Patient Protected Health Information Research Articles

A De-Identification Model for Korean Clinical Notes: Using Deep Learning Models.

To extract information from free-text in clinical records due to the patient's protected health information PHI in the records pre-processing of de-identification is required. Therefore we aimed to identify PHI list and fine-tune the deep learning BERT model for developing de-identification model. The result of fine-tuning the model is strict F1 score of 0.924. Due to the convinced score the model can be used for the development of a de-identification model.

Use of Patients' Protected Health Information to Solicit Hospital Funds: How did This Practice Come About?

Modifications to Health Insurance Portability and Accountability Act (HIPAA) have allowed for the disclosure of patient protected health information (PHI) for the purpose of hospital fundraising. The public has recently raised ethical concerns regarding these practices. We examined the forces that brought about these HIPAA modifications. We first examined 304 comments submitted to the proposed rule for the HIPPA regulation modifications. We additionally queried the OpenSecrets repository for lobbying activity by these commenters. We found that 57 out of the 304 comments pertained specifically to fundraising practices. The majority of comments were from hospital developmental (fundraising) offices (51%, 29 of 57 comments), and the majority (96%, 24 of 25 hospital comments; 83%, 34 of 41 total comments discussing PHI disclosure) supported additional PHI disclosure. There was a paucity of comments from physician organizations (1 of 57) and patient advocates (2 of 57). The majority of lobbying dollars (95% of over $81 million) were from commenters who favored the modifications. The lack of physician and patient representation in the rule-making process likely contributed to the creation of regulations that elicit ethical concerns in physicians, and potential harm for patients.

Privacy in the Coronavirus Era.

Privacy in the Coronavirus Era.

The American Academy of Dermatology COVID-19 registry: Crowdsourcing dermatology in the age of COVID-19

The American Academy of Dermatology COVID-19 registry: Crowdsourcing dermatology in the age of COVID-19

DE-IDENTIFICATION OF PROTECTED HEALTH INFORMATION PHI FROM FREE TEXT IN MEDICAL RECORDS

Medical health records often contain clinical investigations results and critical information regarding patient health conditions. In these medical records, along with patient health information, patient Protected Health Information (PHI) such as names, locations and date information can co-exist. As per Health Insurance Portability and Accountability Act (HIPAA), before sharing the medical records with researchers and others, all types of PHI information needs to be de-identified. Manual de-identification through human annotators is laborious and error prone, hence, a reliable automated de-identification system is need of the hour. In this work, various state of the art techniques for de-identification of patient notes in electronic health records were analyzed for their performance, based on the performance quoted in the literature, NeuroNER was selected to de-identify Indian Radiology reports. NeuroNER is a named-entity recognition text de-identification tool developed by Massachusetts Institute of Technology (MIT). This tool is based on the Artificial Neural Networks written in Python and uses Tensorflow machine-learning framework and it comes with five pre-trained models. To test the NeuroNER models on Indian context data such as name of the person and place, 3300 medical records were simulated. Medical records were simulated by extracting clinical findings, remarks from MIMIC-III data set. For collection of all the relevant Indian data, various websites were scraped to include Indian names, Indian locations (all towns and cities), and Indian Hospital and unit names. During the testing of NeuroNER system, we observed that some of the Indian data such as name, location, etc. were not de-identified satisfactorily. To improve the performance of NeuroNER on Indian context data, along with the existing NeuroNER pre-trained model, a new pre-trained model was added to handle Indian medical reports. Medical dictionary lookup was used to reduce number of misclassifications. Results from all four pre-trained models and the model trained on Indian simulated data were concatenated and final PHI token list was generated to anonymize the medical records to obtain de-identified records. Using this approach, we improved the applicability of the NeuroNER system to Indian data and improved its efficiency and reliability. 2000 simulated reports were used for transfer learning as training set, 1000 reports were used for test set and 300 reports were used for validation (unseen) set.

Serologic Confirmation of Rubella Immunity During Index Pregnancy Can Eliminate Re-testing in Later Pregnancies [11F

INTRODUCTION: Vaccination ended endemic rubella transmission in America with the last documented case of congenital rubella syndrome in 2004. The American College of Obstetrics and Gynecology recommends rubella susceptibility screening as a prenatal lab for all pregnancies. As no studies in the United States support or contest this, we explored whether women with documented immunity during their index pregnancy demonstrated serologic evidence of Rubella immunity during subsequent gestations. METHODS: A retrospective cohort study of Medicaid insured pregnant women receiving prenatal care at an urban clinic from 2012-2017 was undertaken. Only those with documented immunity during their initial antenatal visit and repeat serologies during subsequent pregnancies were included. Immunity was defined as rubella IgG antibodies titers greater than 10 IU/mL. All patient protected health information has been de-identified and patient faces are entirely covered. RESULTS: Five hundred women were screened for study eligibility with rubella serologies obtained in 318 during both index and subsequent pregnancies. In this cohort, 94.3% (n=300) were noted to be immune during their index pregnancy. Among this immunized population, 98.3% continued to demonstrate serologic immunity during subsequent pregnancies. There was no relationship between the time interval between pregnancies and rubella sero-conversion rates. CONCLUSION: Our data indicates 98% of women with rubella immunity during their first pregnancy maintain immunity during subsequent pregnancies. Given rates of retained immunity and low disease prevalence with routine vaccination, this study suggests reconfirmation of rubella immunity during subsequent pregnancies is unnecessary. Given the small sample size and retrospective nature of data, large, prospective studies evaluating the sero-conversion rate between pregnancies and the cost-effectiveness of screening prior to every pregnancy are warranted.

Medical photography with a mobile phone: useful techniques, and what neurosurgeons need to know about HIPAA compliance.

Medical photographs are commonly employed to enhance education, research, and patient care throughout the neurosurgical discipline. Current mobile phone camera technology enables surgeons to quickly capture, document, and share a patient scenario with colleagues. Research demonstrates that patients generally view clinical photography favorably, and the practice has become an integral part of healthcare. Neurosurgeons in satellite locations often rely on residents to send photographs of diagnostic imaging studies, neurological examination findings, and postoperative wounds. Images are also frequently obtained for research purposes, teaching and learning operative techniques, lectures and presentations, comparing preoperative and postoperative outcomes, and patient education. However, image quality and technique are highly variable. Capturing and sharing photographs must be accompanied by an awareness of the legal ramifications of the Health Insurance Portability and Accountability Act (HIPAA). HIPAA compliance is straightforward when one is empowered with the knowledge of what constitutes a patient identifier in a photograph. Little has been published to describe means of improving the accuracy and educational value of medical photographs in neurosurgery. Therefore, in this paper, the authors present a brief discussion regarding four easily implemented photography skills every surgeon who uses his or her mobile phone for patient care should know: 1) provide context, 2) use appropriate lighting, 3) use appropriate dimensionality, and 4) manage distracting elements. Details of the HIPAA-related components of mobile phone photographs and patient-protected health information are also included.

Prescription Drug Policing: The Right to Protected Health Information Privacy Pre- and Post-Carpenter

This article operates at the intersection of privacy law, Fourth Amendment doctrine, and public health realities triggered by the United States drug overdose epidemic. Reputable reporting sources, public health scholars, and pundits frequently frame the ongoing American overdose crisis as a prescription drug overdose problem attributable to the overprescribing of opioid analgesics. The problem with this narrative is that it runs counter to the current epidemiological data, which indicate that the majority of American overdose deaths are now a result of illicit drug use and not prescription drug abuse. The prescription-centric frame has nonetheless sparked the rapid rise of law enforcement and regulatory surveillance of prescribers and patients in the form of state prescription drug monitoring program (PDMP) databases. State PDMPs, which maintain and analyze significant data concerning every dispensed prescription, collect a stunning amount of patient protected health information (PHI). To put things in context, Americans filled 4,063,166,658 prescriptions at retail pharmacies in 2017 alone. PDMPs are largely criminal and regulatory law enforcement tools dressed up in public health promoting rhetoric. Under the guise of rogue prescriber, pill mill, and doctor shopper crack downs, the Drug Enforcement Administration (DEA) has made it a routine practice to self-issue administrative subpoenas to conduct warrantless, dragnet-style sweeps of the swarms of sensitive protected health data stored in state PDMP databases. This widespread law enforcement prescribing surveillance tactic, which reveals highly personal health information, including, among other things, patients’ contraceptive histories, gender transition decisions, and HIV diagnoses, raises serious constitutional privacy concerns. The Supreme Court’s recent Fourth Amendment decision, Carpenter v. United States, however, may limit law enforcement’s ability to continue to access droves of electronically-stored patient prescribing-related PHI in the custody of a state regulatory agency without a court order supported by probable cause. The Court’s decision in Carpenter already has been heralded as “a landmark privacy case,” which this article uniquely applies to prescription drug monitoring and law enforcement surveillance tactics provoked by the U.S. overdose crisis and its dominant narrative. Carpenter and the Fourth Amendment doctrines central to its holding motivate this article and animate its two core contentions. First, this article maintains that pertinent pre-Carpenter precedent requires the DEA to obtain a Fourth Amendment warrant in order to conduct sweeps of state PDMP databases searching patient protected health information. It then posits that courts are even more likely to rule that warrantless DEA searches of sensitive and frequently revealing health care data run afoul of the Fourth Amendment in the post-Carpenter world. Simply stated, PDMP protected health information is entitled to Fourth Amendment warrant protection.

Ensuring compliance with the HIPAA Security Rule: Think twice when e-mailing protected health information.

Are healthcare providers violating the Health Insurance Portability and Accountability Act (HIPAA) of 1996 when a patient's protected health information is e-mailed?1 They could be if they are not complying with the HIPAA Security Rule.2 Nonadherent healthcare providers could face sizeable monet

MP40-20 DO SURGEONS WISH TO KNOW ABOUT THEIR LONG-TERM COMPLICATIONS?

You have accessJournal of UrologyUrodynamics/Lower Urinary Tract Dysfunction/Female Pelvic Medicine: Female Incontinence: Therapy I1 Apr 2017MP40-20 DO SURGEONS WISH TO KNOW ABOUT THEIR LONG-TERM COMPLICATIONS? Jennifer Wimberly, Shawn Okpara, and Philippe Zimmern Jennifer WimberlyJennifer Wimberly More articles by this author , Shawn OkparaShawn Okpara More articles by this author , and Philippe ZimmernPhilippe Zimmern More articles by this author View All Author Informationhttps://doi.org/10.1016/j.juro.2017.02.1267AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookTwitterLinked InEmail INTRODUCTION AND OBJECTIVES Inspired by our experience with handling long-term vaginal mesh complications, we aimed to assess practitioner′s interest in being made aware of their long-term surgical complications. METHODS Prior to a lecture on this topic, a 3 question survey (table 1) was administered to 16 faculty operative surgeons (FS) in the Department of Urology and to 59 future attendants who had enrolled to attend the lecture, including private practice urologists, nurse and midlevel providers. Long-term complications were defined as those involving re-admissions or reoperations beyond 30 days post-surgery as those are not captured by most quality improvement programs and not reported in Morbidity and Mortality conferences. RESULTS Of the 16 FS, 100% answered that doctors should be alerted of their post-surgical complications (question 1). And, of the lecture attendants, 95.6% also stated they wished to be alerted (10 skipped). Based on the second question on reasons for why we do not contact each other when we are made aware of a long-term complication, 60% of the FS and 53% of the attendants believed that a surgeon might not want to offend or lose a referral base. 13% of FS and 21% of attendants believed that surgeons not knowing his/her own outcomes data was a possible reason. 13% of surgeons and 21% of the attendants believe that the unwillingness to want to increase the operative surgeon′s legal risk could be a reason. 20% of surgeons and 17% of attendants believed that a surgeon might not think feedback decreases complication risks. Lastly 73% of FS and 72% of attendants believed that a surgeon being too busy to track down whom to contact is a primary reason. As far as the best method of providing this long-term tracking data (question 3), 94% of the FS and 84% of the attendants answered that a phone call was the best means for this feedback. The practicality of providing this feedback is hampered by unintended consequences of legal mandates related to patient protected health information. CONCLUSIONS Despite legal barriers in place prohibiting this process, this data suggest that operative surgeons and most urology care providers are interested in receiving information on their long-term post-surgical complications. © 2017FiguresReferencesRelatedDetails Volume 197Issue 4SApril 2017Page: e531 Advertisement Copyright & Permissions© 2017MetricsAuthor Information Jennifer Wimberly More articles by this author Shawn Okpara More articles by this author Philippe Zimmern More articles by this author Expand All Advertisement Advertisement PDF downloadLoading ...

Linking temporal medical records using non-protected health information data.

Modern medical research relies on multi-institutional collaborations which enhance the knowledge discovery and data reuse. While these collaborations allow researchers to perform analytics otherwise impossible on individual datasets, they often pose significant challenges in the data integration process. Due to the lack of a unique identifier, data integration solutions often have to rely on patient's protected health information (PHI). In many situations, such information cannot leave the institutions or must be strictly protected. Furthermore, the presence of noisy values for these attributes may result in poor overall utility. While much research has been done to address these challenges, most of the current solutions are designed for a static setting without considering the temporal information of the data (e.g. EHR). In this work, we propose a novel approach that uses non-PHI for linking patient longitudinal data. Specifically, our technique captures the diagnosis dependencies using patterns which are shown to provide important indications for linking patient records. Our solution can be used as a standalone technique to perform temporal record linkage using non-protected health information data or it can be combined with Privacy Preserving Record Linkage solutions (PPRL) when protected health information is available. In this case, our approach can solve ambiguities in results. Experimental evaluations on real datasets demonstrate the effectiveness of our technique.

Cloudy.

Cloudy.

Healthcare IT: Is Your Information At Risk?

Healthcare Information Technology (IT) has made great advances over the past few years and while these advances have enable healthcare professionals to provide higher quality healthcare to a larger number of individuals it also provides the criminal element more opportunities to access sensitive information, such as patient protected health information (PHI) and Personal identification Information (PII). Having an Information Assurance (IA) programallows for the protection of information and information systems and ensures the organization is in compliance with all requires regulations, laws and directive is essential. While most organizations have such a policy in place, often it is inadequate to ensure the proper protection to prevent security breaches. The increase of data breaches in the last few years demonstrates the importance of an effective IA program. To ensure an effective IA policy, the policy must manage the operational risk, including identifying risks, assessment and mitigation of identified risks and ongoing monitoring to ensure compliance

HIPAA for Cancer Educators: Are You Correctly Using PHI?

Privacy and confidentiality policies and practices, including Health Insurance Portability and Accountability Act (HIPAA) policies, may vary from institution to institution because they are developed to be institution-specific. HIPAA privacy and security regulations represent the minimum standards, and the expectation is that institutions will develop policies and practices that are reasonable and appropriate for their institution. These privacy and information security safeguards impact the use of sensitive and protected data often used by cancer educators. Therefore, it is important for cancer educators to be familiar with the policies, rules, and guidelines their institution has developed to comply with HIPAA. However, despite institutional differences, certain principles related to the confidentiality, protection, and uses of a patient's health information remain consistent. HIPAA provides two sets of regulations that directly impact the work of many cancer educators: privacy and information security. The HIPAA Privacy Rule includes some security requirements, and HIPAA Security Regulations were designed to ensure privacy of the patient's protected health information (PHI). This paper focuses primarily on the privacy factors.

When microchip implants do more than drug delivery: Blending, blurring, and bundling of protected health information and patient monitoring

Although currently in the research stage, scientists argue that drug-releasing microchip implants are on the horizon for future patients. This paper presents ethical reflection on these implants and identifies specific areas of concern; namely, patient monitoring and tracking, and patient privacy and confidentiality. It is foreseeable that drug delivery chips could be multifunctional with the overt or covert addition of sensors that monitor more than just the bloodstream concentrations of prescribed drugs (e.g., cotinine and alcohol in non-compliant patients, patient location via radio frequency or global positioning satellite). Similarly, it is foreseeable that these chips could be embedded with a patient's protected health information that could potentially be accessed and used by unauthorized persons. While drug delivery microchips are theoretically convenient and accurate for dosing, and might offer faster drug delivery with fewer side effects, ethical issues loom and should be contemplated now, while the technology is still under development.