scholarly journals Unsupervised Discovery of Emphysema Subtypes in a Large Clinical Cohort

2016 ◽  
pp. 180-187 ◽  
Author(s):  
Polina Binder ◽  
Nematollah K. Batmanghelich ◽  
Raul San Jose Estepar ◽  
Polina Golland
Keyword(s):  
Clinical Cohort

scholarly journals Real-Time Identification of Patients Included in the CMS Bundled Payment Care Improvement (BPCI) Program

2020 ◽  
Vol 41 (S1) ◽  
pp. s367-s368
Author(s):  
Michael Korvink ◽  
John Martin ◽  
Michael Long
Keyword(s):  
Performance Evaluation ◽  
Real Time ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Care Providers ◽  
Meta Model ◽  
Bundled Payment ◽  
Clinical Cohort ◽  
Real Time Identification ◽  
Care Improvement

Background: The Bundled Payment Care Improvement Program is a CMS initiative designed to encourage greater collaboration across settings of care, especially as it relates to an initial set of targeted clinical episodes, which include sepsis and pneumonia. As with many CMS incentive programs, performance evaluation is retrospective in nature, resulting in after-the-fact changes in operational processes to improve both efficiency and quality. Although retrospective performance evaluation is informative, care providers would ideally identify a patient’s potential clinical cohort during the index stay and implement care management procedures as necessary to prevent or reduce the severity of the condition. The primary challenges for real-time identification of a patient’s clinical cohort are CMS-targeted cohorts are based on either MS-DRG (grouping of ICD-10 codes) or HCPCS coding—coding that occurs after discharge by clinical abstractors. Additionally, many informative data elements in the EHR lack standardization and no simple and reliable heuristic rules can be employed to meaningfully identify those cohorts without human review. Objective: To share the results of an ensemble statistical model to predict patient risks of sepsis and pneumonia during their hospital (ie, index) stay. Methods: The predictive model uses a combination of Bernoulli Naïve Bayes natural language processing (NLP) classifiers, to reduce text dimensionality into a single probability value, and an eXtreme Gradient Boosting (XGBoost) algorithm as a meta-model to collectively evaluate both standardized clinical elements alongside the NLP-based text probabilities. Results: Bernoulli Naïve Bayes classifiers have proven to perform well on short text strings and allow for highly explanatory unstructured or semistructured text fields (eg, reason for visit, culture results), to be used in a both comparative and generalizable way within the larger XGBoost model. Conclusions: The choice of XGBoost as the meta-model has the benefits of mitigating concerns of nonlinearity among clinical features, reducing potential of overfitting, while allowing missing values to exist within the data. Both the Bayesian classifier and meta-model were trained using a patient-level integrated dataset extracted from both a patient-billing and EHR data warehouse maintained by Premier. The data set, joined by patient admission-date, medical record number, date of birth, and hospital entity code, allows the presence of both the coded clinical cohort (derived from the MS-DRG) and the explanatory features in the EHR to exist within a single patient encounter record. The resulting model produced F1 performance scores of .65 for the sepsis population and .61 for the pneumonia population.Funding: NoneDisclosures: None

Student nurses’ unethical behavior, social media, and year of birth

2016 ◽  
Vol 23 (8) ◽  
pp. 910-918 ◽  
Author(s):  
Gloria Copeland Smith ◽  
Troy Keith Knudson
Keyword(s):  
Social Media ◽  
Nursing Students ◽  
Unethical Behavior ◽  
Ethics Education ◽  
Student Nurses ◽  
Clinical Cohort ◽  
Follow Up Study ◽  
Significant Difference ◽  
Use Of Social Media

Background: This study is the result of findings from a previous dissertation conducted by this author on Student Nurses’ Unethical Behavior, Boundaries, and Social Media. The use of social media can be detrimental to the nurse–patient relationship if used in an unethical manner. Method: A mixed method, using a quantitative approach based on research questions that explored differences in student nurses’ unethical behavior by age (millennial vs nonmillennial) and clinical cohort, the relationship of unethical behavior to the utilization of social media, and analysis on year of birth and unethical behavior. A qualitative approach was used based on a guided faculty interview and common themes of student nurses’ unethical behavior. Participants and Research Context: In total, 55 Associate Degree nursing students participated in the study; the research was conducted at Central Texas College. There were eight faculty-guided interviews. Ethical considerations: The main research instrument was an anonymous survey. All participants were assured of their right to an informed consent. All participants were informed of the right to withdraw from the study at any time. Findings: Findings indicate a significant correlation between student nurses’ unethical behavior and use of social media (p = 0.036) and a significant difference between student unethical conduct by generation (millennials vs nonmillennials (p = 0.033)) and by clinical cohort (p = 0.045). Further findings from the follow-up study on year of birth and student unethical behavior reveal a correlation coefficient of 0.384 with a significance level of 0.003. Discussion: Surprisingly, the study found that second-semester students had less unethical behavior than first-, third-, and fourth-semester students. The follow-up study found that this is because second-semester students were the oldest cohort. Conclusion: Implications for positive social change for nursing students include improved ethics education that may motivate ethical conduct throughout students’ careers nationally and globally for better understanding and promotion of ethics and behavior.

scholarly journals Cyclooxygenase-2 Expression in Bladder Cancer and Patient Prognosis: Results from a Large Clinical Cohort and Meta-Analysis

PLoS ONE ◽  
2012 ◽  
Vol 7 (9) ◽  
pp. e45025 ◽  
Author(s):  
Maciej J. Czachorowski ◽  
André F. S. Amaral ◽  
Santiago Montes-Moreno ◽  
Josep Lloreta ◽  
Alfredo Carrato ◽  
...  
Keyword(s):  
Bladder Cancer ◽  
Meta Analysis ◽  
Cyclooxygenase 2 ◽  
Clinical Cohort ◽  
Patient Prognosis

scholarly journals Virologic Response to Lopinavir-Ritonavir-Based Antiretroviral Regimens in a Multicenter International Clinical Cohort: Comparison of Genotypic Interpretation Scores

2008 ◽  
Vol 52 (11) ◽  
pp. 4050-4056 ◽  
Author(s):  
Philip Grant ◽  
Eric C. Wong ◽  
Richard Rode ◽  
Robert Shafer ◽  
Andrea De Luca ◽  
...  
Keyword(s):  
Viral Load ◽  
Multivariate Analyses ◽  
Virologic Response ◽  
Receiver Operator Characteristic ◽  
Independent Data ◽  
Data Set ◽  
Clinical Cohort ◽  
Multicenter Cohort ◽  
Mutation Score ◽  
Clinical Breakpoints

ABSTRACT Several genotypic interpretation scores have been proposed for the evaluation of susceptibility to lopinavir/ritonavir (LPV/r) but have not been compared using an independent data set. This study was a retrospective multicenter cohort of patients initiating LPV/r-based therapy. The virologic response (VR) was defined as a viral load of <500 copies/ml at week 24. The genotypic interpretation scores surveyed were the LPV mutation score, the ViroLogic score, the ATU score, the Stanford database score, and the International AIDS Society-USA mutation list. Of the 103 patients included in the analysis, 76% achieved VR at 24 weeks. For scores with clinical breakpoints defined (LPV mutation, ATU, ViroLogic, and Stanford), over 80% of the patients below the breakpoints achieved VR, while 50% or less above the breakpoints responded. Protease mutations at positions 10, 54, and 82 and at positions 54, 84, and 90 were associated with a lack of VR in the univariate and multivariate analyses, respectively. The area under the receiver-operator characteristic curves for the five genotypic interpretation scores studied ranged from 0.73 to 0.76. The study confirms that the currently available genotypic interpretation scores which are widely used by clinicians performed similarly well and can be effectively used to predict the virologic activity of LPV/r in treatment-experienced patients.

Sign in / Sign up

Export Citation Format

Share Document