Bayesian inference of local government audit outcomes.

The scandals in publicly listed companies have highlighted the large losses that can result from financial statement fraud and weak corporate governance. Machine learning techniques have been applied to automatically detect financial statement fraud with great success. This work presents the first application of a Bayesian inference approach to the problem of predicting the audit outcomes of financial statements of local government entities using financial ratios. Bayesian logistic regression (BLR) with automatic relevance determination (BLR-ARD) is applied to predict audit outcomes. The benefit of using BLR-ARD, instead of BLR without ARD, is that it allows one to automatically determine which input features are the most relevant for the task at hand, which is a critical aspect to consider when designing decision support systems. This work presents the first implementation of BLR-ARD trained with Separable Shadow Hamiltonian Hybrid Monte Carlo, No-U-Turn sampler, Metropolis Adjusted Langevin Algorithm and Metropolis-Hasting algorithms. Unlike the Gibbs sampling procedure that is typically employed in sampling from ARD models, in this work we jointly sample the parameters and the hyperparameters by putting a log normal prior on the hyperparameters. The analysis also shows that the repairs and maintenance as a percentage of total assets ratio, current ratio, debt to total operating revenue, net operating surplus margin and capital cost to total operating expenditure ratio are the important features when predicting local government audit outcomes using financial ratios. These results could be of use for auditors as focusing on these ratios could potentially speed up the detection of fraudulent behaviour in municipal entities, and improve the speed and quality of the overall audit.

Audit Data Analysis and Application Based on Correlation Analysis Algorithm.

Traditional audit data analysis algorithms have many shortcomings, such as the lack of means to mine the hidden audit clues behind the data, the difficulty of finding increasingly hidden cheating techniques caused by the electronic and networked environment, and the inability to solve the quality defects of the audited data. Correlation analysis algorithm in data mining technology is an effective means to obtain knowledge from massive data, which can complete, muffle, clean, and reduce defective data and then can analyze massive data and obtain audit trails under the guidance of expert experience or analysts. Therefore, on the basis of summarizing and analyzing previous research works, this paper expounds the research status and significance of audit data analysis and application; elaborates the development background, current status, and future challenges of correlation analysis algorithm; introduces the methods and principles of data model and its conversion and audit model construction; conducts audit data collection and cleaning; implements audit data preprocessing and its algorithm description; performs audit data analysis based on correlation analysis algorithm; analyzes the hidden node activation value and audit rule extraction in correlation analysis algorithm; proposes the application of audit data based on correlation analysis algorithm; discusses the relationship between audit data quality and audit risk; and finally compares different data mining algorithms in audit data analysis. The findings demonstrate that by analyzing association rules, the correlation analysis algorithm can determine the significance of a huge quantity of audit data and characterise the degree to which linked events would occur concurrently or sequentially in a probabilistic manner. The correlation analysis algorithm first inputs the collected audit data through preprocessing module to filter out useless data and then organizes the obtained data into a format that can be recognized by data mining algorithm and executes the correlation analysis algorithm on the sorted data; finally, the obtained hidden data is divided into normal data and suspicious data by comparing it with the pattern in the rule base. The algorithm can conduct in-depth analysis and research on the company's accounting vouchers, account books, and a large number of financial accounting data and other data of various natures in the company's accounting vouchers; reveal its original characteristics and internal connections; and turn it into an audit. People need more direct and useful information. The study results of this paper provide a reference for further researches on audit data analysis and application based on correlation analysis algorithm.

A hospital-specific template for benchmarking its cost and quality.

OBJECTIVE: Develop an improved method for auditing hospital cost and quality tailored to a specific hospital's patient population. DATA SOURCES/SETTING: Medicare claims in general, gynecologic and urologic surgery, and orthopedics from Illinois, New York, and Texas between 2004 and 2006. STUDY DESIGN: A template of 300 representative patients from a single index hospital was constructed and used to match 300 patients at 43 hospitals that had a minimum of 500 patients over a 3-year study period. DATA COLLECTION/EXTRACTION METHODS: From each of 43 hospitals we chose 300 patients most resembling the template using multivariate matching. PRINCIPAL FINDINGS: We found close matches on procedures and patient characteristics, far more balanced than would be expected in a randomized trial. There were little to no differences between the index hospital's template and the 43 hospitals on most patient characteristics yet large and significant differences in mortality, failure-to-rescue, and cost. CONCLUSION: Matching can produce fair, directly standardized audits. From the perspective of the index hospital, "hospital-specific" template matching provides the fairness of direct standardization with the specific institutional relevance of indirect standardization. Using this approach, hospitals will be better able to examine their performance, and better determine why they are achieving the results they observe.

Is the two-midnight rule much ado about nothing?

The Centers for Medicare & Medicaid Services has declared that stays that span two midnights should be presumed to be inpatient stays, but case managers still need to make sure patients meet inpatient criteria and that the documentation is complete. Physicians must certify medical necessity, sign, date, and time the admission, and include a treatment plan and the anticipated length of stay. Physician documentation must be accurate, detailed and give a complete picture of what's going on with the patient or hospitals could face significant payment implications. Medicare auditors still will be scrutinizing the records and are likely to continue to target one-day stays and two-day stays for medical necessity.

Common embezzlement myths.

With published statistics suggesting that embezzlement strikes three in five doctors at some point in their careers, this topic is of interest to every professional owning a medical or dental office, and tackles some of the biggest areas of misunderstanding concerning embezzlement in professional offices. Many readers will be surprised to learn that many of the steps that are frequently advocated to control embezzlement are, in fact, ineffective. This article suggests an approach that is quite different from what is normally recommended, and yet is far easier to implement than conventional embezzlement-control strategies.

Pharmacy revenue cycle audits can bring unexpected returns.

An end-to-end pharmacy revenue cycle analysis, led by a multidisciplinary team with broad expertise, can enable a hospital to identify unsuspected errors and oversights that could be causing the organization to lose millions of dollars in revenue annually that it is entitled to receive. If the analysis finds that considerable revenue is being lost, the next step for the team should be to develop a remediation plan to identify the exact cause of each issue and correct it. Following completion of the initial analysis, the hospital should assign permanent accountability and ownership to the team to ensuring the ongoing integrity and accuracy of the pharmacy revenue cycle.

A comparative study of financial data sources for critical access hospitals: audited financial statements, the Medicare cost report, and the Internal Revenue Service form 990.

PURPOSE: Medicare cost reports (MCR), Internal Revenue Service form 990s (IRS 990), and audited financial statements (AFS) vary in their content, detail, purpose, timeliness, and certification. The purpose of this study was to compare selected financial data elements and characterize the extent of differences in financial data and ratios across the MCR, IRS 990, and AFS for a sample of nonprofit critical access hospitals (CAHs). METHODS: Line items from AFS of 47 CAHs were compared to data reported in the hospitals' MCR and IRS 990s. Line items were based on 9 financial indicators commonly used to assess hospital financial performance. FINDINGS: Of the indicators examined, the equity financing ratio most frequently matched between the 3 reports, while salaries and benefits to total expenses and debt service coverage were often different. Variances were driven by differences in individual account balances used to construct the ratios. Relative to AFS, cash was frequently lower on the IRS 990 while marketable securities and unrestricted investments were often higher. Other revenue and net income were consistently lower on the MCR and IRS 990, and depreciation was often higher on the MCR. The majority of total assets and fund balance (equity) values matched across the 3 reports, suggesting differences in classification among detailed accounts were more common than variances between the component totals (total assets, total liabilities, and fund balance). CONCLUSIONS: Health policy researchers should consider the impact of these variances on study results and consider ways to improve the availability and quality of financial accounting information.

Scientific fraud in 20 falsified anesthesia papers : detection using financial auditing methods.

Data from natural sources show counter-intuitive distribution patterns for the leading digits to the left of the decimal point and the digit 1 is observed more frequently than all other numbers. This pattern, which was first described by Newcomb and later confirmed by Benford, is used in financial and tax auditing to detect fraud. Deviations from the pattern indicate possible falsifications. Anesthesiology journals are affected not only by ghostwriting and plagiarism but also by counterfeiting. In the present study 20 publications in anesthesiology known to be falsified by an author were investigated for irregularities with respect to Benford's law using the χ(2)-test and the Z-test. In the 20 retracted publications an average first-digit frequency of 243.1 (standard deviation SD ± 118.2, range: 30-592) and an average second-digit frequency of 132.3 (SD ± 72.2, range: 15-383) were found. The observed distribution of the first and second digits to the left of the decimal point differed significantly (p< 0.01) from the expected distribution described by Benford. Only the observed absolute frequencies for digits 3, 4 and 5 did not differ significantly from the expected values. In an analysis of each paper 17 out of 20 studies differed significantly from the expected value for the first digit and 18 out of 20 studies varied significantly from the expected value of the second digit. Only one paper did not vary significantly from expected values for the digits to the left of the decimal. For comparison, a meta-analysis using complex mathematical procedures was chosen as a control. The analysis showed a first-digit distribution consistent with the Benford distribution. Thus, the method used in the present study seems to be sensitive for detecting fraud. Additional statements of specificity cannot yet be made as this requires further analysis of data that is definitely not falsified. Future studies exploring conformity might help prevent falsified studies from being published.

Early warning system for financially distressed hospitals via data mining application.

The aim of this study is to develop a Financial Early Warning System (FEWS) for hospitals by using data mining. A data mining method, Chi-Square Automatic Interaction Detector (CHAID) decision tree algorithm, was used in the study for financial profiling and developing FEWS. The study was conducted in Turkish Ministry of Health's public hospitals which were in financial distress and in need of urgent solutions for financial issues. 839 hospitals were covered and financial data of the year 2008 was obtained from Ministry of Health. As a result of the study, it was determined that 28 hospitals (3.34%) had good financial performance, and 811 hospitals (96.66%) had poor financial performance. According to FEWS, the covered hospitals were categorized into 11 different financial risk profiles, and it was found that 6 variables affected financial risk of hospitals. According to the profiles of hospitals in financial distress, one early warning signal was detected and financial road map was developed for risk mitigation.