April S. Liang

Importance: Current methods for identifying hospitalized patients at increased risk of delirium require nurse-administered questionnaires with moderate accuracy. Objective: To develop and validate a machine learning model that predicts incident delirium risk based on electronic health data available on admission. Design, Setting, and Participants: Retrospective cohort study evaluating 5 machine learning algorithms to predict delirium using 796 clinical variables identified by an expert panel as relevant to delirium prediction and consistently available in electronic health records within 24 hours of admission. The training set comprised 14 227 adult patients with non-intensive care unit hospital stays and no delirium on admission who were discharged between January 1, 2016, and August 31, 2017, from UCSF Health, a large academic health institution. The test set comprised 3996 patients with hospital stays who were discharged between August 1, 2017, and November 30, 2017. Exposures: Patient demographic characteristics, diagnoses, nursing records, laboratory results, and medications available in electronic health records during hospitalization. Main Outcomes and Measures: Delirium was defined as a positive Nursing Delirium Screening Scale or Confusion Assessment Method for the Intensive Care Unit score. Models were assessed using the area under the receiver operating characteristic curve (AUC) and compared against the 4-point scoring system AWOL (age >79 years, failure to spell world backward, disorientation to place, and higher nurse-rated illness severity), a validated delirium risk-assessment tool routinely administered in this cohort. Results: The training set included 14 227 patients (5113 [35.9%] aged >64 years; 7335 [51.6%] female; 687 [4.8%] with delirium), and the test set included 3996 patients (1491 [37.3%] aged >64 years; 1966 [49.2%] female; 191 [4.8%] with delirium). In total, the analysis included 18 223 hospital admissions (6604 [36.2%] aged >64 years; 9301 [51.0%] female; 878 [4.8%] with delirium). The AWOL system achieved a baseline AUC of 0.678. The gradient boosting machine model performed best, with an AUC of 0.855. Setting specificity at 90%, the model had a 59.7% (95% CI, 52.4%-66.7%) sensitivity, 23.1% (95% CI, 20.5%-25.9%) positive predictive value, 97.8% (95% CI, 97.4%-98.1%) negative predictive value, and a number needed to screen of 4.8. Penalized logistic regression and random forest models also performed well, with AUCs of 0.854 and 0.848, respectively. Conclusions and Relevance: Machine learning can be used to estimate hospital-acquired delirium risk using electronic health record data available within 24 hours of hospital admission. Such a model may allow more precise targeting of delirium prevention resources without increasing the burden on health care professionals.

BACKGROUND: Chromatin organization is central to precise control of gene expression. In various eukaryotic species, domains of pervasive cis-chromatin interactions demarcate functional domains of the genomes. In nematode Caenorhabditis elegans, however, pervasive chromatin contact domains are limited to the dosage-compensated sex chromosome, leaving the principle of C. elegans chromatin organization unclear. Transcription factor III C (TFIIIC) is a basal transcription factor complex for RNA polymerase III, and is implicated in chromatin organization. TFIIIC binding without RNA polymerase III co-occupancy, referred to as extra-TFIIIC binding, has been implicated in insulating active and inactive chromatin domains in yeasts, flies, and mammalian cells. Whether extra-TFIIIC sites are present and contribute to chromatin organization in C. elegans remains unknown. RESULTS: We identified 504 TFIIIC-bound sites absent of RNA polymerase III and TATA-binding protein co-occupancy characteristic of extra-TFIIIC sites in C. elegans embryos. Extra-TFIIIC sites constituted half of all identified TFIIIC binding sites in the genome. Extra-TFIIIC sites formed dense clusters in cis. The clusters of extra-TFIIIC sites were highly over-represented within the distal arm domains of the autosomes that presented a high level of heterochromatin-associated histone H3K9 trimethylation (H3K9me3). Furthermore, extra-TFIIIC clusters were embedded in the lamina-associated domains. Despite the heterochromatin environment of extra-TFIIIC sites, the individual clusters of extra-TFIIIC sites were devoid of and resided near the individual H3K9me3-marked regions. CONCLUSION: Clusters of extra-TFIIIC sites were pervasive in the arm domains of C. elegans autosomes, near the outer boundaries of H3K9me3-marked regions. Given the reported activity of extra-TFIIIC sites in heterochromatin insulation in yeasts, our observation raised the possibility that TFIIIC may also demarcate heterochromatin in C. elegans.

e13035 Background: The goal of the WISDOM study (Women Informed to Screen Depending on Measures of risk) is to examine the effectiveness of a personalized approach to breast cancer screening and to bring clarity and objective recommendations to the current debate regarding mammography screening frequency. The WISDOM study, funded by PCORI, is a randomized trial with a preference-tolerant design that aims to determine if risk-based (RBS), vs. annual screening, is as safe, less morbid, enables prevention and is preferred by women. A pilot was conducted to test the logistics and examine the acceptance of the study. Methods: Women were recruited from the UCSF site of the Athena Breast Health Network, a clinical care-research cohort including 100,000 women from the 5 UC Medical Centers and Sanford Health. We recruited women 40 -74 years of age that had no history of breast cancer and had a normal mammogram in the past year. The Breast Cancer Surveillance Consortium model (standard risk factors, ethnicity, breast density and SNP risk alleles) in addition to gene panel testing was used to calculate breast cancer risks to inform the start and frequency of screening. Results: An online electronic enrollment process, e-Consent and patient engagement portal was successfully implemented. To date, 623 women were invited, 220 registered, and 159 have completed intake. 72% chose to be randomized, and 28% chose to self-assign, of whom 70% chose annual screening. Mean age of pilot participants was 56 years old. The ethnic breakdown of the cohort is: 80% White, 10% Asian, 4% Latino, 3% Black, and 3% other. 30% of participants identify as having Jewish ancestry. Initial patient interviews reveal overall enthusiasm for the study and provide ongoing feedback to improve the study materials. The pilot will conclude April 2016 when the full trial is launched. Additional data on distribution of personal risk estimates, and exit survey data evaluating uptake of screening recommendations will be presented. Conclusions: Our pilot reveals that the majority of women are willing to be randomized to answer the important question on optimal breast cancer screening. This pilot study is designed to inform the implementation of the 100,000 women WISDOM Study. Clinical trial information: NCT02620852.