Using Big Data Analytics to Identify Dentists with Frequent Future Malpractice Claims

Healthcare spending has been growing at an increasing rate in the US, due in part to medical malpractice costs. Dental malpractice is an area that has not been studied in depth. Using National Practitioner Data Bank (NPDB), we explored the extent of dental malpractice claims and sought to construct a predictive model that can help us identify dental practitioners at risk of performing medical malpractice. Over 1,500 dental malpractice claims were reported annually, and over $1.7 billion being paid out by medical malpractice insurers over the past 15 years. Majority of claims resulted in minor injuries, and the number of major injury claims increased over years. In prediction, we randomly split the data into train (75%) and test (25%) datasets. We trained and tuned models using 5-fold cross validation on the training set. Then, we fitted the model on the test data for performance measures. We used Logistic Regression, Random Forest (RF) and XGBoost and tuned the hypermeters of models accordingly through grid search and cross validation. XGBoost was the best machine learning model to predict the risk of dentists having several malpractice reports. The best performing model had an accuracy of 72.8% with 30.6% F1 score. The NPDB database is a valuable dataset to study dental malpractice claims. Further analysis of information extracted from this dataset is warranted.

Reputation management

Patients with a computer and access to social media can now easily and effortlessly comment on your practice and your services. Most comments about physicians are positive. However, a negative one may be posted by a disgruntled patient and can severely impact your practice with a mere mouse click. A physician's most valuable asset is his or her reputation. This article will discuss how to manage and protect your online reputation.

The National Practitioner Data Bank: what CRNAs need to know

As a nationwide flagging system, the National Practitioner Data Bank (NPDB) allows state licensing boards, hospitals, and other registered healthcare entities the ability to monitor practitioners through reporting and inquiry about the qualifications and competency of healthcare practitioners seeking clinical privileges where incompetence or unprofessional conduct could adversely affect a patient's welfare. Certified Registered Nurse Anesthetists are not exempt from being reported on or queried by registered reporting and querying entities. The NPDB warehouses data pertaining to adverse actions or medical malpractice payments taken against a practitioner. Based on the updated federal ruling published in the Federal Register regarding the NPDB and Section 1921 of the Social Security Act, the NPDB has expanded the definition of healthcare practitioners to include all healthcare practitioners as a means of protecting beneficiaries of the Social Security Act's healthcare programs. As such, nurse anesthetists should be aware of the additional reportable information that may be collected or disseminated based on the updated ruling pertaining to the NPDB.

Which is feared more: harm to the ego or financial peril? A survey of anesthesiologists' attitudes about medical malpractice

This article reports the results of a study of anesthesiologists to assess their concerns regarding medical malpractice liability risk. Specifically, it explored whether their fears stem more from being named as a party to a suit or from the financial impact of damage awards. According to the respondents, their reputation among patients and colleagues is of greater concern than the financial impact of a malpractice suit. Forty-six percent of the 149 respondents reported a constant fear of malpractice risk; 43% were concerned about their reputation among colleagues and 57% feared their reputation would be compromised among patients. A large majority voiced concern about potential inclusion in the National Practitioner Data Bank (83%) and their rankings on online physician-grading sites (85%). Forty-one percent said financial consequences were a concern, and 54% indicated that obtaining affordable liability coverage was an issue.

Comparing manual and automated coding of physicians quality reporting initiative measures in an ambulatory EHR

The objective of this study was to compare the completeness and accuracy of Physicians Quality Reporting Initiative (PQRI) quality measure code assignment by manual coding and the automated system. Documentation for 62 PQRI quality measures was built into the electronic health record (EHR) system used in 15 rural ambulatory clinics with 70,000 patient encounters per year. The documentation systems and processes within the ambulatory EHR were standardized so data required for quality measurement would be available as extractable data. Completeness and accuracy of coding was compared between an expert coder and an automated system. Automated coding was significantly more complete and accurate than manual coding for the quality measures examined.

The impact of the National Practitioner Data Bank on licensing actions by state medical licensing boards

The United States Congress mandated the establishment of the National Practitioner Data Bank in large part to decrease the likelihood that errant individuals might be able to avoid detection by licensing boards and practice medicine. We use a decade of longitudinal data (1985-94), for each of the 50 states, to evaluate the Bank's impact on state licensing board actions, during the four years following its 1990 birth. The results of a pooled, time-series analysis reveal that medical board restrictions on physicians' practices increased substantially following the creation of the Data Bank. We conclude that the increase was likely due to the licensing boards taking actions against delinquent physicians who had previously slipped through cracks in the regulatory system or who had earlier received warnings or administrative fines.

Should fear of malpractice dissuade dentists from caring for children?

PURPOSE

Little information is available on malpractice related to dentistry for children. The purpose of this report was to examine characteristics of malpractice allegations related to dentistry for children from the National Practitioner Databank (NPDB) from February 1, 2004 to November 22, 2006.

METHODS

The public use file of the NPDB was obtained and transformed into a searchable database and allegations involving children were sorted and characterized by payment size, reason, practitioner type, and location.

RESULTS

During the roughly 34-month study period, 571,172 total cases were evaluated. 51,691 (9%) of these involved dentists; 367 reports were identified using age-based variable reporting. The majority of cases (275; 75%) involved 10- to 19-year-old children and 92 (25%) of the cases involved 0- to 9-year-old children. One case was an infant younger than one year old. No cases were found with the provider citation of dental resident. The geographic distribution of cases was consistent with relation to practitioner (dentist) density and mean age.

CONCLUSION

The allegation of malpractice related to dentistry for children is a very small portion of both dental and general health malpractice in the United States.

Credentialing

Credentialing is the administrative process for validating the qualifications of licensed professionals and appraising their background. It is used by hospitals and other health care facilities, educational institutions, and insurance companies to ensure the qualification of their clinicians and to grant privileges to provide specific services and perform different medical or dental procedures. This article familiarizes the reader with the credentialing process and the documentation that is needed to be credentialed by certain organizations.

Your choice: documentation or litigation?

As the nursing shortage worsens and the care required by the elderly population increases and becomes more complex, the need for accurate, portable, and permanent electronic documentation methods will and must become an integral part of gerontological nurses' routine recordkeeping. Integrating technology into care regimens is inevitable. Gerontological nurses must exert their leadership so the newest technology can be used to both improve the care of older patients while protecting those who provide that care.

Wrong-Side/Wrong-Site, Wrong-Procedure, and Wrong-Patient Adverse Events

HYPOTHESIS

Wrong-side/wrong-site, wrong-procedure, and wrong-patient adverse events (WSPEs) are devastating, unacceptable, and often result in litigation, but their frequency and root causes are unknown. Wrong-side/wrong-site, wrong-procedure, and wrong-patient events are likely more common than realized, with little evidence that current prevention practice is adequate.

DESIGN

Analysis of several databases demonstrates that WSPEs occur across all specialties, with high numbers noted in orthopedic and dental surgery. Databases analyzed included: (1) the National Practitioner Data Bank (NPDB), (2) the Florida Code 15 mandatory reporting system, (3) the American Society of Anesthesiologists (ASA) Closed Claims Project database, and (4) a novel Web-based system for collecting WSPE cases (http://www.wrong-side.org).

RESULTS

The NPDB recorded 5940 WSPEs (2217 wrong-side surgical procedures and 3723 wrong-treatment/wrong-procedure errors) in 13 years. Florida Code 15 occurrences of WSPEs number 494 since 1991, averaging 75 events per year since 2000. The ASA Closed Claims Project has recorded 54 cases of WSPEs. Analysis of WSPE cases, including WSPE cases submitted to http://www.wrong-side.org, suggest several common causes of WSPEs and recurrent systemic failures. Based on these findings, we estimate that there are 1300 to 2700 WSPEs annually in the United States. Despite a significant number of cases, reporting of WSPEs is virtually nonexistent, with reports in the lay press far more common than reports in the medical literature. Our research suggests clear factors that contribute to the occurrence of WSPEs, as well as ways to reduce them.

CONCLUSIONS

Wrong-side/wrong-site, wrong-procedure, and wrong-patient adverse events, although rare, are more common than health care providers and patients appreciate. Prevention of WSPEs requires new and innovative technologies, reporting of case occurrence, and learning from successful safety initiatives (such as in transfusion medicine and other high-risk nonmedical industries), while reducing the shame associated with these events.

The National Practitioner Data Bank and Anesthesia Malpractice Payments

A publicly available SPSS database was obtained at the National Practitioner Data Bank website (www.npdb-hipdb.com). After analysis, we found that between 1991 and 2004, there were 276,274 medical malpractice-related payments in the United States. During that period, 8297 anesthesia-related malpractice payments were made on behalf of practitioners in the United States. When adjusted for population growth, there was a 27.7% decrease in the annual number of anesthesia malpractice payments per 100,000 people during the period 2001-2004 as compared with the period a decade earlier 1991-1994 (0.26 versus 0.19). Also, the median anesthesia malpractice payments, adjusted to 2005 dollars, increased significantly from 1991 to 1994 and 2001 to 2004 (69,330 dollars versus 205,222 dollars). We conclude that over the past 14 yr, whereas the number of anesthesia malpractice payments has decreased, the median payment of cases has increased.

The role of the national practitioner data bank in the credentialing process

Federal law requires hospitals and permits other entities to seek information from the National Practitioner Data Bank (NPDB) but places no requirements on how that information should be used. Our survey of NPDB users demonstrates that although the NPDB has generated substantial controversy and its information is nominally available from other sources, it still plays an important role in the credentialing process. Most institutions make timely NPDB inquiries that facilitate widespread use of the information in credentialing activities (4-5 individuals or committees). However, in 3% to 7% of cases, a decision was reached before the institution had the NPDB report. Between 5% and 30% of privileging and licensure applications involving an NPDB report were not granted "as requested," suggesting the NPDB data are important to the process. Unfortunately, underreporting was also evident: 60% to 75% of reportable actions were not reported, limiting the information to which health care entities have access.

Fitness, knowledge, progress: assessing physician qualification

The informed and empowered consumer is an ideal invoked by many would-be health care reformers. An actual consumer wishing to don the mantle of power may be hindered by the scarcity of information available, particularly with respect to choosing among physicians. How is one to know who is best qualified? This issue brief looks at the basics of physician qualification and the processes by which physicians are licensed, credentialed, and board-certified. It examines how the evolution of these processes (for example, the move from lifetime certification to ongoing maintenance of certification) affects clinicians and their patients. The rise of quality measurement and pay-for-performance programs is considered as well.

Graph kernels for chemical informatics

Increased availability of large repositories of chemical compounds is creating new challenges and opportunities for the application of machine learning methods to problems in computational chemistry and chemical informatics. Because chemical compounds are often represented by the graph of their covalent bonds, machine learning methods in this domain must be capable of processing graphical structures with variable size. Here, we first briefly review the literature on graph kernels and then introduce three new kernels (Tanimoto, MinMax, Hybrid) based on the idea of molecular fingerprints and counting labeled paths of depth up to d using depth-first search from each possible vertex. The kernels are applied to three classification problems to predict mutagenicity, toxicity, and anti-cancer activity on three publicly available data sets. The kernels achieve performances at least comparable, and most often superior, to those previously reported in the literature reaching accuracies of 91.5% on the Mutag dataset, 65-67% on the PTC (Predictive Toxicology Challenge) dataset, and 72% on the NCI (National Cancer Institute) dataset. Properties and tradeoffs of these kernels, as well as other proposed kernels that leverage 1D or 3D representations of molecules, are briefly discussed.

Credentialing for nurse practitioners: an update

The public has the right to safe, quality healthcare delivered by professionals with the appropriate education, training, and experience. The Joint Commission on Accreditation of Healthcare Organizations, the Accreditation Association for Ambulatory Healthcare, and managed care organizations take this commitment very seriously. One mechanism required by these agencies to ensure patient safety is the process of credentialing and delineation of clinical privileges for medical staff and allied health professionals, such as Acute Care Nurse Practitioners. This commitment extends to patients receiving healthcare through the technology of telemedicine and to those requiring emergency care resulting from trauma, disasters, and varying forms of terrorism. In addition, safeguards must be in place to prevent identity theft of healthcare providers, including Acute Care Nurse Practitioners. It is essential that Acute Care Nurse Practitioners be familiar with the regulations that impact and guide the process of credentialing and obtaining clinical privileges in a variety of venues.

The Growth Of Physician Medical Malpractice Payments: Evidence From The National Practitioner Data Bank

We used data from the National Practitioner Data Bank (NPDB) to study the growth of physician malpractice payments. Judgments at trial account for 4 percent of all malpractice payments; settlements account for the remaining 96 percent. The average payment grew 52 percent between 1991 and 2003 (4 percent per year) and now exceeds dollar 12 per capita each year. These increases are consistent with increases in the cost of health care. A preoccupation with data on judgments, extreme awards, or specific specialties results in an incomplete understanding of the growth of physician malpractice payments.

Health care fraud and abuse data collection program: technical revisions to healthcare integrity and protection data bank data collection activities. Interim final rule with comment period

The rule makes technical changes to the Healthcare Integrity and Protection Data Bank (HIPDB) data collection reporting requirements set forth in 45 CFR part 61 by clarifying the types of personal numeric identifiers that may be reported to the data bank in connection with adverse actions. Specifically, the rule clarifies that in lieu of a Social Security Number (SSN), an individual taxpayer identification number (ITIN) may be reported to the data bank when, in those limited situations, an individual does not have an SSN.

Nurses must cooperate with internal and external investigations

The problem with bad nurses or incompetent practitioners is that they may get away with murder because their poor behaviour is not effectively dealt with or challenged. A typical example of this is the nurse who works for an employer and after a period in the job gets into trouble and leaves before any further action can be taken. Many healthcare organizations, such as NHS trusts and private nursing homes, do not want either the hassle or the bad publicity, so they often sack the bad nurse without addressing the issues.

Impact of the National Practitioner Data Bank on resolution of malpractice claims

Policymakers and commentators are concerned that the National Practitioner Data Bank (NPDB) has influenced malpractice litigation dynamics. This study examines whether the introduction of the NPDB changed the outcomes, process, and equity of malpractice litigation. Using pre- and post-NPDB analyses, we examine rates of unpaid claims, trials, resolution time, physician defense costs, and payments on claims with a low/high probability of negligence. We find that physicians and their insurers have been less likely to settle claims since introduction of the NPDB, especially for payments less than dollars 50,000. Because this disruption appears to have decreased the proportion of questionable claims receiving compensation, the NPDB actually may have increased overall tort system specificity.

Standing up to the scrutiny of medical malpractice

Correct charting, updated policies and procedures, and firm staff understanding are critical components of avoiding medical malpractice.

Reconsidering medical malpractice reform: the case for arbitration and transparency in non-emergent contexts

This Article proposes a two-pronged legislative response to the current debate over medical malpractice insurance. The author does not advocate mandatory caps on malpractice damages, nor the imposition of a uniform regime on the field of medicine. Rather, he articulates some of the important legal, medical, and societal benefits that would come from embracing arbitration in the non-emergent medical malpractice context. The author also calls for the reformulation of the National Practitioner Data Bank to achieve greater transparentcy and to leverage advances in information technology and data-mining software to measure the risk levels of individual practitioners. This reform, in turn, would open up the possibility of greater subcategorization of premiums and more effective deterrence in medical malpractice insurance.

The medicolegal aspects of proctoring

Virtually every medical staff ensures surgeons technical competency by requiring a proctoring process. However, rarely do medical staff bylaws specify the relationship between completion of proctoring and acquisition of medical staff privileges. For this reason surgeons failing to acquire privileges because of adverse proctor evaluations might be subject to National Practitioners Data Bank reporting. Few proctors understand what their responsibilities are should they witness malpractice being committed. In the State of California, case law has demonstrated that proctors are immune from liability should they allow substandard practices to continue and fail to intervene on the patient's behalf. Alternatively, if the proctor intervenes on a Good Samaritan basis they are most likely protected from malpractice liability. We recommend the implementation of two processes to avoid legal pitfalls: (1) Liability can be minimized if proctoring consents are obtained that clearly delineate the proctor's responsibilities during the operation. (2) Medical staff bylaws should clearly specify the temporal relationship between application of privileges, duration of proctoring process and final acquisition of clinical privileges.

Peer review

Peer review is essential for ensuring quality medical care. In the 1980s a physician-plaintiff prevailed in lawsuit filed against peer reviewers who excluded the physician from a hospital's medical staff. The peer reviewers had acted to preserve their own economic interests. A multimillion-dollar verdict against the peer reviewers destroyed the community's only multispecialty practice and received national attention. Congress reacted by passing the Health Care Quality Improvement Act that granted sweeping, legal immunity for peer reviewers but also created the National Practitioner's Data Bank. The combination of the establishment of a public repository for physicians malpractice and medical staff privileging activity in combination with the near complete legal protection of peer reviewers has converted peer review from an evaluative to a punitive process. The peer review process and the laws that govern it should be reformed to regain its ability to improve and assure quality without being a threat to physicians.