2018. Real-world evidence: useful in the real world of us payer decision making? How? When? And What studies? Value Health, 21(3):326-333.

[54]MartinP, CohenJB, WangM, et al., 2023. Treatment outcomes and roles of transplantation and maintenance rituximab in patients with previously untreated mantle cell lymphoma: results from large real-world cohorts. J Clin Oncol, 41(3):541-554.

[55]McCarneyR, WarnerJ, IliffeS, et al., 2007. The Hawthorne effect: a randomised, controlled trial. BMC Med Res Methodol, 7:30.

[56]MerolaD, CampbellU, GautamN, et al., 2023. The aetion coalition to advance real-world evidence through randomized controlled trial emulation initiative: oncology. Clin Pharmacol Ther, 113(6):1217-1222.

[57]MiksadRA, AbernethyAP, 2018. Harnessing the power of real-world evidence (RWE): a checklist to ensure regulatory-grade data quality. Clin Pharmacol Ther, 103(2):202-205.

[58]MooreS, LeungB, WuJ, et al., 2019. Real-world treatment of stage III NSCLC: the role of trimodality treatment in the era of immunotherapy. J Thorac Oncol, 14(8):1430-1439.

[59]NewmanLA, 2022. Breast cancer screening in low and middle-income countries. Best Pract Res Clin Obstet Gynaecol, 83:15-23.

[60]NúñezER, CaverlyTJ, ZhangSQ, et al., 2021. Adherence to follow-up testing recommendations in US veterans screened for lung cancer, 2015-2019. JAMA Netw Open, 4(7):e2116233.

[61]PatilVM, NoronhaV, MenonN, et al., 2023. Low-dose immunotherapy in head and neck cancer: a randomized study. J Clin Oncol, 41(2):222-232.

[62]PenberthyLT, RiveraDR, LundJL, et al., 2022. An overview of real-world data sources for oncology and considerations for research. CA Cancer J Clin, 72(3):287-300.

[63]Perez-LopezR, Ghaffari LalehN, MahmoodF, et al., 2024. A guide to artificial intelligence for cancer researchers. Nat Rev Cancer, 24(6):427-441.

[64]PoirionOB, JingZ, ChaudharyK, et al., 2021. DeepProg: an ensemble of deep-learning and machine-learning models for prognosis prediction using multi-omics data. Genome Med, 13:112.

[65]PollardS, WeymannD, ChanB, et al., 2022. Defining a core data set for the economic evaluation of precision oncology. Value Health, 25(8):1371-1380.

[66]PrelajA, MiskovicV, ZanittiM, et al., 2024. Artificial intelligence for predictive biomarker discovery in immuno-oncology: a systematic review. Ann Oncol, 35(1):29-65.

[67]PrzepiorkaD, KoCW, DeisserothA, et al., 2015. FDA approval: blinatumomab. Clin Cancer Res, 21(18):4035-4039.

[68]QaiserT, RajpootNM, 2019. Learning where to see: a novel attention model for automated immunohistochemical scoring. IEEE Trans Med Imaging, 38(11):2620-2631.

[69]RoshandelG, BadarF, BarchukA, et al., 2023. REPCAN: guideline for REporting population-based CANcer registry data. Asian Pac J Cancer Prev, 24(9):3297-3303.

[70]SamlowskiW, RobertNJ, ChenLW, et al., 2023. Real-world nivolumab dosing patterns and safety outcomes in patients receiving adjuvant therapy for melanoma. Cancer Med, 12(3):2378-2388.

[71]ShermanRE, AndersonSA, Dal PanGJ, et al., 2016. Real-world evidence — what is it and what can it tell us? N Engl J Med, 375(23):2293-2297.

[72]SimJA, HuangXL, HoranMR, et al., 2023. Natural language processing with machine learning methods to analyze unstructured patient-reported outcomes derived from electronic health records: a systematic review. Artif Intell Med, 146:102701.

[73]SinhaS, LaskarSG, WadasadawalaT, et al., 2022. Adopting health economic research in radiation oncology: a perspective from low- or middle-income countries. JCO Glob Oncol, 8:e2100374.

[74]SkovlundE, LeufkensHGM, SmythJF, 2018. The use of real-world data in cancer drug development. Eur J Cancer, 101:69-76.

[75]SolimanR, OkeJ, SidhomI, et al., 2023. Cost-effectiveness of childhood cancer treatment in Egypt: lessons to promote high-value care in a resource-limited setting based on real-world evidence. eClinicalMedicine, 55:101729.

[76]StabelliniN, CaoLF, ToweCW, et al., 2023. Validation of the PREDICT prognostication tool in US patients with breast cancer. J Natl Compr Canc Netw, 21(10):1011-1019.e6.

[77]Stein-O'BrienGL, LeDT, JaffeeEM, et al., 2023. Converging on a cure: the roads to predictive immunotherapy. Cancer Discov, 13(5):1053-1057.

[78]TangM, PearsonSA, SimesRJ, et al., 2023. Harnessing real-world evidence to advance cancer research. Curr Oncol, 30(2):1844-1859.

[79]TerranovaN, VenkatakrishnanK, 2024. Machine learning in modeling disease trajectory and treatment outcomes: an emerging enabler for model-informed precision medicine. Clin Pharmacol Ther, 115(4):720-726.

[80]TimminsIR, JonesME, O'BrienKM, et al., 2024. International pooled analysis of leisure-time physical activity and premenopausal breast cancer in women from 19 cohorts. J Clin Oncol, 42(8):927-939.

[81]ToppMS, GökbugetN, SteinAS, et al., 2015. Safety and activity of blinatumomab for adult patients with relapsed or refractory B-precursor acute lymphoblastic leukaemia: a multicentre, single-arm, phase 2 study. Lancet Oncol, 16(1):57-66.

[82]TortoraM, CordelliE, SiciliaR, et al., 2021. Deep reinforcement learning for fractionated radiotherapy in non-small cell lung carcinoma. Artif Intell Med, 119:102137.

[83]Trentham-DietzA, ChapmanCH, JayasekeraJ, et al., 2024. Collaborative modeling to compare different breast cancer screening strategies: a decision analysis for the US preventive services task force. JAMA, 331(22):1947-1960.

[84]TsaiCJ, RiazN, GomezSL, 2019. Big data in cancer research: real-world resources for precision oncology to improve cancer care delivery. Semin Radiat Oncol, 29(4):306-310.

[85]U.S. Food and Drug Administration, 2023. Using the PICOTS Framework to Strengthen Evidence Gathered in Clinical Trials—Guidance from the AHRQ’s Evidence-based Practice Centers Program. U.S. Food and Drug Administration, Silver Spring. https://www.fda.gov/media/109448/download[accessed on Nov. 25, 2024].

[86]van den PuttelaarR, MeesterRGS, PeterseEFP, et al., 2023. Risk-stratified screening for colorectal cancer using genetic and environmental risk factors: a cost-effectiveness analysis based on real-world data. Clin Gastroenterol Hepatol, 21(13):3415-3423.e29.

[87]VeitchZ, KhanOF, TilleyD, et al., 2019. Real-world outcomes of adjuvant chemotherapy for node-negative and node-positive HER2-positive breast cancer. J Natl Compr Canc Netw, 17(1):47-56.

[88]VelmovitskyPE, BevilacquaT, AlencarP, et al., 2021. Convergence of precision medicine and public health into precision public health: toward a big data perspective. Front Public Health, 9:561873.

[89]VerkerkK, VoestEE, 2024. Generating and using real-world data: a worthwhile uphill battle. Cell, 187(7):1636-1650.

[90]VoelkerRA, 2023. Cervical cancer screening. JAMA, 330(20):2030.

[91]VorisekCN, LehneM, KlopfensteinSAI, et al., 2022. Fast healthcare interoperability resources (FHIR) for interoperability in health research: systematic review. JMIR Med Inform, 10(7):e35724.

[92]WangSV, PinheiroS, HuaW, et al., 2021. STaRT-RWE: structured template for planning and reporting on the implementation of real world evidence studies. BMJ, 372:m4856.

[93]WangX, FengKX, WangWY, et al., 2022. Long-term outcomes of intraoperative radiotherapy for early-stage breast cancer in China: a multicenter real-world study. Cancer Commun, 42(3):277-280.

[94]WangYS, 2024. 123P Goserelin 10.8 mg and 3.6 mg depots in breast cancer (BC): a large real-world noninferiority study. ESMO Open, 9(S4):103111.

[95]WedamS, Fashoyin-AjeL, BloomquistE, et al., 2020. FDA approval summary: palbociclib for male patients with metastatic breast cancer. Clin Cancer Res, 26(6):1208-1212.

[96]WuSY, LiJW, WangYJ, et al., 2023. Clinical feasibility and oncological safety of non-radioactive targeted axillary dissection after neoadjuvant chemotherapy in biopsy-proven node-positive breast cancer: a prospective diagnostic and prognostic study. Int J Surg, 109(7):1863-1870.

[97]XuC, SongYH, ZhangD, et al., 2023. Spatiotemporal knowledge teacher-student reinforcement learning to detect liver tumors without contrast agents. Med Image Anal, 90:102980.

[98]XuJY, WuWK, ZhangX, et al., 2024. The use of real-world evidence for regulatory decisions in China. Clin Pharmacol Ther, 116(1):82-95.

[99]YalaA, MikhaelPG, LehmanC, et al., 2022. Optimizing risk-based breast cancer screening policies with reinforcement learning. Nat Med, 28(1):136-143.

[100]YanYT, LvR, WangTY, et al., 2023. Real-world treatment patterns, discontinuation and clinical outcomes in patients with B-cell lymphoproliferative diseases treated with BTK inhibitors in China. Front Immunol, 14:1184395.

[101]YimWW, YetisgenM, HarrisWP, et al., 2016. Natural language processing in oncology: a review. JAMA Oncol, 2(6):797-804.

[102]ZhangJD, WuJJ, ZhouXS, et al., 2023. Recent advancements in artificial intelligence for breast cancer: image augmentation, segmentation, diagnosis, and prognosis approaches. Semin Cancer Biol, 96:11-25.

[103]ZhaoYF, KosorokMR, ZengDL, 2009. Reinforcement learning design for cancer clinical trials. Stat Med, 28(26):3294-3315.

[104]ZhuR, VoraB, MenonS, et al., 2023. Clinical pharmacology applications of real-world data and real-world evidence in drug development and approval‒an industry perspective. Clin Pharmacol Ther, 114(4):751-767.