Pain Information Model and Its Potential for Predictive Analytics: Applicability of a Big Data Science Framework.

PURPOSE: To describe the application of a big data science framework to develop a pain information model and to discuss the potential for its use in predictive modeling. DESIGN AND METHOD: This is an application of a cross-industry standard process for a data mining adapted framework (the Applied Healthcare Data Science Framework) to build an information model on pain management and its potential for predictive modeling. Data were derived from electronic health records and were composed of approximately 51,000 records of unique adult patients admitted to clinical and surgical units between July 2015 and June 2019. FINDINGS: The application of the Applied Healthcare Data Science Framework steps allowed the development of an information model on pain management, considering pain assessment, interventions, goals, and outcomes. The developed model has the potential to be used for predicting which patients are most likely to be discharged with self-reported pain. CONCLUSIONS: Through the application of the framework, it is possible to support health professionals' decision making on the use of data to improve the effectiveness of pain management. CLINICAL RELEVANCE: In the long term, the framework is intended to guide data science methodologies to personalize treatments, reduce costs, and improve health outcomes.

Clinical indicators to monitor patients with risk for ineffective cerebral tissue perfusion.

OBJECTIVE: Select and validate the clinical indicators to monitor patients on risk for ineffective cerebral tissue perfusion, according to the Nursing Outcomes Classification (NOC). METHODOLOGY: Validation study carried out between November 2012 and August 2013, in a Brazilian hospital. Seventeen judges nurses evaluated the clinical indicators of Nursing Outcomes, according to NOC for patients on risk for ineffective cerebral tissue perfusion. In the first stage, were selected the nursing results for the assessment of the studied diagnosis and, in the second nurses assessment the importance of the indicators of the validated results in the previous step through a five points Likert scale (1 = not important to 5 = extremely important). Were used the content validity index (CVI) that corresponds to the calculation of weighted averages of them marks awarded for each indicator, as it considered the following weights: 1=0.00, 2=0.25, 3=0.50; 4=0.75; 5=1.00. For categorization, the CVI considered as critical = ≥0.80; supplementary =≥0.50 to 0.79 and were disposed results <0.50. RESULTS: Of the 9 nursing results, only the cerebral tissue perfusion obtained a 100% consensus. The CVI of the 18 indicators of this result showed that five were validated as critical (impaired neurological reflexes, systolic blood pressure, diastolic blood pressure, reduced level of consciousness and mean arterial pressure), 12 were validated as supplementary (Agitation, Impaired cognition, Intracranial pressure, Syncope, Vomiting, Findings of cerebral angiography, Headache, Restlessness, Fever, Unexplained anxiety, listlessness and Hiccughs) and one was disposed (carotid bruit). CONCLUSIONS: The validation of information about the conditions of risk may allow early intervention to minimize the consequences of ineffective cerebral tissue perfusion.