ESMO Real World Data and Digital Oncology最新文献

{"title":"Challenges in analyzing real-world evidence: analysis of androgen deprivation therapy use for prostate cancer in the REASSURE study","authors":"B. Tran ,&nbsp;N. Yeh ,&nbsp;A. Gayle ,&nbsp;E. Holmes ,&nbsp;J. Hu ,&nbsp;S. Damineni ,&nbsp;N. Kebede ,&nbsp;N. Shore","doi":"10.1016/j.esmorw.2025.100149","DOIUrl":"10.1016/j.esmorw.2025.100149","url":null,"abstract":"<div><div>An understanding of how androgen deprivation therapy (ADT) prescribing patterns impact patient outcomes in a real-world setting is needed to help inform treatment decisions and improve the care of patients with prostate cancer (PCa). REASSURE was a retrospective, observational study that described patterns of ADT use derived from the electronic health records of 952 patients with PCa in the CancerLinQ database. Study objectives included patient demographics, clinical characteristics, and ADT treatment duration by treatment received [goserelin or other ADTs (leuprorelin, degarelix, or triptorelin)]. While some patterns of ADT use in REASSURE were consistent with recommendations from clinical practice guidelines, there were also some inconsistencies. Findings from REASSURE highlighted the importance of considering potential differences in health care systems, population coverage, and patient data collection between regions, as well as incorporating data from multiple sources to capture data from more diverse patient populations, thus improving the quality of outputs from real-world studies.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"8 ","pages":"Article 100149"},"PeriodicalIF":0.0,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144139715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Time to next treatment to evaluate the therapeutic sequence after first- or second-line CDK4/6 inhibitors of hormone receptor-positive, HER2-negative advanced breast cancer in Italy: a retrospective/prospective observational trial GOIRC-04-2019","authors":"L. Moscetti ,&nbsp;E. Barbieri ,&nbsp;E. Zattarin ,&nbsp;P. Vici ,&nbsp;G. Zoppoli ,&nbsp;A. Musolino ,&nbsp;S. Natalizio ,&nbsp;F. Canino ,&nbsp;F. Ravera ,&nbsp;L. Filomeno ,&nbsp;T. Arcuri ,&nbsp;C. Omarini ,&nbsp;F. Piacentini ,&nbsp;M. Barbolini ,&nbsp;L. Cortesi ,&nbsp;F. Caggia ,&nbsp;M. Civallero ,&nbsp;M. Dominici ,&nbsp;A. Toss","doi":"10.1016/j.esmorw.2025.100154","DOIUrl":"10.1016/j.esmorw.2025.100154","url":null,"abstract":"<div><h3>Background</h3><div>Palbociclib, ribociclib, and abemaciclib are approved for the treatment of hormone receptor (HR)-positive, human epidermal growth factor receptor 2 (HER2)-negative advanced breast cancer (aBC), in combination with aromatase inhibitors or fulvestrant. However, there is no standard care following progression on cyclin-dependent kinase 4/6 inhibitors (CDK4/6i).</div></div><div><h3>Materials and methods</h3><div>This study aimed to evaluate treatment patterns and effectiveness following the failure of CDK4/6i therapy. The analysis included 407 patients who received CDK4/6i in first- or second-line treatment across three cancer centers. Primary endpoints included time to next treatment (TTNT) and real-world progression-free survival.</div></div><div><h3>Results</h3><div>The results demonstrated a median TTNT (mTTNT) of 26 months [95% confidence interval (CI) 21-31 months] for patients receiving CDK4/6i as first-line treatment. Subsequent therapies, including chemotherapy (CT), endocrine therapy (ET) with or without everolimus, and CDK4/6i-based regimens, were evaluated. The mTTNT for second-line treatments was 13 months (95% CI 9-16 months), with CT showing the longest duration [24 months (95% CI 17-30 months) versus 15 months (95% CI 11-18 months)] for CDK4/6-based regimens versus 9.6 months for everolimus with or without ET (95% CI 6-11 months). Multivariate analysis identified the number of disease sites as a significant predictor of longer TTNT in the first-line setting. Safety data revealed that CDK4/6i dose reductions due to toxicity occurred in 47% of patients, with neutropenia being the most common adverse event.</div></div><div><h3>Conclusions</h3><div>These findings emphasize the variability in treatment efficacy following CDK4/6i therapy and underscore the importance of personalized treatment strategies. Further research is needed to optimize therapeutic sequences and improve patient outcomes in this setting.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"8 ","pages":"Article 100154"},"PeriodicalIF":0.0,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144147265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prolonged progression-free survival on epidermal growth factor receptor-tyrosine kinase inhibitors predicts superior response to atezolizumab-based therapy over chemotherapy in epidermal growth factor receptor-mutated non-small-cell lung cancer following progression","authors":"K. Morimoto ,&nbsp;T. Yamada ,&nbsp;N. Furuya ,&nbsp;H. Tanaka ,&nbsp;A. Yoshimura ,&nbsp;T. Oba ,&nbsp;M. Hibino ,&nbsp;T. Fukuda ,&nbsp;Y. Goto ,&nbsp;A. Nakao ,&nbsp;S. Ogusu ,&nbsp;Y. Okazaki ,&nbsp;T. Harada ,&nbsp;T. Ota ,&nbsp;K. Masubuchi ,&nbsp;K. Mikami ,&nbsp;T. Hata ,&nbsp;S. Matsumoto ,&nbsp;R. Honda ,&nbsp;K. Date ,&nbsp;K. Takayama","doi":"10.1016/j.esmorw.2025.100152","DOIUrl":"10.1016/j.esmorw.2025.100152","url":null,"abstract":"<div><h3>Background</h3><div>Patients with non-small-cell lung cancer (NSCLC) harboring epidermal growth factor receptor (<em>EGFR</em>) mutations who experience disease progression after treatment with an EGFR-tyrosine kinase inhibitor (EGFR-TKI) often receive subsequent treatment with either platinum-based chemotherapy (Chemo) or a combination regimen of atezolizumab, bevacizumab, carboplatin, and paclitaxel (ABCP). However, whether the efficacy of prior EGFR-TKI treatment influences the outcomes of Chemo or ABCP remains unclear.</div></div><div><h3>Materials and methods</h3><div>Between January 2017 and July 2022, we retrospectively assessed patients with <em>EGFR-</em>mutant NSCLC who received Chemo or ABCP after EGFR-TKIs across 20 institutions.</div></div><div><h3>Results</h3><div>Overall, data of 350 patients with advanced or recurrent <em>EGFR</em>-mutant NSCLC were analyzed. Of these, 262 patients (74.9%) received Chemo, and 88 (25.1%) received ABCP. No significant difference was noted in progression-free survival (PFS) after Chemo between patients who responded to prior EGFR-TKIs for ≥10 months and those who had responded for &lt;10 months (6.1 versus 5.1 months; log-rank test, <em>P</em> = 0.12). In contrast, patients who responded to prior EGFR-TKIs for ≥10 months exhibited a significantly longer PFS to ABCP (8.7 versus 6.7 months; log-rank test, <em>P</em> = 0.002). After propensity score matching, among patients who responded to prior EGFR-TKIs for ≥10 months, the ABCP group had a significantly longer PFS than the Chemo group (8.6 versus 5.3 months; log-rank test, <em>P</em> = 0.008).</div></div><div><h3>Conclusion</h3><div>The efficacy of prior EGFR-TKI treatment in patients with <em>EGFR-</em>mutant NSCLC who experience disease progression could be a predictive marker for ABCP rather than Chemo efficacy.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"8 ","pages":"Article 100152"},"PeriodicalIF":0.0,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144105251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Guy’s Cancer Cohort: Guy’s Cancer Centre’s Real-World Evidence Programme 5 years later","authors":"C.L. Moss ,&nbsp;B. Russell ,&nbsp;G. George ,&nbsp;J. Handford ,&nbsp;E. Josephides ,&nbsp;S. Green ,&nbsp;A. Mera ,&nbsp;K. Haire ,&nbsp;A. Igra ,&nbsp;M. Gladman ,&nbsp;S. Hachlili ,&nbsp;A. Davies ,&nbsp;D. Smith ,&nbsp;S. Dolly ,&nbsp;P. Ross ,&nbsp;M. Lei ,&nbsp;E. Sawyer ,&nbsp;C. Harrison ,&nbsp;M. Kazmi ,&nbsp;A. Rigg ,&nbsp;J. Brady","doi":"10.1016/j.esmorw.2025.100145","DOIUrl":"10.1016/j.esmorw.2025.100145","url":null,"abstract":"<div><h3>Background</h3><div>As the burden of cancer rises, the value of real-world data in addressing clinically relevant research questions is increasingly recognised. The Guy’s Cancer Real-World Evidence Programme, initiated in 2018 at Guy’s and St Thomas’ Trust (GSTT), informs decision making and local policy. Within this programme, the Guy’s Cancer Cohort (GCC) database has amplified real-world evidence (RWE) capabilities and improved data internalisation. GCC was renewed by the Research Ethics Committee in May 2023 (Ref: 23/NW/0105) and expanded to include patients investigated for new or recurrent cancer.</div></div><div><h3>Construction and content</h3><div>GCC includes patients investigated, diagnosed, and/or treated for cancer, enabling case-control studies and the exploration of factors linked to cancer diagnosis. Annually, ∼8000 cancers are diagnosed at Guy’s Cancer Centre. Only pseudonymised data are processed, and the database aligns with the National Health Service national opt-out scheme. Clinical data captured include demographics, tumour characteristics, treatments, quality of life, and imaging data.</div></div><div><h3>Conclusions</h3><div>GCC provides essential infrastructure to explore clinical, mechanistic, and supportive care research questions. Its renewal and expansion optimise data collection and linkage, improving patient care and outcomes. Applications for pseudonymised datasets can be directed to <span><span><span>[email protected]</span></span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"8 ","pages":"Article 100145"},"PeriodicalIF":0.0,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143935057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of a clinical prediction model for hospitalization after emergency department admission in patients with cancer","authors":"Z.L.R. Kaplan ,&nbsp;D. van Klaveren ,&nbsp;J.G.A. den Duijn ,&nbsp;R.J.C.G. Verdonschot ,&nbsp;N. Wlazlo ,&nbsp;J.G.J.V. Aerts ,&nbsp;J. Bromberg ,&nbsp;H.F. Lingsma ,&nbsp;J. Alsma ,&nbsp;M.M.E.M. Bos","doi":"10.1016/j.esmorw.2025.100141","DOIUrl":"10.1016/j.esmorw.2025.100141","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Emergency department (ED) admissions by cancer patients often result in hospitalization and prolonged ED stays, contributing to overcrowding. Early identification of patients at risk of hospitalization could improve ED flow and ensure timely provision of oncological care. This study aimed to develop and validate models to predict hospitalization among cancer patients admitted to the ED.</div></div><div><h3>Methods</h3><div>Adult cancer patients who were admitted to the ED between 1 July 2018 and 30 September 2020 at the Erasmus University Medical Center were included. Data from electronic health records (EHR) were used to develop two logistic regression models: (i) a baseline model including predictors available after ED triage (e.g. patient characteristics, vital parameters) and (ii) an extended model including blood test results. Predictors were selected using the Wald χ² statistic. To prevent overfitting, a uniform shrinkage factor was applied. Model performance was assessed with temporal validation (1 October 2019 to 1 January 2020) and evaluated with calibration plots and C-statistics.</div></div><div><h3>Results</h3><div>Of 7284 ED admissions, 3967 (54%) resulted in hospitalization. The most common cancers requiring hospitalization were lung, hepatopancreatobiliary, and colorectal cancer. The baseline model included age, sex, primary malignancy, symptoms, metastasis, temperature, pain score, diastolic blood pressure, and heart rate. The model showed good calibration (intercept −0.04, slope 0.86) and discriminative ability [C-statistic 0.71, 95% confidence interval (CI) 0.68-0.74]. The extended model showed improved performance (intercept −0.09, slope 0.92; C-statistic 0.75, 95% CI 0.72-0.78).</div></div><div><h3>Conclusion</h3><div>Hospitalization risk of cancer patients admitted to the ED can be predicted using routinely collected EHR data, which could aid in optimizing ED patient flow and ensuring timely provision of oncological services.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"8 ","pages":"Article 100141"},"PeriodicalIF":0.0,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prognostic score models for acquired resistance to frontline anti-programmed cell death protein 1/programmed death-ligand 1 therapy in metastatic non-small-cell lung cancer","authors":"J.C. Murray ,&nbsp;Q. Huang ,&nbsp;Y.-C. Chen ,&nbsp;C. Hu ,&nbsp;R.L. DiSantostefano ,&nbsp;C. Wong ,&nbsp;L. Glatz ,&nbsp;E. Curran ,&nbsp;L.C. Villaruz ,&nbsp;A.N. Hasan ,&nbsp;A.J. Schoenfeld","doi":"10.1016/j.esmorw.2025.100148","DOIUrl":"10.1016/j.esmorw.2025.100148","url":null,"abstract":"<div><h3>Background</h3><div>Acquired resistance (AR) to immunotherapy following initial response occurs frequently in metastatic non-small-cell lung cancer (mNSCLC). We developed and validated easy-to-apply prognostic score models to identify patients with mNSCLC at greater risk of AR to frontline (1L) anti-programmed cell death protein 1/programmed death-ligand 1 [anti-PD-(L)1] therapy.</div></div><div><h3>Materials and methods</h3><div>Electronic health records of patients with mNSCLC who responded to 1L anti-PD-(L)1 (diagnosed 2015-2023) in the ConcertAI Patient360™ database were analyzed. Multivariable Cox models (monotherapy versus combination) assessing association between baseline prognostic factors and real-world duration of response (rwDoR) were used to develop prognostic scores and stratify patients into low- and high-risk groups. Risk stratification was evaluated using Kaplan-Meier curves, performance metrics, and decision curves. External validation utilized the COTA NSCLC dataset.</div></div><div><h3>Results</h3><div>The majority of patients (<em>n</em> = 3181) did not respond to anti-PD-(L)1, leaving 1891 1L immunotherapy-responding patients (94% partial responders, 6% complete responders), with a median (interquartile range) time from anti-PD-(L)1 initiation to first response of 2.5 months (1.84-3.19 months). Across the monotherapy and combination therapy cohorts, median rwDOR was significantly shorter in high-risk (7.6 and 5.2 months) versus low-risk groups (18.9 and 12.0 months), suggesting model differentiation. Decision curves were above reference lines at predicted AR probabilities 180-day after initial response (monotherapy: 35.5%; combination therapy: 45.4%) corresponding to the cut-off for high-risk patients, indicating greater net benefits when employing risk grouping. External dataset validation demonstrated that model-based risk grouping significantly distinguished rwDOR and exhibited consistent performance metrics.</div></div><div><h3>Conclusions</h3><div>Proposed prognostic score models may facilitate identifying patient subsets at higher risk of AR to 1L anti-PD-(L)1.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"8 ","pages":"Article 100148"},"PeriodicalIF":0.0,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143923375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning for prediction of 30-day mortality in patients with advanced cancer: comparing pan-cancer and single-cancer models","authors":"S. Bjerregaard-Michelsen ,&nbsp;L.Ø. Poulsen ,&nbsp;A. Bjerrum ,&nbsp;M. Bøgsted ,&nbsp;C. Vesteghem","doi":"10.1016/j.esmorw.2025.100146","DOIUrl":"10.1016/j.esmorw.2025.100146","url":null,"abstract":"<div><h3>Background</h3><div>Systemic anticancer therapy (SACT) near the end of life (EOL) reduces the quality of the patient’s remaining life without clinical benefit. Studies investigating machine learning models for predicting cancer mortality to guide treatment decisions have primarily focused on specific types of cancer. This study aimed to evaluate the ability of a pan-cancer model to generalize across 10 cancer types when predicting short-term mortality.</div></div><div><h3>Patients and methods</h3><div>This study included patients with advanced cancer who were referred to the Department of Oncology at Aalborg University Hospital and died between January 2008 and December 2021 (<em>N</em> = 8690). Clinical data were used to train, validate, and test a pan-cancer model and 10 single-cancer models based on the eXtreme Gradient Boosting (XGBoost) algorithm. The average precision (AP) of the pan-cancer and single-cancer models was assessed and compared. Furthermore, explainable AI with Shapley additive explanations (SHAP) was used to evaluate shared prognostic information across the cancer types.</div></div><div><h3>Results</h3><div>The mean AP increased from 0.51 using the single-cancer models to 0.56 using the pan-cancer model to predict short-term mortality (random baseline 0.12). Important features identified by SHAP were shared across cancer types, indicating shared predictors of 30-day mortality. The most important features for predicting 30-day mortality were plasma albumin level, white blood cell count, and lactate dehydrogenase levels.</div></div><div><h3>Conclusion</h3><div>A pan-cancer model enhanced the performance of short-term mortality estimates compared with models based on single cancer types. Thus, including multiple cancer types in predictive modeling in oncology could be advantageous when shared predictors are expected across cancer types.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"8 ","pages":"Article 100146"},"PeriodicalIF":0.0,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143916839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Local and central testing for HER2, PD-L1, MSI/MMR, EBV, and CLDN18.2 in advanced gastric cancer: results from the SAPHIR registry☆","authors":"K. Potthoff ,&nbsp;H. Bläker ,&nbsp;T. Dechow ,&nbsp;A. Binninger ,&nbsp;K. Ringwald ,&nbsp;R. de Buhr ,&nbsp;E. von der Heyde ,&nbsp;M.-O. Zahn ,&nbsp;A. Nusch ,&nbsp;S. Dörfel ,&nbsp;H. Schulz ,&nbsp;I. Haffner ,&nbsp;A.K. Höhn ,&nbsp;A. Monecke ,&nbsp;S. Lorenzen ,&nbsp;A. Reinacher-Schick ,&nbsp;M. Jänicke ,&nbsp;F. Lordick","doi":"10.1016/j.esmorw.2025.100144","DOIUrl":"10.1016/j.esmorw.2025.100144","url":null,"abstract":"<div><h3>Background</h3><div>Predictive biomarkers guide treatment selection of patients with advanced gastric and gastroesophageal junction adenocarcinoma (GAC/GEJAC). However, real-world data on testing frequencies and prevalence of biomarkers in Europe are limited.</div></div><div><h3>Methods</h3><div>The SAPHIR registry, a prospective, observational cohort study of patients with metastatic GAC/GEJAC, collects longitudinal clinical data, patient-reported outcomes as well as tumor tissue samples from routine diagnostics. Here, we focus on biomarker testing and test results in routine clinical practice. In addition, central pathology assessment was performed for HER2, PD-L1, dMMR/MSI, EBV, and CLDN18.2.</div></div><div><h3>Results</h3><div>From December 2019 until March 2022, a total of 473 evaluable patients were enrolled at 109 study sites in Germany. Their median age was 66.8 years, 73.6% were male, and 76.7% had an ECOG performance status of 0/1. In clinical routine, testing rates for HER2, PD-L1, MSI, EBV, and MMR were 78.6%, 31.3%, 15.6%, 4.9%, and 2.5%, respectively. CLDN18.2 was not tested during the respective period. By central testing, the positivity rates were 11.8% for HER2, 75.2% for PD-L1 (CPS ≥1, TPS/IC ≥1%), 2.5% for dMMR/MSI-H, 0.6% for EBV, and 26.7% for CLDN18.2. Deviations between local and central testing were 12.4% for HER2 and 22.4% for PD-L1.</div></div><div><h3>Conclusions</h3><div>This study provides valuable insights on molecular testing in patients with GAC/GEJAC in Germany. In real-world, patients were frequently tested for actionable alterations, but there is room for improvement. Deviating test results of HER2 and PD-L1 by local and central pathology may reflect limitations in testing methodologies. In addition, these patients might not receive the most effective treatment.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"8 ","pages":"Article 100144"},"PeriodicalIF":0.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bridging communication gaps: the role of voice-enabled AI in medicine","authors":"C.M.L. Loeffler ,&nbsp;H.S. Muti ,&nbsp;J.N. Kather ,&nbsp;D. Truhn","doi":"10.1016/j.esmorw.2025.100138","DOIUrl":"10.1016/j.esmorw.2025.100138","url":null,"abstract":"<div><div>Recent advancements in voice-enabled artificial intelligence (AI), particularly end-to-end speech-to-speech models, are reshaping communication within health care. These models, such as OpenAI’s Advanced Voice Mode (AVM), offer real-time, nuanced human-like interactions by capturing intonation and pitch, thereby enabling more natural machine–human dialogue. In this paper we explore the integration of voice-enabled AI into medical practice, highlighting the potential to improve clinical efficiency, medical education, and patient engagement by providing self-recorded use cases. While the benefits are promising—ranging from increased accessibility to reduced clinician workload—challenges remain in data security, reliability, integration with existing systems, and ethical use. Addressing these concerns through robust regulation, transparent development, and targeted training will be essential. Ultimately, voice-enabled AI holds transformative potential to bridge communication gaps in medicine and support more equitable, efficient, and patient-centered care.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"8 ","pages":"Article 100138"},"PeriodicalIF":0.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Time to adjuvant chemotherapy and overall survival in advanced-stage ovarian cancer patients in England: a population-based retrospective cohort study","authors":"L. Steventon ,&nbsp;S. Nicum ,&nbsp;K. Man ,&nbsp;D. Dodwell ,&nbsp;Z. Wang ,&nbsp;A. Patel ,&nbsp;B. Pickwell-Smith ,&nbsp;L. Wei ,&nbsp;P. Chambers","doi":"10.1016/j.esmorw.2025.100143","DOIUrl":"10.1016/j.esmorw.2025.100143","url":null,"abstract":"<div><h3>Background and purpose</h3><div>In advanced ovarian cancer, delayed time to chemotherapy (TTC) has been associated with poorer survival outcomes; evidence is conflicting, however. This study investigated the impact of patient demographic factors on TTC and assessed whether TTC was associated with 5-year overall survival.</div></div><div><h3>Materials and methods</h3><div>A retrospective cohort study was conducted using English national data for women with advanced-stage ovarian cancer (IIB-IV), treated with primary debulking surgery (PDS) or interval debulking surgery (IDS) + adjuvant carboplatin/paclitaxel chemotherapy between 1 January 2014 and 31 December 2019. Cox proportional hazards regression was used to compare the primary outcome of 5-year overall survival between patients treated within ≤6 weeks (0-42 days) or &gt;6 weeks (&gt;42 days) of surgery.</div></div><div><h3>Results</h3><div>A total of 4619 patients were included. Of these, 42% (<em>n</em> = 1940) received PDS and 58% (<em>n</em> = 2679) IDS. Median TTC was 45 days [interquartile range (IQR) 37-55 days] for PDS and 34 days (IQR 27-42 days) for IDS. TTC ≤6 weeks was associated with 5-year survival in the IDS cohort (HR 1.18, 95% CI 1.06-1.33, <em>P</em> = 0.003), but not in the PDS cohort (HR 1.04, 95% CI 0.90-1.21, <em>P</em> = 0.6). A higher proportion of patients from the most socioeconomically deprived backgrounds waited &gt;6 weeks (45%, <em>n</em> = 291) compared with the least deprived (37%, <em>n</em> = 398). Adjuvant chemotherapy was initiated in 72% of patients in London within ≤6 weeks compared with 47% in the North West.</div></div><div><h3>Conclusions</h3><div>Median TTC exceeded 4-week guidance from the European Society of Medical Oncology. TTC &gt;6 weeks was associated with reduced 5-year survival in patients treated with interval surgery, but not primary surgery. Regional disparities in TTC were observed.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"8 ","pages":"Article 100143"},"PeriodicalIF":0.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143881849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}