Creating a Real Return-on-Investment for Information System Implementation: Life After HITECH

Lai, Manda; Kheterpal, Sachin

doi:10.1016/j.anclin.2011.05.005

Cited by 6 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning classifiers have already been successfully applied to many prediction problems, including crime prevention, handwriting recognition, fraud detection, and email spam filtering . Furthermore, the recent focus on the adoption and meaningful use of electronic medical records (EMR) has led to massive clinical datasets comprising variables collected by healthcare providers during the course of a patient's hospitalization . Machine learning approaches have the potential to leverage this clinical “Big Data” to create more accurate and automated predictions of postoperative pain.…”

Section: Introductionmentioning

confidence: 99%

Teaching a Machine to Feel Postoperative Pain: Combining High-Dimensional Clinical Data with Machine Learning Algorithms to Forecast Acute Postoperative Pain

Tighe

Harle²,

Hurley

et al. 2015

Pain Med

View full text Add to dashboard Cite

Background Given their ability to process highly dimensional datasets with hundreds of variables, machine learning algorithms may offer one solution to the vexing challenge of predicting postoperative pain. Methods Here, we report on the application of machine learning algorithms to predict postoperative pain outcomes in a retrospective cohort of 8071 surgical patients using 796 clinical variables. Five algorithms were compared in terms of their ability to forecast moderate to severe postoperative pain: Least Absolute Shrinkage and Selection Operator (LASSO), gradient-boosted decision tree, support vector machine, neural network, and k-nearest neighbor, with logistic regression included for baseline comparison. Results In forecasting moderate to severe postoperative pain for postoperative day (POD) 1, the LASSO algorithm, using all 796 variables, had the highest accuracy with an area under the receiver-operating curve (ROC) of 0.704. Next, the gradient-boosted decision tree had an ROC of 0.665 and the k-nearest neighbor algorithm had an ROC of 0.643. For POD 3, the LASSO algorithm, using all variables, again had the highest accuracy, with an ROC of 0.727. Logistic regression had a lower ROC of 0.5 for predicting pain outcomes on POD 1 and 3. Conclusions Machine learning algorithms, when combined with complex and heterogeneous data from electronic medical record systems, can forecast acute postoperative pain outcomes with accuracies similar to methods that rely only on variables specifically collected for pain outcome prediction.

show abstract

Section: Introductionmentioning

confidence: 99%

Teaching a Machine to Feel Postoperative Pain: Combining High-Dimensional Clinical Data with Machine Learning Algorithms to Forecast Acute Postoperative Pain

Tighe

Harle²,

Hurley

et al. 2015

Pain Med

View full text Add to dashboard Cite

show abstract

Implementation of an Anesthesia Information Management System in an Ambulatory Surgery Center

Mudumbai

2015

J Med Syst

View full text Add to dashboard Cite

Anesthesia information management systems (AIMS) are increasingly being implemented throughout the United States. However, little information exists on the implementation process for AIMS within ambulatory surgery centers (ASC). The objectives of this descriptive study are to document: 1) the phases of implementation of an AIMS at an ASC; and 2) lessons learnt from a socio-technical perspective. The ASC, within the Veterans Health Administration (VHA), has hosted an AIMS since 2008. As a quality improvement effort, we implemented a new version of the AIMS. This new version involved fundamental software changes to enhance clinical care such as real-time importing of laboratory data and total hardware exchange. The pre-implementation phase involved coordinated preparation over six months between multiple informatics teams along with local leadership. During this time, we conducted component, integration, and validation testing to ensure correct data flow from medical devices to AIMS and centralized databases. The implementation phase occurred in September 2014 over three days and was successful. Over the next several months, during post-implementation phase, we addressed residual items like latency of the application. Important lessons learnt from the implementation included the utility of partnering early with executive leadership; ensuring end user acceptance of new clinical workflow; continuous testing of data flow; use of a staged rollout; and providing additional personnel throughout implementation. Implementation of an AIMS at an ASC can utilize methods developed for large hospitals. However, issues unique to an ASC such as limited number of support personnel and distinctive workflows must be considered.

show abstract

“Meaningful Use” – The New Buzzword in Medicine

Winters-Miner¹,

Bolding²,

Hilbe³

et al. 2015

Practical Predictive Analytics and Decisioning Systems for Medicine

View full text Add to dashboard Cite

Creating a Real Return-on-Investment for Information System Implementation: Life After HITECH

Cited by 6 publications

References 2 publications

Teaching a Machine to Feel Postoperative Pain: Combining High-Dimensional Clinical Data with Machine Learning Algorithms to Forecast Acute Postoperative Pain

Teaching a Machine to Feel Postoperative Pain: Combining High-Dimensional Clinical Data with Machine Learning Algorithms to Forecast Acute Postoperative Pain

Implementation of an Anesthesia Information Management System in an Ambulatory Surgery Center

“Meaningful Use” – The New Buzzword in Medicine

Contact Info

Product

Resources

About