Utility of Routine Surveillance Laboratory Testing in Detecting Relapse in Patients With Classic Hodgkin Lymphoma in First Remission: Results From a Large Single-Institution Study.
JCO oncology practice
Automated model versus treating physician for predicting survival time of patients with metastatic cancer.
Journal of the American Medical Informatics Association : JAMIA
PURPOSE: Classic Hodgkin lymphoma is highly curable with contemporary therapy. Although the limited role of surveillance imaging to detect early relapse for patients in complete remission at the end of therapy is well established, there is a paucity of data regarding role of laboratory testing in this setting.METHODS: Patients with newly diagnosed classic Hodgkin lymphoma uniformly treated with the Stanford V regimen from 1998-2014 and in complete remission for at least 3 months were identified in a single-center institutional database. Laboratory tests categorized by Common Terminology Criteria for Adverse Events v4.03 as grade 2 or higher were considered abnormal. Primary analysis included sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of surveillance laboratory tests for predicting relapse in the first 3 years after end of treatment.RESULTS: Among 235 eligible patients, 24 (10.2%) patients ultimately relapsed. In the first 3 years after end of therapy, the mean number of surveillance blood draws per patient was 7.1, (range, 1-13). These 1,661 surveillance blood draws included 4,684 individual laboratory tests, comprising 1,609 CBCs, 1,578 metabolic panels, and 1,497 erythrocyte sedimentation rates. None of the biopsies confirming relapses were prompted by any abnormal laboratory finding. The sensitivity of any surveillance laboratory test for detecting relapse within 3 years of end of treatment was 72.7% (95% CI, 49.8% to 89.3%), specificity 22.6% (95% CI, 17.2% to 28.9%), yielding a PPV of 8.9% (95% CI, 7.0% to 11.3%) and NPV of 88.9% (95% CI, 79% to 94%).CONCLUSION: Our study found limited clinically meaningful utility for routine surveillance laboratory testing in detecting relapse in patients with complete remission at end of treatment. Our results warrant consideration of modifications to current practice guidelines.
View details for DOI 10.1200/JOP.19.00733
View details for PubMedID 32369413
Changes in Cancer Management due to COVID-19 Illness in Patients with Cancer in Northern California.
JCO oncology practice
Being able to predict a patient's life expectancy can help doctors and patients prioritize treatments and supportive care. For predicting life expectancy, physicians have been shown to outperform traditional models that use only a few predictor variables. It is possible that a machine learning model that uses many predictor variables and diverse data sources from the electronic medical record can improve on physicians' performance. For patients with metastatic cancer, we compared accuracy of life expectancy predictions by the treating physician, a machine learning model, and a traditional model.A machine learning model was trained using 14 600 metastatic cancer patients' data to predict each patient's distribution of survival time. Data sources included note text, laboratory values, and vital signs. From 2015-2016, 899 patients receiving radiotherapy for metastatic cancer were enrolled in a study in which their radiation oncologist estimated life expectancy. Survival predictions were also made by the machine learning model and a traditional model using only performance status. Performance was assessed with area under the curve for 1-year survival and calibration plots.The radiotherapy study included 1190 treatment courses in 899 patients. A total of 879 treatment courses in 685 patients were included in this analysis. Median overall survival was 11.7 months. Physicians, machine learning model, and traditional model had area under the curve for 1-year survival of 0.72 (95% CI 0.63-0.81), 0.77 (0.73-0.81), and 0.68 (0.65-0.71), respectively.The machine learning model's predictions were more accurate than those of the treating physician or a traditional model.
View details for DOI 10.1093/jamia/ocaa290
View details for PubMedID 33313792
Automated Survival Prediction in Metastatic Cancer Patients Using High-Dimensional Electronic Medical Record Data
JNCI-JOURNAL OF THE NATIONAL CANCER INSTITUTE
2019; 111 (6): 568–74
Natural Disease History, Outcomes, and Co-mutations in a Series of Patients With BRAF-Mutated Non-small-cell Lung Cancer
CLINICAL LUNG CANCER
2019; 20 (2): E208–E217
Dynamin impacts homology-directed repair and breast cancer response to chemotherapy
JOURNAL OF CLINICAL INVESTIGATION
2018; 128 (12): 5307–21
Natural Disease History, Outcomes, and Co-mutations in a Series of Patients With BRAF-Mutated Non-small-cell Lung Cancer.
Clinical lung cancer
The response to the COVID-19 pandemic has affected the management of patients with cancer. In this pooled retrospective analysis, we describe changes in management patterns for patients with cancer diagnosed with COVID-19 in two academic institutions in the San Francisco Bay Area.Adult and pediatric patients diagnosed with COVID-19 with a current or historical diagnosis of malignancy were identified from the electronic medical record at the University of California, San Francisco, and Stanford University. The proportion of patients undergoing active cancer management whose care was affected was quantified and analyzed for significant differences with regard to management type, treatment intent, and the time of COVID-19 diagnosis. The duration and characteristics of such changes were compared across subgroups.A total of 131 patients were included, of whom 55 were undergoing active cancer management. Of these, 35 of 55 (64%) had significant changes in management that consisted primarily of delays. An additional three patients not undergoing active cancer management experienced a delay in management after being diagnosed with COVID-19. The decision to change management was correlated with the time of COVID-19 diagnosis, with more delays identified in patients treated with palliative intent earlier in the course of the pandemic (March/April 2020) compared with later (May/June 2020) (OR, 4.2; 95% CI, 1.03 to 17.3; P = .0497). This difference was not seen among patients treated with curative intent during the same timeframe.We found significant changes in the management of cancer patients with COVID-19 treated with curative and palliative intent that evolved over time. Future studies are needed to determine the impact of changes in management and treatment on cancer outcomes for patients with cancer and COVID-19.
View details for DOI 10.1200/OP.20.00790
View details for PubMedID 33332170
Automated Survival Prediction in Metastatic Cancer Patients Using High-Dimensional Electronic Medical Record Data.
Journal of the National Cancer Institute
BACKGROUND: BRAF mutations occur in 1% to 4% of non-small-cell lung cancer (NSCLC) cases. Previous retrospective studies have reported similar outcomes for BRAF-mutated NSCLC as compared with wild-type tumors without a known driver mutation or tumors harboring other mutations. However, select cases of prolonged survival have also been described, and thus, the natural history of BRAF-mutated NSCLC remains an area of ongoing study. The aim of this series was to describe the natural history, clinical outcomes, and occurrence of co-mutations in patients with BRAF-mutated NSCLC.PATIENTS AND METHODS: Patients with BRAF-mutated NSCLC seen at Stanford University Medical Center from January 1, 2006 through July 31, 2015 were reviewed. The Kaplan-Meier method was used to calculate median overall survival, and the generalized Wilcoxon test was used to compare median survivals across subgroups of patients.RESULTS: Within a cohort of 18 patients with BRAF-mutated NSCLC, V600E mutations were most common (72%; 13/18). Clinicopathologic features were similar between patients with V600E versus non-V600E mutations, although there was a trend toward more patients with non-V600E mutations being heavy smokers (80% vs. 31%; P= .12). Co-occurring mutations in TP53 were identified most commonly (28%; 5/18). The median overall survival for the entire cohort was 40.1 months, and the median survival from the onset of metastases (n= 16) was 28.1 months. Survival rates at 2 and 5 years from the onset of metastases were 56% and 13%, respectively.CONCLUSION: The clinical behavior of BRAF-mutated NSCLC is variable, but favorable outcomes can be seen in a subset of patients.
View details for PubMedID 30442523
Probabilistic Prognostic Estimates of Survival in Metastatic Cancer Patients (PPES-Met) Utilizing Free-Text Clinical Narratives.
2018; 8 (1): 10037
Background: Oncologists use patients' life expectancy to guide decisions and may benefit from a tool that accurately predicts prognosis. Existing prognostic models generally use only a few predictor variables. We used an electronic medical record dataset to train a prognostic model for patients with metastatic cancer.Methods: The model was trained and tested using 12588 patients treated for metastatic cancer in the Stanford Health Care system from 2008 to 2017. Data sources included provider note text, labs, vital signs, procedures, medication orders, and diagnosis codes. Patients were divided randomly into a training set used to fit the model coefficients and a test set used to evaluate model performance (80%/20% split). A regularized Cox model with 4126 predictor variables was used. A landmarking approach was used due to the multiple observations per patient, with t0 set to the time of metastatic cancer diagnosis. Performance was also evaluated using 399 palliative radiation courses in test set patients.Results: The C-index for overall survival was 0.786 in the test set (averaged across landmark times). For palliative radiation courses, the C-index was 0.745 (95% confidence interval [CI] = 0.715 to 0.775) compared with 0.635 (95% CI = 0.601 to 0.669) for a published model using performance status, primary tumor site, and treated site (two-sided P<.001). Our model's predictions were well-calibrated.Conclusions: The model showed high predictive performance, which will need to be validated using external data. Because it is fully automated, the model can be used to examine providers' practice patterns and could be deployed in a decision support tool to help improve quality of care.
View details for PubMedID 30346554
Probabilistic Prognostic Estimates of Survival in Metastatic Cancer Patients (PPES-Met) Utilizing Free-Text Clinical Narratives
Dynamin impacts homology-directed repair and breast cancer response to chemotherapy.
The Journal of clinical investigation
We propose a deep learning model - Probabilistic Prognostic Estimates of Survival in Metastatic Cancer Patients (PPES-Met) for estimating short-term life expectancy (>3 months) of the patients by analyzing free-text clinical notes in the electronic medical record, while maintaining the temporal visit sequence. In a single framework, we integrated semantic data mapping and neural embedding technique to produce a text processing method that extracts relevant information from heterogeneous types of clinical notes in an unsupervised manner, and we designed a recurrent neural network to model the temporal dependency of the patient visits. The model was trained on a large dataset (10,293 patients) and validated on a separated dataset (1818 patients). Our method achieved an area under the ROC curve (AUC) of 0.89. To provide explain-ability, we developed an interactive graphical tool that may improve physician understanding of the basis for the model's predictions. The high accuracy and explain-ability of the PPES-Met model may enable our model to be used as a decision support tool to personalize metastatic cancer treatment and provide valuable assistance to the physicians.
View details for PubMedID 29968730
Chart Review Versus an Automated Bioinformatic Approach to Assess Real-World Crizotinib Effectiveness in Anaplastic Lymphoma Kinase–Positive Non–Small-Cell Lung Cancer
JCO: Clinical Cancer Informatics
Third party assessment of resection margin status in head and neck cancer
2016; 57: 27-31
After the initial responsiveness of triple-negative breast cancers (TNBCs) to chemotherapy, they often recur as chemotherapy-resistant tumors, and this has been associated with upregulated homology-directed repair (HDR). Thus, inhibitors of HDR could be a useful adjunct to chemotherapy treatment of these cancers. We performed a high-throughput chemical screen for inhibitors of HDR from which we obtained a number of hits that disrupted microtubule dynamics. We postulated that high levels of the target molecules of our screen in tumors would correlate with poor chemotherapy response. We found that inhibition or knockdown of dynamin 2 (DNM2), known for its role in endocytic cell trafficking and microtubule dynamics, impaired HDR and improved response to chemotherapy of cells and of tumors in mice. In a retrospective analysis, levels of DNM2 at the time of treatment strongly predicted chemotherapy outcome for estrogen receptor-negative and especially for TNBC patients. We propose that DNM2-associated DNA repair enzyme trafficking is important for HDR efficiency and is a powerful predictor of sensitivity to breast cancer chemotherapy and an important target for therapy.
View details for PubMedID 30371505
Increased Risk of Cutaneous Squamous Cell Carcinoma After Vismodegib Therapy for Basal Cell Carcinoma
2016; 152 (5): 527-532
Definitive assessment of primary site margin status following resection of head and neck cancer is necessary for prognostication, treatment determination and qualification for clinical trials. This retrospective analysis determined how often an independent reviewer can assess primary tumor margin status of head and neck cancer resections based on review of the pathology report, surgical operative report, and first follow-up note alone.We extracted from the electronic medical record pathology reports, operative reports, and follow-up notes from head and neck cancer resections performed at Stanford Hospital. We classified margin status as definitive or not. We labeled any pathology report clearly indicating a positive, negative, or close (<5mm) margin as definitive. For each non-definitive pathology report, we reviewed the operative report and then the first follow-up note in an attempt to clarify margin status. We also looked for associations between non-definitive status and surgeon, year, and primary site.743 unique cases of head and neck cancer resection were extracted. We discarded 255 as non-head and neck cancer cases, or cases that did not involve a definitive resection of a primary tumor site. We could not definitively establish margin status in 20% of resections by independent review of the medical record. There was no correlation between margin determination and surgeon, site, or year of surgery.A substantial fraction (20%) of primary site surgical margins could not be definitively determined via independent EMR review. This could have implications for subsequent patient care decisions and clinical trial options.
View details for DOI 10.1016/j.oraloncology.2016.03.009
View details for Web of Science ID 000376084500010
View details for PubMedID 27208841
New models and online calculator for predicting non-sentinel lymph node status in sentinel lymph node positive breast cancer patients
Smoothened inhibitors (SIs) are a new type of targeted therapy for advanced basal cell carcinoma (BCC), and their long-term effects, such as increased risk of subsequent malignancy, are still being explored.To evaluate the risk of developing a non-BCC malignancy after SI exposure in patients with BCC.A case-control study at Stanford Medical Center, an academic hospital. Participants were higher-risk patients with BCC diagnosed from January 1, 1998, to December 31, 2014. The dates of the analysis were January 1 to November 1, 2015.The exposed participants (cases) comprised patients who had confirmed prior vismodegib treatment, and the nonexposed participants (controls) comprised patients who had never received any SI. Because vismodegib was the first approved SI, only patients exposed to this SI were included.Hazard ratio for non-BCC malignancies after vismodegib exposure, adjusting for covariates.The study cohort comprised 180 participants. Their mean (SD) age at BCC diagnosis was 56 (16) years, and 68.9% (n = 124) were male. Fifty-five cases were compared with 125 controls, accounting for age, sex, prior radiation therapy or cisplatin treatment, Charlson Comorbidity Index, clinical follow-up time, immunosuppression, and basal cell nevus syndrome status. Patients exposed to vismodegib had a hazard ratio of 6.37 (95% CI, 3.39-11.96; P < .001), indicating increased risk of developing a non-BCC malignancy. Most non-BCC malignancies were cutaneous squamous cell carcinomas, with a hazard ratio of 8.12 (95% CI, 3.89-16.97; P < .001), accounting for age and basal cell nevus syndrome status. There was no significant increase in other cancers.Increased risk for cutaneous squamous cell carcinomas after vismodegib therapy highlights the importance of continued skin surveillance after initiation of this therapy.
View details for DOI 10.1001/jamadermatol.2015.4330
View details for PubMedID 26914338
Current practice is to perform a completion axillary lymph node dissection (ALND) for breast cancer patients with tumor-involved sentinel lymph nodes (SLNs), although fewer than half will have non-sentinel node (NSLN) metastasis. Our goal was to develop new models to quantify the risk of NSLN metastasis in SLN-positive patients and to compare predictive capabilities to another widely used model.We constructed three models to predict NSLN status: recursive partitioning with receiver operating characteristic curves (RP-ROC), boosted Classification and Regression Trees (CART), and multivariate logistic regression (MLR) informed by CART. Data were compiled from a multicenter Northern California and Oregon database of 784 patients who prospectively underwent SLN biopsy and completion ALND. We compared the predictive abilities of our best model and the Memorial Sloan-Kettering Breast Cancer Nomogram (Nomogram) in our dataset and an independent dataset from Northwestern University.285 patients had positive SLNs, of which 213 had known angiolymphatic invasion status and 171 had complete pathologic data including hormone receptor status. 264 (93%) patients had limited SLN disease (micrometastasis, 70%, or isolated tumor cells, 23%). 101 (35%) of all SLN-positive patients had tumor-involved NSLNs. Three variables (tumor size, angiolymphatic invasion, and SLN metastasis size) predicted risk in all our models. RP-ROC and boosted CART stratified patients into four risk levels. MLR informed by CART was most accurate. Using two composite predictors calculated from three variables, MLR informed by CART was more accurate than the Nomogram computed using eight predictors. In our dataset, area under ROC curve (AUC) was 0.83/0.85 for MLR (n = 213/n = 171) and 0.77 for Nomogram (n = 171). When applied to an independent dataset (n = 77), AUC was 0.74 for our model and 0.62 for Nomogram. The composite predictors in our model were the product of angiolymphatic invasion and size of SLN metastasis, and the product of tumor size and square of SLN metastasis size.We present a new model developed from a community-based SLN database that uses only three rather than eight variables to achieve higher accuracy than the Nomogram for predicting NSLN status in two different datasets.
View details for DOI 10.1186/1471-2407-8-66
View details for PubMedID 18315887