Search

Objective: Simulating electronic health record data offers an opportunity to resolve the tension between data sharing and patient privacy. Recent techniques based on generative adversarial networks have shown promise but neglect the temporal aspect of healthcare. We introduce a generative framework for simulating the trajectory of patients' diagnoses and measures to evaluate utility and privacy., Materials and Methods: The framework simulates date-stamped diagnosis sequences based on a 2-stage process that 1) sequentially extracts temporal patterns from clinical visits and 2) generates synthetic data conditioned on the learned patterns. We designed 3 utility measures to characterize the extent to which the framework maintains feature correlations and temporal patterns in clinical events. We evaluated the framework with billing codes, represented as phenome-wide association study codes (phecodes), from over 500 000 Vanderbilt University Medical Center electronic health records. We further assessed the privacy risks based on membership inference and attribute disclosure attacks., Results: The simulated temporal sequences exhibited similar characteristics to real sequences on the utility measures. Notably, diagnosis prediction models based on real versus synthetic temporal data exhibited an average relative difference in area under the ROC curve of 1.6% with standard deviation of 3.8% for 1276 phecodes. Additionally, the relative difference in the mean occurrence age and time between visits were 4.9% and 4.2%, respectively. The privacy risks in synthetic data, with respect to the membership and attribute inference were negligible., Conclusion: This investigation indicates that temporal diagnosis code sequences can be simulated in a manner that provides utility and respects privacy., (© The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Objective: To construct and validate billing code algorithms for identifying patients with peripheral arterial disease (PAD)., Methods: We extracted all encounters and line item details including PAD-related billing codes at Mayo Clinic Rochester, Minnesota, between July 1, 1997 and June 30, 2008; 22 712 patients evaluated in the vascular laboratory were divided into training and validation sets. Multiple logistic regression analysis was used to create an integer code score from the training dataset, and this was tested in the validation set. We applied a model-based code algorithm to patients evaluated in the vascular laboratory and compared this with a simpler algorithm (presence of at least one of the ICD-9 PAD codes 440.20-440.29). We also applied both algorithms to a community-based sample (n=4420), followed by a manual review., Results: The logistic regression model performed well in both training and validation datasets (c statistic=0.91). In patients evaluated in the vascular laboratory, the model-based code algorithm provided better negative predictive value. The simpler algorithm was reasonably accurate for identification of PAD status, with lesser sensitivity and greater specificity. In the community-based sample, the sensitivity (38.7% vs 68.0%) of the simpler algorithm was much lower, whereas the specificity (92.0% vs 87.6%) was higher than the model-based algorithm., Conclusions: A model-based billing code algorithm had reasonable accuracy in identifying PAD cases from the community, and in patients referred to the non-invasive vascular laboratory. The simpler algorithm had reasonable accuracy for identification of PAD in patients referred to the vascular laboratory but was significantly less sensitive in a community-based sample.

Background: Previous studies have shown that the cost of hospitalization due to stroke is significantly associated with the length of stay, stroke severity and other clinical characteristics, as well as various socio-demographic factors. However, these studies have been rather inconsistent with regard to the influence of stroke subtypes on costs., Aims: This study was examined and compared hospital charges of in-patients with acute ischemic stroke according to the Trial of Org 10172 in Acute Stroke Treatment classification., Materials and Methods: The costs of case of 749 patients with first ever ischemic stroke who were admitted to an academic medical center between January 2006 and December 2008 were analyzed. The hospital charges were compared among the stroke subtypes using Analysis of Variance. Multiple regression analyses were further performed to test the significance of the impact of the stroke subtype after controlling for other variables., Results: The stroke subtype turned out to be a statistically significant factor influencing both the total charge and several categorized charges even after controlling for other contributing factors such as hospital length of stay and stroke severity., Conclusions: This study concludes that the stroke subtype should be included when considering in-patient medical expenses of acute ischemic stroke.

Aims: As part of the diagnosis related groups in Europe (EuroDRG) project, researchers from 11 countries (i.e. Austria, England, Estonia, Finland, France, Germany, Ireland, Netherlands, Poland, Spain, and Sweden) compared how their DRG systems deal with patients admitted to hospital for acute myocardial infarction (AMI). The study aims to assist cardiologists and national authorities to optimize their DRG systems., Methods and Results: National or regional databases were used to identify hospital cases with a primary diagnosis of AMI. Diagnosis-related group classification algorithms and indicators of resource consumption were compared for those DRGs that individually contained at least 1% of cases. Six standardized case vignettes were defined, and quasi prices according to national DRG-based hospital payment systems were ascertained. European DRG systems vary widely: they classify AMI patients according to different sets of variables into diverging numbers of DRGs (between 4 DRGs in Estonia and 16 DRGs in France). The most complex DRG is valued 11 times more resource intensive than an index case in Estonia but only 1.38 times more resource intensive than an index case in England. Comparisons of quasi prices for the case vignettes show that hypothetical payments for the index case amount to only €420 in Poland but to €7930 in Ireland., Conclusions: Large variation exists in the classification of AMI patients across Europe. Cardiologists and national DRG authorities should consider how other countries' DRG systems classify AMI patients in order to identify potential scope for improvement and to ensure fair and appropriate reimbursement.

The OIG's new definition of "usual charges" could have a significant impact on payment rates for a hospital's services. Traditionally, "usual charges" has referred simply to non-discounted rates maintained in a hospital's charge description master. The OIG's definition of the term includes discounted rates that a hospital negotiates with commercial payers. If the OIG's definition is adopted, payers may attempt to apply it, thereby complicating rate setting negotiations and monitoring of contract compliance.

Effective CDM management not only minimizes revenue losses due to denied claims, but also helps eliminate administrative costs associated with correcting coding errors. Accountability for CDM management should be assigned to a single individual, who ideally reports to the CFO or high-level finance director. If your organization is prone to making billing errors due to CDM deficiencies, you should consider purchasing CDM software to help you manage your CDM.

Cedars-Sinai Medical Center in Los Angeles revamped its billing system to better meet patients' needs for comprehensible billing information. After changing its billing format and processes, the provider's phone-call volume decreased 31 percent, translating into an annual savings of more than $250,000. Patient feedback regarding the new system has been over-whelmingly positive. The new billing system has contributed to 20 percent acceleration in payment.

Upcoming modifications are designed to capture current service delivery patterns, reimbursement methods, and payment sources for hospital visits, rather than what the hospital charges for individual treatment inputs; the result will be an index that better reflects price changes in the dynamic health care field.