Citations

Abstract Introduction: An Our Practice Advisory (OPA), formerly known as Best Practice Advisory (BPA), is an electronic health record (EHR) tool. OPAs identify key parameters to alert providers of potential interventions that could enhance quality of care. Such functionality is increasingly relevant given the rapid pace of new drug approvals. Within the Mayo Clinic system, we previously identified that amongst Mayo Clinic patients (pts) meeting the MonarchE criteria, 28% of pts did not undergo a documented discussion with their provider regarding the role of adjuvant abemaciclib (Premji, SABCS 2024). Further, a Flatiron study identified that only 40% of eligible pts received abemaciclib (Sandoval, Miami Breast 2025). To address this practice gap, in 2024 we began to implement EHR clinical decision support by creating an OPA trigger for pts eligible for an adjuvant CDK 4/6 inhibitor (CDK 4/6i). Here we report on ‘action taken’ versus not for the OPA and the most common reasons for re-prompts. Methods: The Mayo Breast Disease Group designed an OPA including pts who are within 14 months of a clinical or pathologic diagnosis of high-risk early-stage breast cancer. We leveraged structured data captured in the Epic staging forms (Epic Systems) to identify pts with clinical or pathologic T-stage, N-stage, grade, ± Ki-67/ multigene signature to identify ER+/HER2- pts eligible for adjuvant ribociclib or abemaciclib based on FDA approvals. The OPA was triggered by a patient encounter in oncology when endocrine therapy (but not CDK4/6i) was on the active medication list resulting in a hard stop. The OPA gathered limited details about whether adjuvant CDK4/6 inhibitors were discussed and whether the provider followed a link that resulted in prescribing one—considered an indicator of action taken. In this IRB-exempt quality improvement project, we describe the responses captured in the OPA trigger utilizing Epic tools. Results: The OPA went live on 1/10/2025. Over a 5-month period post OPA initiation, we identified 517 OPA alerts among 332 unique pts. Their median age was 62.5 years, and the majority were female (97%). The median time to resolve the OPA was 17.5 seconds (range 2-567 seconds). 12.6% (65/517) of the time there was ‘action taken’ by selecting the hyperlink to potentially start a treatment plan. Providers selected the following OPA pre-set responses: ‘re-prompt in one month’ 248 (48%), ‘patient not a candidate for therapy’ 48 (9%), ‘patient declines’ 69 (13%), ‘outside oncologist will prescribe’ 36 (7%), ‘not discussed’ 44 (9%), and unknown 72 (14%). The most common free text comments among the 517 OPA alerts (summarized) included: ‘revisit in future’ 108 (21%), ‘too early’ 65 (13%), ‘patient declines’ 66 (13%), ‘outside oncologist will start’ 31 (6%), ‘not a candidate’ 26 (5%), and ‘co-morbidities’ 18 (3%). Erroneous OPA prompting occurred in 14 (3%) who previously failed a CDK4/6i due to toxicity and in 18 (3%) for pts currently on a CDK4/6i. 30 (6%) OPA comments noted that they discussed or started therapy that day. Conclusion: The OPA offered clinical decision support and ensured that clinicians considered prescribing CDK 4/6i in all pts identified as eligible, and captured deferrals. Refinements are needed to ensure appropriate timing of OPA and minimize erroneous firing. The OPA remains active and captures the reason for deferral of adjuvant CDK 4/6i prescription. This data pairs real world decision making to better understand clinically meaningful application of improved invasive disease-free survival (iDFS). Citation Format: S. Premji, P. Advani, S. Chumsri, L. Mina, J. Taraba, J. Carroll, J. Hoppenworth, E. Cathcart-Rake, T. Haddad, B. Rudder, G. Choong, D. Idossa, C. O’Sullivan, S. Yadav, K. Ruddy, P. Peethambaram, T. Hobday, M. Goetz, R. Rao, B. Ernst, F. Batalini, R. Leon-Ferre, A. Tevaarwerk, K. Giridhar. Implementing an Our Practice Advisory (OPA) to provide clinical decision support for adjuvant CDK4/6 inhibitors in early-stage hormone receptor positive breast cancer: The Mayo Clinic Experience [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS5-11-10.

Abstract Background: Clinical benefit with PARP inhibitors (PARPi) has been demonstrated in patients (pts) with HER2-negative (HER2−) metastatic breast cancer (mBC) and germline or tumor mutations in BRCA1 or BRCA2 (g/tBRCAm). Understanding real-world PARPi use and its impact on clinical outcomes may improve the treatment of pts with BRCAm HER2− mBC. Methods: This retrospective study captured data from US pts aged ≥18 years diagnosed with HER2− mBC from January 12, 2018, to March 31, 2024, in the deidentified electronic health record-derived Flatiron Health Research Database. PARPi use and outcomes were described by tumor subtype (hormone receptor-positive [HR+]/HER2− mBC or triple-negative mBC [mTNBC]), g/tBRCA status, disease stage at diagnosis (de novo or recurrent), line of therapy (LoT), and prior treatments. Real-world overall survival (rwOS) by PARPi use was estimated using the Kaplan-Meier method. Results: Of 848 pts with gBRCAm mBC, 352 (42%) received PARPi (Table), with consistent PARPi initiation rates of 42%-48% from 2018-2022. PARPi was initiated in 223/566 (39%) pts with gBRCAm HR+/HER2− mBC, 125/275 (45%) pts with gBRCAm mTNBC, and 4/7 (57%) pts with unknown tumor subtype. Among 304 pts with gBRCAm who had received ≥3 LoT by the end of follow-up, 93/225 (41%) pts with HR+/HER2− mBC and 18/78 (23%) pts with mTNBC received PARPi in the third LoT or later (3L+); 50/103 (49%) pts with de novo mBC and 54/184 (29%) pts with recurrent mBC received PARPi in 3L+. PARPi was also initiated in 13/231 (6%) pts with gBRCA variants of uncertain significance (VUS) and 176/662 (27%) pts with tBRCAm and non-gBRCAm/unknown gBRCAm status. Among 539/1573 (34%) pts with g/tBRCAm who received PARPi, 167 had not received prior chemotherapy in any setting; 40 of these pts (39 with HR+/HER2− mBC and 1 with mTNBC) received PARPi in 3L+. With a median follow-up of 17.0 months from initiation of 1L therapy, median rwOS was numerically longer among pts with gBRCAm who received PARPi versus pts who did not (HR+/HER2− mBC: 39.3 months [95% CI: 35.5-46.8], n=208 vs 24.2 months [95% CI: 21.4-33.0], n=259; mTNBC: 27.6 months [95% CI: 18.0-41.7], n=119 vs 16.9 months [95% CI: 14.5-31.9], n=81). Among pts with tBRCAm who were negative for gBRCAm, median rwOS was numerically longer in pts who received PARPi versus pts who did not. Conclusions: Pts with HR+/HER2− mBC had slightly lower rates of PARPi use, and received PARPi later, than pts with mTNBC. Although improved efficacy with PARPi use in earlier LoT has been demonstrated, many pts first received PARPi in 3L+, suggesting unmet potential to ensure timely testing and optimize treatment. Although immortal time bias and other factors should be considered, rwOS was numerically longer in pts with BRCAm HR+/HER2− mBC and with BRCAm mTNBC who initiated PARPi versus pts who did not. Further research into PARPi use and survival trends in pts with BRCAm and/or other actionable biomarkers in mBC is needed. Citation Format: S. Yadav, Q. Li, Z. Tan, K. E. Mishkin, J. F. Hayes, X. Xu, F. J. Couch. Real-world PARP inhibitor use and clinical outcomes in US patients with HER2-negative metastatic breast cancer [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS2-02-08.

Abstract Introduction: Women with a germline pathogenic variant (PV) in PALB2 face a lifetime risk of breast cancer, generally exceeding 40%. We have initiated an international clinical follow up study of women with stage 0 to stage 4 breast cancer and a PALB2 PV to evaluate clinical characteristics and to determine optimal treatments. The objective of the current study was to estimate and to identify factors predictive of contralateral breast cancer (CBC) risk. Methods: Clinical data, including diagnostic, treatment, and follow-up data, were collected by medical record review for eligible women with breast cancer and a germline PV in PALB2. PV carriers were followed every two years to collect information about recurrences, new cancers, and vital status. Data was summarized using descriptive statistics. The risk of CBC was estimated by following women from the date of breast cancer diagnosis until the date of: 1) contralateral breast cancer, 2) contralateral mastectomy, 3) death from any cause, or 4) last follow-up. The cumulative incidence of CBC was calculated with the Kaplan-Meier method. Cox proportional hazards regression was used to identify factors associated with contralateral breast cancer risk. Covariates included age at diagnosis, ER status, grade, nodal status, chemotherapy, radiation therapy, tamoxifen, and bilateral salpingo-oophorectomy (time-dependent). Results: Among 888 PALB2 carriers, the mean age at diagnosis of breast cancer was 49.3 years (range 22 to 83 years). Overall, 36 women (4.1%) were diagnosed with synchronous bilateral breast cancer. 73.6% of the breast cancers were ER-positive, and 29% were lymph node-positive. Patients were followed for a mean of 5.6 years (range 0.3 to 22 years) from date of diagnosis. During the follow-up period, 53 patients were diagnosed with a metachronous CBC. The 15-year risk of metachronous CBC was 26.4% overall; 19.5% for those diagnosed younger than 50 years, and 34.8% for those diagnosed at 50 years or older. In a multivariate analysis, ER status was not significantly associated with CBC risk (RR 1.15, 95%CI 0.45-2.93, p=0.77). Bilateral salpingo-oophorectomy (BSO) was associated with a significant reduction in the risk of CBC (RR 0.17, 95%CI 0.04-0.70, p=0.02). In the follow-up period, 47 women were diagnosed with another incident cancer, including seven with pancreatic cancer and three with ovarian cancer Conclusion: The high 15-year risk of contralateral breast cancer suggests that bilateral mastectomy should be considered for primary surgical intervention. Moreover, bilateral salpingo-oophorectomy (BSO) significantly reduces the risk of CBC and should be considered post-treatment. Citation Format: K. Metcalfe, A. Stachowski, F. Couch, M. Marabelli, S. Wong, S. Domchek, A. Aeilts, A. Eisen, R. Kim, T. Ramon y Cajal, R. Fruscio, S. Yadav, C. Hoey, S. Karamali, P. Sun, J. Lubinski, S. Narod, T. Pal. Contralateral Breast Cancer Risk in Women with PALB2-Associated Breast Cancer [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PD4-11.

Abstract Background: International guidelines recommend that all patients (pts) with metastatic breast cancer (mBC) are offered testing for germline BRCA1/BRCA2 mutations (gBRCAm) and other biomarkers to aid treatment decisions. This retrospective study describes real-world testing patterns for germline/tumor (g/t)BRCAm and other biomarkers among US pts with HER2-negative [HER2−] mBC. Methods: Data were captured from US pts aged ≥18 years with HER2− mBC from January 12, 2018, to March 31, 2024, in the deidentified, electronic health record-derived Flatiron Health Research Database. Demographics, clinical characteristics, and testing patterns for g/tBRCAm and other actionable biomarkers were examined. Testing rates, test timing, and biomarker status were described across subgroups defined by demographics (including age, race, and ethnicity), tumor subtype (hormone receptor-positive [HR+]/HER2− mBC or triple-negative mBC [mTNBC]), and disease stage at mBC diagnosis (recurrent/de novo). Results: The BRCA testing rate among pts with mBC increased from 2018 (48%) to 2023 (62%); the overall testing rate was 19,820/34,379 (58%): 5880 pts (17%) received a gBRCA test only, 7285 (21%) received a tBRCA test only, and 6655 (19%) received both gBRCA and tBRCA tests. BRCA testing rates were numerically lower in pts with HR+/HER2− mBC (56%) versus mTNBC (68%), and in pts aged >65 years (HR+/HER2− mBC, 48%; mTNBC, 62%) versus ≤65 years (HR+/HER2− mBC, 64%; mTNBC, 74%; Table). The proportion of pts who received a test before initiation of first-line (1L) therapy was lower among pts with HR+/HER2− mBC than with mTNBC (recurrent, 60% vs 81%; de novo, 37% vs 57%). Among tested pts, 1067/15,168 (7%) with HR+/HER2− mBC and 494/4539 (11%) with mTNBC had a positive result for g/tBRCAm; 365/1067 (34%) pts with g/tBRCAm HR+/HER2− mBC and 138/494 (28%) pts with g/tBRCAm mTNBC were aged >65 years. Among 528 pts with gBRCAm HR+/HER2− mBC, co-mutations in PIK3CA, ESR1, PTEN, and AKT1 were identified in 48 (9%), 38 (7%), 20 (4%), and 3 (<1%) pts, respectively. Among pts diagnosed with gBRCAm HR+/HER2− mBC in 2020-2023 (median follow-up: 15 months), 175/371 (47%) did not receive a test for PIK3CA mutations at any time, and 48/97 (49%) pts diagnosed in 2023 (median follow-up: 6 months) did not receive a test for ESR1 mutations. In 2021-2023, 72/256 (28%) pts with g/tBRCAm mTNBC had tumors with programmed cell death-ligand 1 (PD-L1) combined positive score ≥10; 88 (34%) pts did not receive a PD-L1 test. Conclusions: Although BRCA testing rates increased from 2018 to 2023, 38% of US pts diagnosed with HER2− mBC in 2023 did not receive any BRCA test. BRCA testing rates were low among pts with HR+/HER2− mBC and/or aged >65 years, suggesting that many g/tBRCAm remained undetected. Wider and timelier testing for germline and tumor biomarkers is warranted to identify pts who are eligible for targeted therapies. Citation Format: S. Yadav, Q. Li, Z. Tan, K. E. Mishkin, J. F. Hayes, X. Xu, F. J. Couch. Real-world biomarker testing patterns in US patients with HER2-negative metastatic breast cancer [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PD4-08.

Abstract Background: BRCA2 variants with partially aberrant RNA splicing have been associated with a relatively lower breast cancer risk (reduced penetrance) relative to canonical pathogenic variants. However, the existence of partial loss of function (hypomorphic) missense variants, conferring reduced penetrance, is less certain. Identification and assessment of the clinical relevance of such reduced penetrance pathogenic variants (RPPVs) is needed to provide accurate risk estimates. Methods: Comprehensive functional characterization of hypomorphic missense variants (n=70) in the BRCA2 DNA-binding domain, initially identified through homology-directed DNA repair (HDR) assays, was conducted through multiple independent functional assays, including HDR, CRISPR/Cas9-based endogenous targeting, RAD51 foci formation assay, and Poly(ADP-ribose) polymerase (PARP) inhibitor response assay. Risk estimates were obtained using two large datasets from patients referred for hereditary cancer testing. A ClinGen/ACMG/AMP model was used for clinical classification. Results: The variants consistently demonstrated hypomorphic HDR activity and endogenous survival in HAP1 targeted cells, decreased RAD51 foci formation, and increased sensitivity to PARP inhibitors. These variants were associated with a moderate increase in breast cancer risk, as shown in two independent studies: one using multivariable logistic analysis adjusted for age, ancestry and family history (OR=2.41, 95%CI=1.51-3.85) and another comparing frequencies of variants in breast cancer cases to public reference controls adjusted for ancestry (OR=2.09, 95% CI=1.16-4.08). The mean age of breast cancer diagnosis for carriers of hypomorphic variants was 57 years, which was significantly older than the mean age of diagnosis of 51 years for carriers of protein truncating variants. Functional data were combined with other evidence sources in a ClinGen/ACMG/AMP model to classify 14 variants as “likely pathogenic”. Conclusions: We identified partially functional, hypomorphic missense variants associated with reduced penetrance for breast cancer. Cancer risk management guidelines for this new category of variants should be revisited given that the associated breast cancer risks warrant high risk screening but do not meet the threshold at which risk reducing mastectomy is offered. This study supports a shift in paradigm to considering variant-based risks on a continuum, with implications for risk-appropriate cancer risk management. Citation Format: H. Huang, C. Hu, J. Na, M. Kucera, T. Simmons, E. Mundt, C. C. Young, Z. Heidari, P. C. Lyra, Y. Y. Tan, K. L. Nathanson, T. Pal, R. Karam, T. Pesaran, S. Yadav, S. M. Domchek, A. N. Monteiro, E. Hughes, N. Boddicker, W. Chen, M. E. Richardson, F. J. Couch. Partially functional (hypomorphic) missense variants in BRCA2 are reduced penetrance pathogenic variants [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PD4-05.

Abstract Background: Incorporation of Polygenic Risk Scores (PRS) can refine traditional breast cancer (BC) risk assessment models to provide precise estimates of BC risk. However, the impact of such an integrated model on BC risk estimates and clinical decision-making related to BC screening and preventive strategies in germline pathogenic variant (PV) carriers is not fully understood. Methods: The GENRE-2 is a prospective single-arm multisite clinical trial (NCT04474834) incorporating 313-PRS into standard BC risk assessment models to determine the impact of PRS on risk estimates and clinical decisions on prevention and screening. All women received pre- and post-PRS BC risk estimates and completed surveys on their screening and cancer prevention decisions before and after integrating PRS estimates. Herein, we report on the impact of integrating PRS into CanRisk-based BC risk estimates among women enrolled in GENRE-2 due to PVs in ATM, BRCA1, BRCA2, CHEK2, or PALB2. Women were categorized into average risk (<20%), moderate risk (20-40%), or high risk (>40%) for BC based on clinically relevant lifetime risk thresholds for supplemental MRI screening and risk-reducing bilateral mastectomies. Changes in categories of lifetime BC risk estimates were then evaluated before and after integration of PRS. Impact of PRS on patient decisions to undertake screening or preventive action (medication or prophylactic mastectomy) was evaluated based on pre- and post-PRS surveys. Results: Between 2020 and 2025, 933 women were enrolled, 633 received PRS results and completed a survey to date. Of those who received PRS results, 214 (33.8%) were PV carriers (ATM: 24, BRCA1: 54, BRCA2: 73, CHEK2: 54 and PALB2: 9). Among PV carriers, the CanRisk-based median 10-year and lifetime pre-PRS risk estimates were 6.0% and 23.9% for ATM, 22.5% and 77.5% for BRCA1, 17.9% and 77.6% for BRCA2, 7.1% and 26.6% for CHEK2, and 16.6% and 42.4% for PALB2, respectively. A total of 7 (29.2%) ATM PV carriers had a shift in lifetime BC risk categories after integration of PRS, with 1 (4.2%) shifting from average to moderate-risk, 3 (12.5%) shifting from moderate to average-risk category, and 3 (12.5%) shifting from moderate to high-risk category. Among CHEK2 PV carriers, 9 (16.7%) had a shift in lifetime risk categories, with 4 (7.4%) shifting from moderate to average-risk, 2 (3.7%) shifting from moderate to high-risk, and 3 (5.6%) shifting from high to moderate-risk. None of the BRCA1 and 4.1% of BRCA2 PV carriers had a shift in lifetime risk categories after PRS integration. Only 1 (11.1%) PALB2 PV carrier had a change in lifetime risk category after integration of PRS, although this was limited by a small sample. A significantly higher proportion of PV carriers with a high lifetime risk intended to take preventative action compared to the PV carriers with average lifetime risk (41.4% vs. 20.0%, p=0.007). Conclusions: Integration of PRS into BC lifetime risk estimates led to a clinically meaningful change in risk categories in 29.2% of ATM PV carriers and 16.7% of CHEK2 PV carriers, but in <5% of BRCA1 or BRCA2 PV carriers. These findings suggest that PRS may be helpful for BC risk stratification in moderate-risk genes such as ATM and CHEK2 but may have limited clinical utility in high-risk genes such as BRCA1 or BRCA2. Citation Format: S. Yadav, C. Klassen, D. Stan, J. Fraker, S. Sahni, S. A. Khan, L. Khatri, C. Vachon, D. Schaid, J. P. Sinnwell, E. Carlson, L. Hasadsri, F. J. Couch, S. Pruthi. Impact of Polygenic Risk Scores on Breast Cancer Risk Assessment and Clinical Decision Making in Carriers of Germline Pathogenic Variants in ATM, BRCA1, BRCA2, CHEK2, and PALB2: Results from the Prospective Multisite GENRE-2 Clinical Trial [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PD4-04.

ABSTRACT Background Ventricular tachycardia (VT) is a life‐threatening arrhythmia that requires both relatively rapid and accurate detection in intensive care units (ICUs). Continuous monitoring systems play a crucial role in detecting them. However, previous studies have reported that nearly 9 out of 10 arrhythmia alarms in ICUs tend to be false positives, which usually transpire to a well‐documented phenomenon called “alarm fatigue” that leads to desensitization, delayed responses, and increased cognitive burden on healthcare providers. Methods We developed a deep learning based, one‐dimensional convolutional neural network (1D‐CNN) to classify VT alarms using multiple raw waveform inputs, including two electrocardiogram (ECG) leads, photoplethysmogram (PPG) and arterial blood pressure (ABP) signals. The model was trained using the publicly available VTaC Arrhythmia Benchmark Dataset. We used the 10‐second waveform segments that preceded each VT alarm, pre‐processed and then used them to train the machine learning model to correctly classify the VT alarm. Results On the test set, the model achieved an area under the receiver operating characteristic curve of 0.901, overall accuracy of 83.22%, F1‐score of 73.3%, sensitivity of 77.53%, specificity of 85.63%, and positive predictive value of 69.57%. The model successfully detected over three‐quarters of them while significantly reducing false positive rates for the detection of VT. Conclusions This study demonstrates that a deep learning based 1D‐CNN model using short segments of raw waveform data can achieve robust performance in distinguishing true and false VT alarms.

Objectives: Smoking is a key risk factor for pancreatitis, contributing to pathogenesis and disease progression. Data regarding second-hand smoking, or passive smoking (PS) exposure, are lacking. We therefore aimed to assess the impact of PS exposure across the pancreatitis spectrum. Methods: We analyzed baseline data from the PROCEED study, a multicenter study in the United States including patients with acute (AP), recurrent acute (RAP), and chronic (CP) pancreatitis. Participants detailed their individual smoking history and PS exposure, which was compared between AP, RAP, and CP subgroups. Participant factors and clinical characteristics were compared by level of individual and PS exposure. Results: Among 1369 participants (190 AP, 498 RAP, 681 CP), 346 (25.3%) were current and 409 (29.9%) were former smokers. The CP subgroup had the highest proportion of current smokers (36.7% CP vs 15.1% RAP, 11.1% AP, P < 0.001). PS exposure was also significantly higher in the CP subgroup (68.6% CP vs 58.2% RAP, 55.3% AP, P < 0.001). A minority (16.3%) with CP reported no smoking exposure (by self or passive) while nearly half smoked ≥20 pack-years. The mean PS duration was significantly higher in CP participants (21.8 y) compared with those with AP (17.8 y) or RAP (18.9 y) ( P < 0.0166). Conclusions: In this multicenter study, we affirmed an association with smoking use and intensity with CP-related complications. For the first time, we report a high prevalence of prior exposure to passive smoking in all pancreatitis subtypes, which requires further study to understand the impact on disease outcomes.

Abstract Blood–Brain Barrier (BBB) is a specialized vascular structure that protects the brain by controlling what can pass from the bloodstream into the central nervous system. BBB’s highly selective nature prevents neurotoxins and foreign substances, including drugs, from entering the brain. Understanding and predicting whether a drug can cross the BBB is hence crucial in brain-related diseases. Over the past two decades, deep learning in drug discovery has witnessed an upward trend to reduce the cost, labor, and time for finding potential drugs. Majority of recent deep learning-based studies use molecular-level physiochemical properties of known drugs, which are limited and may not be sufficient to capture patterns. Here, we propose a parameter efficient Graph Convolution-based model, graphB3, which uses detailed information about the atoms in a molecule to predict the BBB permeability of drug candidates, outperforming existing methods. In addition to high predictive performance, graphB3 also offers an explanation of which parts of the molecule are most important for crossing the BBB. graphB3 can be employed to discover new BBB-permeable compounds and potential drugs. A free and easy-to-use graphB3 web server is available at https://dhanjal-lab.iiitd.edu.in/graphb3.html, and a standalone tool available at https://github.com/dhanjal-lab/graphB3.

ASCO Guidelines provide recommendations with comprehensive review and analyses of the relevant literature for each recommendation, following the guideline development process as outlined in the ASCO Guidelines Methodology Manual . ASCO Guidelines follow the ASCO Conflict of Interest Policy for Clinical Practice Guidelines . Clinical Practice Guidelines and other guidance (“Guidance”) provided by ASCO is not a comprehensive or definitive guide to treatment options. It is intended for voluntary use by clinicians and should be used in conjunction with independent professional judgment. Guidance may not be applicable to all patients, interventions, diseases or stages of diseases. Guidance is based on review and analysis of relevant literature, and is not intended as a statement of the standard of care. ASCO does not endorse third-party drugs, devices, services, or therapies and assumes no responsibility for any harm arising from or related to the use of this information. See complete disclaimer in Appendix 1 and Appendix 2 (online only) for more. PURPOSE To provide guidance on the recommended management of cancer in pregnant patients. METHODS A multidisciplinary Expert Panel convened and conducted a systematic review of the literature. RESULTS The systematic review identified 450 eligible studies. Much of the evidence consisted of observational data, case series, and case reports. RECOMMENDATIONS Management of cancer during pregnancy should be grounded in a values-based informed-consent process outlining maternal and fetal risks and anticipated benefits. Diagnostic evaluation should follow the as low as reasonably achievable (ALARA) principle, with timing of diagnostic studies individualized based on urgency of cancer detection, potential dangers of delay, and the balance of risks to both the pregnant patient and her embryo or fetus. Due to significant risk of harm to the developing embryo and/or fetus, systemic therapy should be deferred until the second trimester. Methotrexate, hormonal therapies, human epidermal growth factor receptor 2–targeted agents, vascular endothelial growth factor and poly (ADP-ribose) polymerase inhibitors, antibody-drug conjugates, and all cellular therapies are contraindicated during pregnancy, regardless of gestational age. For patients who wish to continue their pregnancy, delivery should be planned at or after 37 weeks, with the final chemotherapy dose scheduled 2-4 weeks before birth. Referral to psychosocial support services is essential to address emotional and practical challenges, reduce distress, and support shared decision making. Additional information is available at www.asco.org/survivorship-guidelines .