JCO precision oncology最新文献

{"title":"Personalized Circulating Tumor DNA Testing for Detection of Progression and Treatment Response Monitoring in Patients With Metastatic Invasive Lobular Carcinoma of the Breast.","authors":"Julia Foldi, Steffi Oesterreich, Antony Tin, Samuel Rivero-Hinojosa, Janie Fielder, Jenifer Ferguson, Giby V George, Ekaterina Kalashnikova, Angel A Rodriguez, Minetta C Liu, Adrian V Lee","doi":"10.1200/PO-24-00577","DOIUrl":"https://doi.org/10.1200/PO-24-00577","url":null,"abstract":"<p><strong>Purpose: </strong>Despite varying treatment responses and vastly different clinicopathologic characteristics, invasive lobular carcinoma (ILC) is treated similar to other subtypes of breast cancer. Serial personalized and tumor-informed, circulating tumor DNA (ctDNA) analysis may enable real-time treatment monitoring in metastatic ILC (mILC).</p><p><strong>Methods: </strong>In this retrospective analysis of real-world data, we analyzed ctDNA longitudinally in 66 patients with mILC using a clinically validated, personalized, tumor-informed 16-plex polymerase chain reaction-next generation sequencing assay (Signatera). We evaluated the predictive value on survival of a single ctDNA test result and correlated ctDNA detection rates and on-treatment ctDNA dynamics with disease status.</p><p><strong>Results: </strong>A total of 355 plasma samples were analyzed from 66 patients with mILC (median age at diagnosis, 62.6 years [range, 32.2-79.7 years]). On treatment, ctDNA dynamics correlated well with clinical response to treatment as assessed by imaging. Ninety-two percent (11 of 12) of patients with either ctDNA decrease (6 of 6) or no change in ctDNA levels (5 of 6) while on treatment showed clinical benefit from their prescribed regimen, whereas only 31% (4 of 13) of patients who showed an increase in their ctDNA had a clinical benefit on imaging. Finally, patients with a positive ctDNA test showed a greater probability of death compared with those with negative results, and the positive predictive value of ctDNA testing continued to increase exponentially with each positive result. Similarly, a negative ctDNA result was associated with 97% overall survival at 6 months and remained high (approximately 90%) at the 12-month follow-up.</p><p><strong>Conclusion: </strong>Serial ctDNA testing in patients with mILC is feasible and may enable personalized surveillance and real-time therapeutic monitoring.</p>","PeriodicalId":14797,"journal":{"name":"JCO precision oncology","volume":"9 ","pages":"e2400577"},"PeriodicalIF":5.3,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12058357/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143984849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-World Analysis of Disparities in Biomarker Testing and Use of Recommended Targeted Therapies in Metastatic Non-Small Cell Lung Cancer in the United States.","authors":"Michael J Dennis, Devin Abrahami, Maria Cecilia Vieira, Darrin Benjumea, Marley Boyd, Anran Shao, John Kelton, Sandip Pravin Patel","doi":"10.1200/PO-24-00449","DOIUrl":"https://doi.org/10.1200/PO-24-00449","url":null,"abstract":"<p><strong>Purpose: </strong>Guidelines recommend biomarker testing and biomarker-informed therapies in patients with metastatic non-small cell cancer (mNSCLC); however, the use remains suboptimal.</p><p><strong>Methods: </strong>To understand contemporary testing and treatment patterns, retrospective data from 42,037 patients with mNSCLC in a nationwide electronic health record-derived deidentified database from January 2011 to April 2023 were used to quantify testing rates, test positivity, and use of biomarker-informed therapies, stratified by key demographics to identify potential disparities. Multivariable logistic regression was conducted to include patient characteristics associated with the receipt of biomarker testing and subsequent biomarker-informed therapies.</p><p><strong>Results: </strong>A total of 34,510 patients (82.1%) received ≥one biomarker test(s). Biomarker testing and use of biomarker-informed therapies increased for all studied biomarkers (<i>EGFR</i>, <i>ALK</i>, <i>ROS1</i>, PD-L1, <i>BRAF</i>, <i>RET</i>, <i>MET</i>) over time, with highest rates observed in 2023: <i>EGFR</i> (88.7% and 79.5%, respectively) and <i>ALK</i> (87.7% and 84.3%, respectively). In multivariate logistic regression, patient sex, race, Eastern Cooperative Oncology Group at baseline, insurance type, smoking status at baseline, and histology were all significantly associated with odds of receiving biomarker testing. Covariates statistically associated with receipt of biomarker-informed therapy varied by biomarker without a clear pattern of association. Although the use of biomarker testing and biomarker-informed therapies has increased in recent years, gaps and potential disparities remain.</p><p><strong>Conclusion: </strong>Analysis of contemporary trends in biomarker testing and use of targeted therapies in mNSCLC in the United States highlight improvements in recent years. However, these rates remain suboptimal in specific strata of the patient population, including differences in racial groups and insurance groups, indicating further work is needed to bridge remaining gaps.</p>","PeriodicalId":14797,"journal":{"name":"JCO precision oncology","volume":"9 ","pages":"e2400449"},"PeriodicalIF":5.3,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144077885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessment of Circulating Tumor DNA Burden in Patients With Metastatic Gastric Cancer Using Real-World Data.","authors":"Senaka A Peter, Razvan Cristescu, Carol Peña, Angela Watkins, Carin R Espenschied, Nicole Zhang, Jiemin Liao","doi":"10.1200/PO-24-00582","DOIUrl":"https://doi.org/10.1200/PO-24-00582","url":null,"abstract":"<p><strong>Purpose: </strong>Circulating tumor DNA (ctDNA) has emerged as a promising biomarker with prognostic and potentially predictive value for several tumor types, including gastric cancer (GC). This study uses real-world data (RWD) to investigate the association of pretreatment ctDNA burden with clinical outcomes among patients with first-line (1L)-treated metastatic gastric cancer (mGC) in the United States.</p><p><strong>Methods: </strong>Patients were identified from the GuardantINFORM real-world clinical-genomic database. Adult patients with mGC who underwent testing with the Guardant360 assay from June 2014 to March 2022 and within 60 days before 1L treatment were included. The median of the maximum variant allele fraction (MVAF) was used to classify patients into high or low ctDNA burden groups, with undetectable ctDNA burden included in the low group. Associations with real-world outcome variables derived from claims, including time to treatment discontinuation (rwTTD), time to next treatment (rwTTNT), and overall survival (rwOS), were assessed using log-rank tests and multivariable Cox models.</p><p><strong>Results: </strong>A cohort of 824 patients with mGC was identified. Median MVAF was 2.9%, with 91% having detectable ctDNA. Among patients receiving chemo-based treatment (n = 537), rwTTDs were similar in low and high ctDNA burden groups, while those with high ctDNA burden showed significantly shorter rwTTNT and rwOS (median rwTTNT = 4.8 months <i>v</i> 7.4 months, <i>P</i> < .001; median rwOS = 13.2 months <i>v</i> 19.1 months, <i>P</i> < .001). Multivariable Cox analyses showed similar results. ctDNA burden in immunotherapy (n = 100) and trastuzumab-based (n = 99) treatment groups did not have significant associations with outcomes.</p><p><strong>Conclusion: </strong>We used RWD to demonstrate that high pretreatment ctDNA burden was associated with worse clinical outcomes in a mGC population receiving 1L chemotherapy-based treatments. Our analysis suggests ctDNA burden could be used as a prognostic biomarker for mGC.</p>","PeriodicalId":14797,"journal":{"name":"JCO precision oncology","volume":"9 ","pages":"e2400582"},"PeriodicalIF":5.3,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143964993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Outcomes After Radiation for Oligoprogressive Disease Sites in Patients With <i>EGFR</i>-Mutant Lung Cancer Treated With Osimertinib.","authors":"Monica F Chen, Mark Y Jeng, Jennifer Ma, Prashasti Agrawal, Elizabeth Dunne, Lillian A Boe, Mark G Kris, James Huang, Harini Veeraraghavan, Daniel Gomez, Helena A Yu","doi":"10.1200/PO-25-00047","DOIUrl":"10.1200/PO-25-00047","url":null,"abstract":"<p><strong>Purpose: </strong>Oligoprogressive disease (OPD) commonly occurs in patients with advanced <i>EGFR</i> mutation-positive non-small cell lung cancer (EGFR+ LC) on systemic therapy. While radiation therapy (XRT) to treat OPD can improve outcomes, the clinical and genomic predictors of benefit from local therapy for oligoprogression on osimertinib are unclear.</p><p><strong>Methods: </strong>We conducted a single-center retrospective analysis of 81 patients with EGFR+ LC on osimertinib who received XRT for OPD (defined as progression in ≤5 lesions) between January 2014 and December 2022. Progression patterns were identified. Times from local therapy to progression, next therapy, and death were measured.</p><p><strong>Results: </strong>The median duration of osimertinib treatment before XRT was 16.9 months. After XRT, time on osimertinib was extended for a median of 9.7 months, with a median progression-free survival (PFS) and overall survival of 6.9 and 24.4 months, respectively. Post-XRT recurrence was most common in the lung (43%), viscera (35%), and bone (35%), with only 15% of patients experiencing in-field recurrence. Patients receiving XRT to lymph nodes or visceral metastases exhibited shorter PFS compared with other sites. <i>EGFR</i> mutation type, concurrent <i>TP53</i>/<i>RB1</i> mutations, and mechanisms of resistance did not significantly predict outcomes.</p><p><strong>Conclusion: </strong>The addition of XRT for OPD led to clinically meaningful time on continued osimertinib beyond progression, irrespective of molecular characteristics or resistance mechanisms.</p>","PeriodicalId":14797,"journal":{"name":"JCO precision oncology","volume":"9 ","pages":"e2500047"},"PeriodicalIF":5.3,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088374/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144077717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synthetic Lethal Co-Mutations in DNA Damage Response Pathways Predict Response to Immunotherapy in Pan-Cancer.","authors":"Lincheng Zhang, Yue Wang, Rong Qiao, Yao Zhang, Huiping Qiang, Huawei Du, Fengcai Wen, Miao Liu, Yan Zhou, Wei Nie, Hua Zhong","doi":"10.1200/PO-25-00035","DOIUrl":"https://doi.org/10.1200/PO-25-00035","url":null,"abstract":"<p><strong>Purpose: </strong>Despite the significance of immune checkpoint inhibitors (ICIs) in solid tumor treatment, identifying ICI-sensitive populations remains a challenge. Mutations in DNA damage response (DDR) pathway genes are increasingly linked to favorable ICI responses; however, selection criteria for specific DDR pathway biomarkers remain elusive.</p><p><strong>Methods: </strong>Data of patients with cancer who received ICIs and non-ICI therapy were extracted from public databases. Synthetic lethal (SL) gene combinations were selected from the SynLethDB database. Kaplan-Meier analysis was conducted to investigate the correlation between SL gene co-mutations in DDR pathways and prognosis. Immune infiltration analysis was performed using the Timer online tool based on DNA and RNA sequences obtained from The Cancer Genome Atlas database.</p><p><strong>Results: </strong>Patients with synthetic lethal co-mutations in DDR pathways exhibited significantly extended overall survival (HRhazard ratio [HR], 0.76 [95% CI, 0.62 to 0.92]; <i>P</i> = .0061), progression-free survival (HR, 0.33 [95% CI, 0.18 to 0.60]; <i>P</i> = .0003), and higher objective response rates (66.7% <i>v</i> 21.0%; <i>P</i> = .0009) after receiving ICIs. Conversely, DDR SL co-mut⁺ patients receiving non-ICI treatment presented with markedly shortened survival (HR, 1.35 [95% CI, 1.16 to 1.56]; <i>P</i> < .0001). High-frequency DDR SL co-mutation pairs were enriched in the checkpoint factor pathway. <i>TP53-ATM</i> emerged as a common combination, with <i>TP53-ATM</i> co-mut⁺ patients receiving more survival benefits from ICI (HR, 0.63 [95% CI, 0.41 to 0.99]; <i>P</i> = .045). Immune infiltration analysis demonstrated altered immune reactivity in <i>TP53-ATM</i> co-mut⁺ tumors, with higher levels of CD4⁺ T cells, plasma cells, macrophages, natural killer cells, and myeloid dendritic cells but lower levels of CD8⁺ T cells.</p><p><strong>Conclusion: </strong>Our study identified SL co-mutations in the DDR pathway as promising biomarkers for ICI efficacy. Specifically, the <i>TP53-ATM</i> co-mutation status can be applied in identifying ICI-responsive patients. SL co-mutations in DDR pathways correlate with modification of the tumor immune microenvironment, shaping a favorable niche for ICIs to stimulate immune responses.</p>","PeriodicalId":14797,"journal":{"name":"JCO precision oncology","volume":"9 ","pages":"e2500035"},"PeriodicalIF":5.3,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144180297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association of Polygenic-Based Breast Cancer Risk Prediction With Patient Management.","authors":"Katherine Johansen Taber, Elisha Hughes, Alexander Gutin, W Brady DeHart, Laura Becker, Jeffery Jasper, Sarah Ratzel, D Claire Miller, Devika Chawla, Pamela Morin, Julia Certa, Allison W Kurian","doi":"10.1200/PO-24-00716","DOIUrl":"https://doi.org/10.1200/PO-24-00716","url":null,"abstract":"<p><strong>Purpose: </strong>Breast cancer (BC) risk prediction is more accurate when clinical and polygenic factors are combined (combined risk score [CRS]), but little is known about how CRS results affect real-world patient management.</p><p><strong>Methods: </strong>Deidentified medical and pharmacy claims data were linked with Tyrer-Cuzick (TC) and CRS results and evaluated for BC risk management. Patients were divided into subcohorts on the basis of lifetime risk predicted by CRS and by TC (\"+\": ≥20% risk, \"-\": <20%): CRS+ TC+, CRS+ TC-, CRS- TC+, and CRS- TC-. Claims data related to screening mammography (SM) in patients younger than 40 years, breast magnetic resonance imaging (MRI), and genetic counseling (GC) were compared 360 days before and after CRS testing. Differences in pre- and post-CRS management were evaluated using McNemar tests, and post-CRS management of subcohorts was compared using multivariable logistic regression.</p><p><strong>Results: </strong>After CRS testing, the CRS+ TC+, CRS+ TC-, and CRS- TC+ subcohorts had 1.6-2.2-fold increases in SM in patients younger than 40 years (all <i>P</i> < .02) and 4.7-5.6-fold increases in breast MRI (all <i>P</i> < .001). The CRS+ TC+ and CRS+ TC- subcohorts had 1.9-2.3-fold increases in GC (both <i>P</i> < .001). SM in those younger than 40 years, breast MRI, and GC did not increase in the CRS- TC- subcohort. After CRS testing, compared with the CRS- TC- subcohort, the CRS+ TC+, CRS+ TC-, and CRS- TC+ subcohorts had significantly higher odds of receiving SM before age 40 years (odds ratio [OR], 3.80-5.19), breast MRI (OR, 11.55-23.09), and GC (OR, 2.03-2.91; all <i>P</i> < .001).</p><p><strong>Conclusion: </strong>Patients with ≥20% lifetime risk predicted by either CRS or TC were more likely to receive enhanced management compared with those who had <20% lifetime risk, suggesting that clinicians considered the CRS in BC risk management.</p>","PeriodicalId":14797,"journal":{"name":"JCO precision oncology","volume":"9 ","pages":"e2400716"},"PeriodicalIF":5.3,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12068550/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144024438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Annotation-Free Whole-Slide Image Analysis Method to Assess Immune Infiltration in Colorectal Cancer.","authors":"Yao Xu, Shangqing Yang, Yaxi Zhu, Su Yao, Lin Wu, Shenyan Zhang, Yiting Wang, Suyun Li, Yunrui Ye, Zhenhui Li, Zaiyi Liu, Ke Zhao","doi":"10.1200/PO-24-00791","DOIUrl":"https://doi.org/10.1200/PO-24-00791","url":null,"abstract":"<p><strong>Purpose: </strong>Tumor-infiltrating lymphocytes (TILs) play a crucial role in host antitumor processes. High level of TILs is associated with better outcomes for patients. We aim to automatically quantify TILs without any nuclei annotation and further construct an immune score to predict the survival of patients with colorectal cancer.</p><p><strong>Patients and methods: </strong>We developed an artificial intelligence-based pipeline to quantify the level of TILs in hematoxylin-eosin (H&E) images with immunohistochemistry (IHC)-guided nuclei annotation-free auxiliary labels. Patients enrolled in the study were divided into two cohorts (development cohort: n = 557; validation cohort: n = 439). The proposed tumor stroma immune score (TSI score) reflects the immune infiltration in the tumor stroma of patients.</p><p><strong>Results: </strong>A strong correlation of TILs was observed between IHC and H&E images made by consecutive sections staining. Moreover, multivariate analysis confirmed that TSI score was an independent prognostic factor, and the higher TSI score was associated with the better prognosis (development cohort: hazard ratio for high <i>v</i> low 0.54 [95% CI, 0.42 to 0.80], <i>P</i> = .001; validation cohort: 0.68 [95% CI, 0.27 to 0.94], <i>P</i> = .031). The model with TSI score showed a higher C-index (development cohort: 0.700 <i>v</i> 0.679; validation cohort: 0.689 <i>v</i> 0.677).</p><p><strong>Conclusion: </strong>IHC images have the value of providing TIL density reference information for spatial corresponding H&E images. TSI score has the ability to predict overall survival.</p>","PeriodicalId":14797,"journal":{"name":"JCO precision oncology","volume":"9 ","pages":"e2400791"},"PeriodicalIF":5.3,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143991129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"<i>TP53</i> Mutations and Phosphatidylinositol 3-Kinase/AKT Pathway Alterations Are Key Determinants of Breast Cancer Outcome Independent of Subtype and Stage.","authors":"Tibor A Zwimpfer, Martin Heidinger, Ricardo Coelho, Nadja Stiegeler, Fabienne D Schwab, Céline Montavon, Ruth S Eller, Nadia Maggi, Julie M Loesch, Marcus Vetter, Matteo Lambertini, Walter P Weber, Christian Kurzeder, Viola Heinzelmann-Schwarz","doi":"10.1200/PO-24-00767","DOIUrl":"https://doi.org/10.1200/PO-24-00767","url":null,"abstract":"<p><strong>Purpose: </strong>Breast cancer (BC) is a heterogeneous disease with genetic alterations influencing prognosis and treatment response. <i>TP53</i> mutations (<i>TP53</i>muts) are present in approximately 30% of BC, but their prognostic impact remains controversial. In addition, the phosphatidylinositol 3-kinase (PI3K)/Ak strain transforming (AKT) pathway is frequently altered and represents a promising therapeutic target for BC. Understanding the combined prognostic impact of <i>TP53</i>mut and PI3K/AKT pathway alterations across BC subtypes remains underexplored.</p><p><strong>Methods: </strong>This retrospective cohort study integrated clinical and genomic data from 4,265 patients with BC from the Molecular Taxonomy of Breast Cancer International Consortium (n = 2,509) and the Memorial Sloan Kettering Cancer Center (n = 1,756). Genetic profiling identified <i>TP53</i>mut and PI3K/AKT pathway alterations (<i>AKT1</i>, <i>AKT2</i>, <i>AKT3</i>, <i>PIK3CA</i>, <i>PTEN</i>, <i>RICTOR</i>). Survival outcomes were assessed using Kaplan-Meier survival analysis and multivariable Cox proportional hazards models.</p><p><strong>Results: </strong>In 3,807 patients with available gene alteration status, <i>TP53</i>mut was associated with younger age, higher tumor grade, advanced stage, and aggressive subtypes (<i>P</i> < .001). <i>TP53</i>mut was associated with worse survival independent of subtype, stage, age, and grade (hazard ratio [HR], 1.43 [95% CI, 1.24 to 1.66]; <i>P</i> < .0001). The type of <i>TP53</i>mut has also been found to be prognostic in BC. PI3K/AKT pathway alterations were more frequent in <i>TP53</i>mut tumors and independently associated with worse survival (HR, 1.18 [95% CI, 1.03 to 1.35]; <i>P</i> = .0173). The combined presence of <i>TP53</i>mut and PI3K/AKT alterations resulted in the worst survival outcomes (HR, 1.61 [95% CI, 1.32 to 1.97]; <i>P</i> < .0001).</p><p><strong>Conclusion: </strong><i>TP53</i>mut status is a critical prognostic factor in BC, independent of subtypes and stage, and its adverse impact is amplified by PI3K/AKT pathway alterations. These findings emphasize the integration of genetic profiling into routine clinical practice to refine treatment strategies and identify potential therapeutic targets for this high-risk population.</p>","PeriodicalId":14797,"journal":{"name":"JCO precision oncology","volume":"9 ","pages":"e2400767"},"PeriodicalIF":5.3,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Training, Validating, and Testing Machine Learning Prediction Models for Endometrial Cancer Recurrence.","authors":"Jesus Gonzalez Bosquet, Andrew Polio, Erin George, Ahmad A Tarhini, Casey M Cosgrove, Marilyn S Huang, Bradley Corr, Aliza L Leiser, Bodour Salhia, Kathleen Darcy, Christopher M Tarney, Rob L Dood, Lauren E Dockery, Stephen B Edge, Michael J Cavnar, Lisa Landrum, Rob J Rounbehler, Michelle Churchman, Vincent M Wagner","doi":"10.1200/PO-24-00859","DOIUrl":"https://doi.org/10.1200/PO-24-00859","url":null,"abstract":"<p><strong>Purpose: </strong>Endometrial cancer (EC) is the most common gynecologic cancer in the United States with rising incidence and mortality. Despite optimal treatment, 15%-20% of all patients will recur. To better select patients for adjuvant therapy, it is important to accurately predict patients at risk for recurrence. Our objective was to train, validate, and test models of EC recurrence using lasso regression and other machine learning (ML) and deep learning (DL) analytics in a large, comprehensive data set.</p><p><strong>Methods: </strong>Data from patients with EC were downloaded from the Oncology Research Information Exchange Network database and stratified into low risk, The International Federation of Gynecology and Obstetrics (FIGO) grade 1 and 2, stage I (N = 329); high risk, or FIGO grade 3 or stages II, III, IV (N = 324); and nonendometrioid histology (N = 239) groups. Clinical, pathologic, genomic, and genetic data were used for the analysis. Genomic data included microRNA, long noncoding RNA, isoforms, and pseudogene expressions. Genetic variation included single-nucleotide variation (SNV) and copy-number variation (CNV). In the discovery phase, we selected variables informative for recurrence (<i>P</i> < .05), using univariate analyses of variance. Then, we trained, validated, and tested multivariate models using selected variables and lasso regression, MATLAB (ML), and TensorFlow (DL).</p><p><strong>Results: </strong>Recurrence clinic models for low-risk, high-risk, and high-risk nonendometrioid histology had AUCs of 56%, 70%, and 65%, respectively. For training, we selected models with AUC >80%: five for the low-risk group, 20 models for the high-risk group, and 20 for the nonendometrioid group. The two best low-risk models included clinical data and CNVs. For the high-risk group, three of the five best-performing models included pseudogene expression. For the nonendometrioid group, pseudogene expression and SNV were overrepresented in the best models.</p><p><strong>Conclusion: </strong>Prediction models of EC recurrence built with ML and DL analytics had better performance than models with clinical and pathologic data alone. Prospective validation is required to determine clinical utility.</p>","PeriodicalId":14797,"journal":{"name":"JCO precision oncology","volume":"9 ","pages":"e2400859"},"PeriodicalIF":5.3,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12054588/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143965111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Factors Affecting Genomic Testing in Prostate Cancer: Results From the Decision-Making, Experience, and Confidence In Determining Genomic Evaluation (DECIDE) Survey.","authors":"Rhonda L Bitting, Christopher McNair, Alexander W Wyatt, Gillian Vandekerkhove, Taehwa Choi, Amy E Leader, Joshua Blanding-Godbolt, Laura Gross, Khaldoun Hamade, Susan Halabi, Veda N Giri","doi":"10.1200/PO-24-00821","DOIUrl":"https://doi.org/10.1200/PO-24-00821","url":null,"abstract":"<p><strong>Purpose: </strong>Genomic testing for prostate cancer (PCa) clinical management and hereditary cancer assessment has grown in clinical impact; however, challenges remain regarding optimal implementation and end-user confidence. The Decision-making, Experience, and Confidence In Determining Genomic Evaluation (DECIDE) survey was designed to collect information regarding utility and understanding of genomic testing from PCa health care providers, researchers, and stakeholders.</p><p><strong>Methods: </strong>The DECIDE survey was administered online from October 2022 to January 2023 with 18 multiple-response questions. Survey domains included self-confidence with ordering and interpreting germline and somatic genomic tests, process of testing and use of results, decision-making factors, and barriers to testing. Data were summarized by evaluating counts and percentages of responses, and the results were presented by descriptive statistics.</p><p><strong>Results: </strong>One hundred twenty-two participants completed the survey. The majority were medical oncologists (70%) and at academic medical centers (89%). Self-confidence was high in knowing indications for genomic testing (82% respondents) but lower in interpretation of results, especially from circulating tumor DNA (52%). Confidence varied in interpreting pathogenic variants (65% high confidence), variants of unknown significance (47%), and incidental findings from genomic tests (35%). Common barriers to testing were difficulty obtaining tissue (71%) and cost (35%). Testing utility was sometimes limited by inability to obtain the recommended treatment (33%). Most of the respondents (55%) agreed that lack of education and training of health care professionals regarding genomic testing is impeding clinical translation.</p><p><strong>Conclusion: </strong>The DECIDE survey provided critical insights into challenges with genomic testing, from provider confidence in interpretating results to testing and practice barriers. The results inform next steps to further educate PCa providers and to collectively improve testing and result reporting for enhanced implementation of PCa genomic testing.</p>","PeriodicalId":14797,"journal":{"name":"JCO precision oncology","volume":"9 ","pages":"e2400821"},"PeriodicalIF":5.3,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144078191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}