IBM's Health Analytics and Clinical Decision Support.

OBJECTIVES: This survey explores the role of big data and health analytics developed by IBM in supporting the transformation of healthcare by augmenting evidence-based decision-making. METHODS: Some problems in healthcare and strategies for change are described. It is argued that change requires better decisions, which, in turn, require better use of the many kinds of healthcare information. Analytic resources that address each of the information challenges are described. Examples of the role of each of the resources are given. RESULTS: There are powerful analytic tools that utilize the various kinds of big data in healthcare to help clinicians make more personalized, evidenced-based decisions. Such resources can extract relevant information and provide insights that clinicians can use to make evidence-supported decisions. There are early suggestions that these resources have clinical value. As with all analytic tools, they are limited by the amount and quality of data. CONCLUSION: Big data is an inevitable part of the future of healthcare. There is a compelling need to manage and use big data to make better decisions to support the transformation of healthcare to the personalized, evidence-supported model of the future. Cognitive computing resources are necessary to manage the challenges in employing big data in healthcare. Such tools have been and are being developed. The analytic resources, themselves, do not drive, but support healthcare transformation.

The acute asthmatic patient in the ED: to admit or discharge.

Treating asthma in the emergency department (ED) always involves the potentially difficult decision as to whether to discharge the patient, to continue treatment, or to admit to the hospital. The following are useful guidelines. (1) The duration of the bronchospasm, frequency of visits, history of previous endotracheal intubation, pulse rate, and accessory muscle use are findings affecting successful discharge from the ED. (2) Patients with peak expiratory flow rate (PEFR) of < 20% and who do not respond to inhalant therapy, with PEFR values persisting at < 40% of predicted, will require 4 or more days to resolve and should be admitted to the hospital. (3) Patients with a PEFR between 40% and 70% of predicted after initial inhalant therapy may well be responsive to steroids in the ED, but an ED will adequately need to care for the patient for 5 to 12 hours while waiting for the onset of action of glucocorticoids. Discharged with glucocorticoids, this group has a 6% relapse rate within 10 days of the ED visit. (4) Patients with a PEFR of > or = 70% have a 14% relapse rate after discharge without glucocorticoids. Other reasons to consider admission are pneumonia, barotrauma, lability, prominent psychiatric difficulties, poor access to medications, poor educability, fear of steroids, patients on glucocorticoids or those who have recently stopped glucocorticoids, and evening discharges of patients from the ED, which all predispose to relapses of acute asthma. To decrease the relapse rate, provocative factors should be reviewed with the patient, as well as access to medication and use of spacers, inhaler techniques, PEFR meters, self-management plans, and referral to a defined appointment at 24 to 48 hours of the ED visit.

In vitro quantitation of canine left ventricular volume by phased-array sector scan.

Ultrasonic sector-scan images can delineate the entire circumference of the canine left ventricle in vitro. This study was undertaken to (1) assess the accuracy of sector scanning for estimating canine left ventricular volume in vitro compared to volume estimates by M-mode echo in the same hearts and (2) determine the optimal techniques for estimating left ventricular volume with sector scanning. 16 volumes (1 volume from 8 hearts and 2 volumes from 4 hearts) were estimated by obtaining sector-scan images from orthogonal long-axis, short-axis and apical views. The sector-scan volumes were calculated by single and biplane area-length methods, as well as biplane Simpson's rule methods, and compared to measured left ventricular volumes. M-mode echo volumes were calculated by cubing the mid-ventricular minor-axis diameter. Sector-scan views containing a long-axis dimension plus the short-axis dimension of the left ventricle had a high correlation with true left ventricular volume while sector-scan views not containing a long-axis view showed only a fair correlation with volume. M-mode echo produced a poor estimate of the true left ventricular volume. It is concluded that (1) sector scanning can provide highly accurate in vitro volume estimates of canine left ventricles which is superior to estimates derived by M-mode echocardiographic methods and (2) the optimal sector-scan views for estimating left ventricular volume are those that make the fewest assumptions about left ventricular geometry and have the greatest amount of dimensional information.