Sutter Health

About: Sutter Health is a healthcare organization based out in Sacramento, California, United States. It is known for research contribution in the topics: Health care & Population. The organization has 310 authors who have published 418 publications receiving 13732 citations.

Lumpectomy plus Tamoxifen with or without Irradiation in Women 70 Years of Age or Older with Early Breast Cancer

Abstract: BACKGROUND In women 70 years of age or older who have early breast cancer, it is unclear whether lumpectomy plus tamoxifen is as effective as lumpectomy followed by tamoxifen plus radiation therapy. METHODS Between July 1994 and February 1999, we randomly assigned 636 women who were 70 years of age or older and who had clinical stage I (T1N0M0 according to the tumor-node-metastasis classification), estrogen-receptor-positive breast carcinoma treated by lumpectomy to receive tamoxifen plus radiation therapy (317 women) or tamoxifen alone (319 women). Primary end points were the time to local or regional recurrence, the frequency of mastectomy for recurrence, breast-cancer-specific survival, the time to distant metastasis, and overall survival. RESULTS The only significant difference between the two groups was in the rate of local or regional recurrence at five years (1 percent in the group given tamoxifen plus irradiation and 4 percent in the group given tamoxifen alone, P<0.001). There were no significant differences between the two groups with regard to the rates of mastectomy for local recurrence, distant metastases, or five-year rates of overall survival (87 percent in the group given tamoxifen plus irradiation and 86 percent in the tamoxifen group, P=0.94). Assessment by physicians and patients of cosmetic results and adverse events uniformly rated tamoxifen plus irradiation inferior to tamoxifen alone. CONCLUSIONS Lumpectomy plus adjuvant therapy with tamoxifen alone is a realistic choice for the treatment of women 70 years of age or older who have early, estrogen-receptor-positive breast cancer.

Caring for Critically Ill Patients with the ABCDEF Bundle: Results of the ICU Liberation Collaborative in Over 15,000 Adults.

Abstract: Objective:Decades-old, common ICU practices including deep sedation, immobilization, and limited family access are being challenged. We endeavoured to evaluate the relationship between ABCDEF bundle performance and patient-centered outcomes in critical care.Design:Prospective, multicenter, cohort st

RETAIN: An interpretable predictive model for healthcare using reverse time attention mechanism

Abstract: Accuracy and interpretability are two dominant features of successful predictive models. Typically, a choice must be made in favor of complex black box models such as recurrent neural networks (RNN) for accuracy versus less accurate but more interpretable traditional models such as logistic regression. This tradeoff poses challenges in medicine where both accuracy and interpretability are important. We addressed this challenge by developing the REverse Time AttentIoN model (RETAIN) for application to Electronic Health Records (EHR) data. RETAIN achieves high accuracy while remaining clinically interpretable and is based on a two-level neural attention model that detects influential past visits and significant clinical variables within those visits (e.g. key diagnoses). RETAIN mimics physician practice by attending the EHR data in a reverse time order so that recent clinical visits are likely to receive higher attention. RETAIN was tested on a large health system EHR dataset with 14 million visits completed by 263K patients over an 8 year period and demonstrated predictive accuracy and computational scalability comparable to state-of-the-art methods such as RNN, and ease of interpretability comparable to traditional models.

GRAM: Graph-based Attention Model for Healthcare Representation Learning

Abstract: Deep learning methods exhibit promising performance for predictive modeling in healthcare, but two important challenges remain: - Data insufficiency: Often in healthcare predictive modeling, the sample size is insufficient for deep learning methods to achieve satisfactory results. Interpretation: The representations learned by deep learning methods should align with medical knowledge. To address these challenges, we propose GRaph-based Attention Model (GRAM) that supplements electronic health records (EHR) with hierarchical information inherent to medical ontologies. Based on the data volume and the ontology structure, GRAM represents a medical concept as a combination of its ancestors in the ontology via an attention mechanism. We compared predictive performance (i.e. accuracy, data needs, interpretability) of GRAM to various methods including the recurrent neural network (RNN) in two sequential diagnoses prediction tasks and one heart failure prediction task. Compared to the basic RNN, GRAM achieved 10% higher accuracy for predicting diseases rarely observed in the training data and 3% improved area under the ROC curve for predicting heart failure using an order of magnitude less training data. Additionally, unlike other methods, the medical concept representations learned by GRAM are well aligned with the medical ontology. Finally, GRAM exhibits intuitive attention behaviors by adaptively generalizing to higher level concepts when facing data insufficiency at the lower level concepts.