ESMO Real World Data and Digital Oncology最新文献

{"title":"Editoiral Board","authors":"","doi":"10.1016/S2949-8201(24)00028-6","DOIUrl":"https://doi.org/10.1016/S2949-8201(24)00028-6","url":null,"abstract":"","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"4 ","pages":"Article 100050"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949820124000286/pdfft?md5=deacee789f443432060faf4b386a7c88&pid=1-s2.0-S2949820124000286-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141314611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-world evidence reported for clinical efficacy evaluation in European Public Assessment Reports of authorised targeted therapies for solid malignancies: a comprehensive review (2018-2022)","authors":"J.W.G. Derksen ,&nbsp;D. Martins-Branco ,&nbsp;A. Valachis ,&nbsp;A. Pellat ,&nbsp;S.C.M.W. van Nassau ,&nbsp;A. Aggarwal ,&nbsp;G. Pentheroudakis ,&nbsp;M. Koopman ,&nbsp;L. Castelo-Branco ,&nbsp;S. Delaloge","doi":"10.1016/j.esmorw.2024.100039","DOIUrl":"https://doi.org/10.1016/j.esmorw.2024.100039","url":null,"abstract":"<div><h3>Background</h3><p>The role of real-world evidence (RWE) for clinical efficacy regulatory evaluation remains unclear. We aimed to assess and describe the reported use of RWE for clinical efficacy evaluation of authorised targeted therapies for treatment of solid malignancies in Europe.</p></div><div><h3>Design</h3><p>We studied all authorised indications of targeted therapies for the treatment of solid malignancies granted by the European Medicines Agency between 2018 and 2022. Data were retrieved in March 2023 from European Public Assessment Reports (EPARs). We evaluated the frequency of RWE use for clinical efficacy evaluation and its role based on the reported information in the EPAR, and assessed characteristics and risk of bias of published studies.</p></div><div><h3>Results</h3><p>Out of 75 authorised indications identified, most related to the treatment of patients with lung (21.3%) or breast (20.0%) cacer, and to advanced settings (89.3%). The use of RWE for clinical efficacy evaluation was reported in the EPAR of 16 (21.3%) indications, tending to increase overtime (15.0%-35.7% in 2018-2022). RWE was more frequently considered in lung (37.5%) and breast (33.3%) cancer indications, for antibody–drug conjugates (60.0%), and conditional approvals (46.7%). We classified RWE’s role as ‘supportive’ confirmatory evidence in 12 of 16 (75.0%) indications. RWE studies were mostly analytical (57.1%), non-international (92.9%), retrospective cohort studies (57.1%), and originated from the United States (78.6%). High or serious risk of bias was identified in different domains of most studies assessed.</p></div><div><h3>Conclusions</h3><p>RWE was reported to be used for clinical efficacy regulatory evaluation in 21% of targeted therapy indications for solid malignancies, with an increasing trend over time.</p></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"4 ","pages":"Article 100039"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949820124000171/pdfft?md5=e2d055fe563356f81b53f550f914089d&pid=1-s2.0-S2949820124000171-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141244452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The 1 million words pathology report or the challenge of a reproducible and meaningful message","authors":"C. Eloy ,&nbsp;P. Seegers ,&nbsp;E. Bazyleva ,&nbsp;F. Fraggetta","doi":"10.1016/j.esmorw.2024.100044","DOIUrl":"https://doi.org/10.1016/j.esmorw.2024.100044","url":null,"abstract":"<div><p>Many years have passed since the pathology report was all about a single-sentence diagnosis based on morphology. The pathology report is an invaluable source of data that needs to evolve from a narrative reporting to a synoptic reporting system by standardizing data elements to ensure consistency and structured formats that improve completeness, interoperability, and scalability across different health care systems. The convergence of technology, structured data, and artificial intelligence propels the field of pathology toward a future where the synthesis of information benefits not only health care professionals and patients but also serves as a wellspring of knowledge for machines, paving the way for unprecedented strides in data mining and health care innovation.</p></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"4 ","pages":"Article 100044"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949820124000225/pdfft?md5=c7de555e84bdf779e371603b14d2d6f7&pid=1-s2.0-S2949820124000225-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141244426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Utilization and safety of trastuzumab emtansine (T-DM1): a nationwide population-based study using the French National Health Data System","authors":"H. Jourdain ,&nbsp;I. Mansouri ,&nbsp;A. Di Meglio ,&nbsp;M. Zureik ,&nbsp;N. Haddy","doi":"10.1016/j.esmorw.2024.100045","DOIUrl":"https://doi.org/10.1016/j.esmorw.2024.100045","url":null,"abstract":"<div><h3>Background</h3><p>Trastuzumab emtansine (T-DM1), the first antibody–drug conjugate targeting human epidermal growth factor receptor 2 (HER2), has provided new alternatives for metastatic breast cancer (mBC) treatment, and for early-stage breast cancer (esBC) since 2020. We characterized T-DM1 users and assessed the risk of hospitalisation for certain adverse events.</p></div><div><h3>Materials and methods</h3><p>Using data from the French National Health Data System (SNDS), we identified patients receiving T-DM1 from 2014 to 2022. Sociodemographic data, medical history, and overall survival were described by indication. The risk of adverse event-related hospitalisation was quantified.</p></div><div><h3>Results</h3><p>We included 12 822 patients initiating T-DM1 treatment in the study: 9232 (72%) with mBC (median age: 59 years, 54.6% with at least one comorbid condition) and 3590 (28%) with esBC (median age: 54 years, 33.9% with at least one comorbid condition). In mBC, median overall survival was 32.6 months, showing a gradual improvement over the years. At 1 year, 75.8% of patients had discontinued treatment and 22.0% had died. Patients in the study faced higher hospitalisation risks than those with incident breast cancer, with increases of 5.7 and 10.5 times for thrombocytopenia, 3.0 and 4.5 times for interstitial lung disease, 3.3 and 5.9 times for acute liver injury, and 2.3 and 7.3 times for sepsis, for esBC and mBC, respectively.</p></div><div><h3>Conclusions</h3><p>Real-world T-DM1 users frequently present with comorbid conditions and prior treatments, with a higher risk of hospitalisation for severe toxicity events than the general population of incident breast cancers. This study highlights the importance of monitoring treated patients to manage the risk of toxicity and prevent treatment discontinuation.</p></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"4 ","pages":"Article 100045"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949820124000237/pdfft?md5=797b441616020f8749e03aac43cba041&pid=1-s2.0-S2949820124000237-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141244425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-world effectiveness of post-trastuzumab emtansine treatment for human epidermal growth factor receptor 2-positive metastatic breast cancer: a multicenter, matched cohort analysis from the Epidemiology Strategy and Medical Economics database (2008-2018)","authors":"C. Courtinard ,&nbsp;V. Barbet ,&nbsp;R. Schiappa ,&nbsp;F. Pilleul ,&nbsp;S. Michiels ,&nbsp;S. Dabakuyo ,&nbsp;S. Gourgou ,&nbsp;A. Jaffre ,&nbsp;B. Asselain ,&nbsp;L. Bosquet ,&nbsp;K. Dunton ,&nbsp;M. Rosenlund ,&nbsp;Z. Liang ,&nbsp;J. Cathcart ,&nbsp;S. Delaloge","doi":"10.1016/j.esmorw.2024.100043","DOIUrl":"https://doi.org/10.1016/j.esmorw.2024.100043","url":null,"abstract":"<div><h3>Background</h3><p>Real-world data (RWD) can contextualize clinical trial data. We present real-world evidence that supplemented the single-arm DESTINY-Breast01 trial, which assessed the efficacy and safety of trastuzumab deruxtecan (T-DXd) in patients with human epidermal growth factor receptor 2-positive (HER2+) metastatic breast cancer (mBC) previously treated with trastuzumab emtansine (T-DM1).</p></div><div><h3>Patients and methods</h3><p>Patients from the French Epidemiology Strategy and Medical Economics (ESME) mBC database who initiated treatment for HER2+ mBC between 1 January 2008 and 31 December 2016, and received one or more treatment lines following T-DM1 were propensity score matched 1 : 1 to patients from DESTINY-Breast01 to create an ESME DB-01 matched cohort. Treatment patterns, real-world best overall response, real-world objective response rate (rwORR), real-world disease control rate (rwDCR), real-world progression-free survival (rwPFS), and overall survival (OS) were estimated, including by prior pertuzumab exposure and <em>de novo</em>/relapsed mBC status.</p></div><div><h3>Results</h3><p>A total of 137 patients from the ESME mBC database (78 received prior pertuzumab, 59 did not) were matched to 137 patients from DESTINY-Breast01. In the ESME DB-01 matched cohort, 73.7% received an anti-HER2 drug after T-DM1 treatment. The rwORR was 12.2% (95% confidence interval [CI] 6.2% to 18.2%; only partial responses) and rwDCR was 73.9% (95% CI 65.9% to 81.9%). The median rwPFS was 4.7 months (95% CI 3.8-6.0 months) and similar regardless of prior pertuzumab exposure or <em>de novo</em>/relapsed mBC status. The median OS was 24.1 months (95% CI 18.5-26.4 months) and longer in patients naive to versus exposed to pertuzumab and in patients with <em>de novo</em> versus relapsed mBC.</p></div><div><h3>Conclusion</h3><p>These RWD contextualized results of DESTINY-Breast01 and demonstrated an unmet medical need in patients with HER2+ mBC after T-DM1 treatment.</p></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"4 ","pages":"Article 100043"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949820124000213/pdfft?md5=a06f050004d7530764c9bb5bb625b611&pid=1-s2.0-S2949820124000213-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141244453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-world behavioral practices of cancer patients: misconceptions compromising daily life activities","authors":"E. Shachar ,&nbsp;S. Peleg-Hasson ,&nbsp;D. Vorobiof ,&nbsp;N. Moisa ,&nbsp;E. Waller ,&nbsp;T. Safra ,&nbsp;I. Wolf","doi":"10.1016/j.esmorw.2024.100041","DOIUrl":"https://doi.org/10.1016/j.esmorw.2024.100041","url":null,"abstract":"<div><h3>Background</h3><p>Health-related quality of life is commonly used as an endpoint in clinical trials. While it evaluates the presence of symptoms, it does not measure patients’ ability to maintain normal daily life activities (DLA). We designed a daily life assessment tool, validated among actively treated cancer patients at a single center before the coronavirus 2019 pandemic. We discovered that most patients reported compromised daily activities. In this study we aimed to examine DLA in an international cohort.</p></div><div><h3>Methods</h3><p>A locally validated questionnaire was distributed internationally using the Belong.life digital health platform. We examined real-world patient-reported practices. The survey consisted of demographic, clinical, behavioral parameters and sources guiding and supporting patient practices.</p></div><div><h3>Results</h3><p>The study comprised 1395 patient-reported outcomes. The majority of participants (1005, 73%) reported at least one adopted limitation in daily activities, and 305 (22%) maintained more than half of these constraints. Daily life restrictions included avoiding sun exposure (779, 58%), international travel (417, 33%), indoor public places (431, 33%), hair dyeing (271, 23%), domestic tourism (284, 22%), contact with friends and family (231, 18%), children and grandchildren (202, 16%), public spaces (190, 14.62%), and contact with pets (135, 10%). Multiple sources were implicated by patients guiding their behavior, including healthcare professionals (951, 66%), non-medical authorities [(internet, patient forums, partners, friends, and family (171, 12%)], and both non-medical authorities and the healthcare team (320, 22.19%). There was no association between country of origin (<em>P</em> = 0.12), and education level (<em>P</em> = 0.36) across patients who maintained strict (≥50% of the limitations) and less strict restrictions (&lt;50% of the limitations). A significant association was noted between younger age (<em>P</em> = 0.001), female sex (<em>P</em> = 0.01) and primary cancer site (<em>P</em> &lt; 0.0001), and the adoption of strict restrictions.</p></div><div><h3>Conclusion</h3><p>The majority of patients globally reported compromised daily activities, which are likely attributed to misconceptions about therapy and disease. These findings call for the assessment of an overlooked measure, DLA reflecting real-life quality of life, as an additional endpoint of clinical trials, aiming to achieve the ultimate benefit for our patients, a measure of a full and meaningful life.</p></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"4 ","pages":"Article 100041"},"PeriodicalIF":0.0,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949820124000195/pdfft?md5=cd73ed96e136733c4817e31a712ca505&pid=1-s2.0-S2949820124000195-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140924372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating GPT-4 as an academic support tool for clinicians: a comparative analysis of case records from the literature","authors":"B.L. Fabre ,&nbsp;M.A.F. Magalhaes Filho ,&nbsp;P.N. Aguiar Jr ,&nbsp;F.M. da Costa ,&nbsp;B. Gutierres ,&nbsp;W.N. William Jr ,&nbsp;A. Del Giglio","doi":"10.1016/j.esmorw.2024.100042","DOIUrl":"https://doi.org/10.1016/j.esmorw.2024.100042","url":null,"abstract":"<div><h3>Background</h3><p>Artificial intelligence (AI) and natural language processing (NLP) advancements have led to sophisticated tools like GPT-4.0, allowing clinicians to explore its utility as a health care management support tool. Our study aimed to assess the capability of GPT-4 in suggesting definitive diagnoses and appropriate work-ups to minimize unnecessary procedures.</p></div><div><h3>Materials and methods</h3><p>We conducted a retrospective comparative analysis, extracting clinical data from 10 cases published in the <em>New England Journal of Medicine</em> after 2022 and inputting this data into GPT-4 to generate diagnostic and work-up recommendations. Primary endpoint: the ability to correctly identify the final diagnosis. Secondary endpoints: its ability to list the definitive diagnosis as the first of the five most likely differential diagnoses and determine an adequate work-up.</p></div><div><h3>Results</h3><p>The AI could not identify the definitive diagnosis in 2 out of 10 cases (20% inaccuracy). Among the eight cases correctly identified by the AI, five (63%) listed the definitive diagnosis at the top of the differential diagnosis list. In terms of diagnostic tests and exams, the AI suggested unnecessary procedures in two cases, representing 40% of the cases where it failed to correctly identify the final diagnosis. Moreover, the AI could not suggest adequate treatment for seven cases (70%). Among them, the AI suggested inappropriate management for two cases, and the remaining five received incomplete or non-specific advice, such as chemotherapy, without specifying the best regimen.</p></div><div><h3>Conclusions</h3><p>Our study demonstrated GPT-4’s potential as an academic support tool, although it cannot correctly identify the final diagnosis in 20% of the cases and the AI requested unnecessary additional diagnostic tests for 40% of the patients. Future research should focus on evaluating the performance of GPT-4 using a more extensive and diverse sample, incorporating prospective assessments, and investigating its ability to improve diagnostic and therapeutic accuracy.</p></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"4 ","pages":"Article 100042"},"PeriodicalIF":0.0,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949820124000201/pdfft?md5=f32f81c8fc771b7987718bc67be461a8&pid=1-s2.0-S2949820124000201-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140924464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Changes in survival of >3800 patients with metastatic colorectal cancer in Germany: results from a 16-year prospective longitudinal real-world data analysis","authors":"N. Marschner ,&nbsp;T. Seufferlein ,&nbsp;K. Potthoff ,&nbsp;M.-O. Zahn ,&nbsp;J. Uhlig ,&nbsp;S. Dörfel ,&nbsp;A. Karcher ,&nbsp;A. Sauer ,&nbsp;C. Maintz ,&nbsp;S. Fruehauf ,&nbsp;U. Hutzschenreuter ,&nbsp;S. Tech ,&nbsp;M. Grafetstätter ,&nbsp;L. Kruggel ,&nbsp;M. Jänicke","doi":"10.1016/j.esmorw.2024.100040","DOIUrl":"https://doi.org/10.1016/j.esmorw.2024.100040","url":null,"abstract":"<div><h3>Background</h3><p>Results from recent clinical trials, showing median survival times of &gt;30 months for patients with metastatic colorectal cancer (mCRC), set a new benchmark for first-line treatment. As, however, most patients are treated outside of trials, evidence from population-based studies is warranted to evaluate whether survival times translate to real world.</p></div><div><h3>Patients and methods</h3><p>Data on treatment and outcome of 3816 patients with mCRC, observed between 2006 and 2022, were collected from 166 sites in Germany into the prospective Tumor Registry Colorectal Cancer. Data were analyzed according to start of first-line palliative treatment, divided into three time periods (2006-2010, 2011-2014 and 2015-2018). Overall survival (OS) was estimated using the Kaplan–Meier method.</p></div><div><h3>Results</h3><p>Most patients received doublet chemotherapy (CTx) across all time periods (about 82%). The use of triplet combination CTx increased over time from 0.9% (2006-2010), over 1.3% (2011-2014) to 5.6% (2015-2018). More patients received anti-epidermal growth factor receptor antibodies over time (2006-2010: 6.5%; 2011-2014: 18.7%; 2015-2018: 25.3%). Median OS for patients who started palliative treatment between 2006 and 2010, 2011 and 2014 and 2015 and 2018 was 21.4 months [95% confidence interval (CI) 20.3-23.1 months], 21.9 months (95% CI 20.8-23.4 months) and 22.9 months (95% CI 21.8-24.9 months), respectively.</p></div><div><h3>Conclusion</h3><p>Since the successful introduction of doublet chemotherapy with monoclonal antibodies, median OS of patients with mCRC in clinical practice remained unchanged at about 22 months over a period of 16 years. As such, our data highlight the need for new treatment options to further improve survival of patients with mCRC.</p></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"4 ","pages":"Article 100040"},"PeriodicalIF":0.0,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949820124000183/pdfft?md5=994c9a3bf3cc448503ebc671405b55ea&pid=1-s2.0-S2949820124000183-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140880196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of machine learning methods for the retrospective detection of ovarian cancer recurrences from chemotherapy data","authors":"A.D. Coles ,&nbsp;C.D. McInerney ,&nbsp;K. Zucker ,&nbsp;S. Cheeseman ,&nbsp;O.A. Johnson ,&nbsp;G. Hall","doi":"10.1016/j.esmorw.2024.100038","DOIUrl":"https://doi.org/10.1016/j.esmorw.2024.100038","url":null,"abstract":"<div><h3>Background</h3><p>Cancer recurrences are poorly recorded within electronic health records around the world. This hinders research into the efficacy of cancer treatments. Currently, the retrospective identification of recurrence/progression diagnosis dates is achieved by staff who manually review patients’ health records. This is expensive, time-consuming, and inefficient. Machine Learning models may expedite the review of health records and facilitate the assessment of alternative cancer therapies.</p></div><div><h3>Materials and methods</h3><p>This paper evaluates the use of four machine learning models (random forests, conditional inference trees, decision trees, and logistic regression) in identifying proxy dates of epithelial ovarian cancer recurrence/progression from chemotherapy data, in 531 patients at Leeds Teaching Hospital Trust.</p></div><div><h3>Results</h3><p>The random forest achieved the highest F1 score of 0.941 (95% confidence interval 0.916-0.968) when identifying recurrence events. Both the random forest and decision tree models’ classifications closely conform to chart-reviewed time to next treatment, serving as a surrogate for recurrence-free survival. Additionally, all models reached an F1 score &gt;0.940 when identifying patients whose cancer recurred/progressed.</p></div><div><h3>Conclusions</h3><p>Our models proficiently identify both proxy dates for recurrence/progression diagnoses and patients whose cancer recurred/progressed. Considering the similar performance of the random forest and decision tree, model preference should be determined by the interpretability required to assist chart review and the ease of implementation into existing architecture.</p></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"4 ","pages":"Article 100038"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S294982012400016X/pdfft?md5=037748083c08b03abbc66eb0cbc15421&pid=1-s2.0-S294982012400016X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140816946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Health-related quality of life in patients with gastrointestinal stromal tumor: data from a real-world cohort compared with a normative population","authors":"D. van de Wal ,&nbsp;D. den Hollander ,&nbsp;I.M.E. Desar ,&nbsp;H. Gelderblom ,&nbsp;A.W. Oosten ,&nbsp;A.K.L. Reyners ,&nbsp;N. Steeghs ,&nbsp;W.T.A. van der Graaf ,&nbsp;O. Husson","doi":"10.1016/j.esmorw.2024.100037","DOIUrl":"https://doi.org/10.1016/j.esmorw.2024.100037","url":null,"abstract":"<div><h3>Background</h3><p>Treatment and follow-up (FU) care procedures for gastrointestinal stromal tumors (GISTs) impose great challenges on patients and could potentially affect their health-related quality of life (HRQoL). The aims of our study were to (i) assess HRQoL among patients with GIST in different treatment phases and settings and to compare this with the HRQoL of an age- and sex-matched normative population, (ii) determine the occurrence of disease- and treatment-specific symptoms, and (iii) investigate which sociodemographic and clinical characteristics and symptoms were associated with HRQoL.</p></div><div><h3>Methods</h3><p>A total of 328 Dutch patients with GIST (response rate 63%) completed a one-time survey including the European Organization for Research and Treatment of Cancer Quality of Life Core Questionnaire (EORTC QLQ-C30), which was used to assess HRQoL. HRQoL scores are presented as means and standard deviations (mean ± SD), and were compared with those of an age- and sex-matched normative population.</p></div><div><h3>Results</h3><p>The global QoL of patients receiving imatinib in a curative setting (mean ± SD 81.2 ± 12.6) was comparable with the normative population (mean ± SD 77.1 ± 18.2), while patients who had completed their curative treatment [including those discharged from FU (mean ± SD 85.2 ± 14.0) and still in FU (mean ± SD 82.7 ± 15.0)] had a significant better global QoL with comparable functioning scores. Patients on tyrosine kinase inhibitors in a palliative setting scored significantly lower on global QoL (mean ± SD 71.6 ± 19.4) and all functioning scales compared with the normative population. HRQoL was most affected by fatigue, in addition to pain, dyspnea, and financial difficulties, which all occurred more often in patients treated in a palliative setting compared with patients in the curative setting.</p></div><div><h3>Conclusion</h3><p>With these results, medical oncologists can reassure patients with GIST treated in an adjuvant setting that their HRQoL will not be permanently affected by imatinib and provide appropriate support to patients in the palliative setting.</p></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"4 ","pages":"Article 100037"},"PeriodicalIF":0.0,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2949820124000158/pdfft?md5=9b727b1bb57d82eff8476753d6b9791d&pid=1-s2.0-S2949820124000158-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140638419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}