scholarly journals Detecting Miscoded Diabetes Diagnosis Codes in Electronic Health Records for Quality Improvement: Temporal Deep Learning Approach (Preprint)

2020 ◽  
Author(s):  
Sina Rashidian ◽  
Kayley Abell-Hart ◽  
Janos Hajagos ◽  
Richard Moffitt ◽  
Veena Lingam ◽  
...  
Keyword(s):  
Health Care ◽  
Deep Learning ◽  
Health Care Providers ◽  
Demographic Data ◽  
The United States ◽  
Heterogeneous Data ◽  
Diabetes Diagnosis ◽  
Care Providers ◽  
Data Set ◽  
Laboratory Test Results

BACKGROUND Diabetes affects more than 30 million patients across the United States. With such a large disease burden, even a small error in classification can be significant. Currently billing codes, assigned at the time of a medical encounter, are the “gold standard” reflecting the actual diseases present in an individual, and thus in aggregate reflect disease prevalence in the population. These codes are generated by highly trained coders and by health care providers but are not always accurate. OBJECTIVE This work provides a scalable deep learning methodology to more accurately classify individuals with diabetes across multiple health care systems. METHODS We leveraged a long short-term memory-dense neural network (LSTM-DNN) model to identify patients with or without diabetes using data from 5 acute care facilities with 187,187 patients and 275,407 encounters, incorporating data elements including laboratory test results, diagnostic/procedure codes, medications, demographic data, and admission information. Furthermore, a blinded physician panel reviewed discordant cases, providing an estimate of the total impact on the population. RESULTS When predicting the documented diagnosis of diabetes, our model achieved an 84% F1 score, 96% area under the curve–receiver operating characteristic curve, and 91% average precision on a heterogeneous data set from 5 distinct health facilities. However, in 81% of cases where the model disagreed with the documented phenotype, a blinded physician panel agreed with the model. Taken together, this suggests that 4.3% of our studied population have either missing or improper diabetes diagnosis. CONCLUSIONS This study demonstrates that deep learning methods can improve clinical phenotyping even when patient data are noisy, sparse, and heterogeneous.

scholarly journals Detecting Miscoded Diabetes Diagnosis Codes in Electronic Health Records for Quality Improvement: Temporal Deep Learning Approach

10.2196/22649 ◽  
2020 ◽  
Vol 8 (12) ◽  
pp. e22649
Author(s):  
Sina Rashidian ◽  
Kayley Abell-Hart ◽  
Janos Hajagos ◽  
Richard Moffitt ◽  
Veena Lingam ◽  
...  
Keyword(s):  
Health Care ◽  
Deep Learning ◽  
Health Care Providers ◽  
Demographic Data ◽  
The United States ◽  
Heterogeneous Data ◽  
Diabetes Diagnosis ◽  
Care Providers ◽  
Data Set ◽  
Laboratory Test Results

Background Diabetes affects more than 30 million patients across the United States. With such a large disease burden, even a small error in classification can be significant. Currently billing codes, assigned at the time of a medical encounter, are the “gold standard” reflecting the actual diseases present in an individual, and thus in aggregate reflect disease prevalence in the population. These codes are generated by highly trained coders and by health care providers but are not always accurate. Objective This work provides a scalable deep learning methodology to more accurately classify individuals with diabetes across multiple health care systems. Methods We leveraged a long short-term memory-dense neural network (LSTM-DNN) model to identify patients with or without diabetes using data from 5 acute care facilities with 187,187 patients and 275,407 encounters, incorporating data elements including laboratory test results, diagnostic/procedure codes, medications, demographic data, and admission information. Furthermore, a blinded physician panel reviewed discordant cases, providing an estimate of the total impact on the population. Results When predicting the documented diagnosis of diabetes, our model achieved an 84% F1 score, 96% area under the curve–receiver operating characteristic curve, and 91% average precision on a heterogeneous data set from 5 distinct health facilities. However, in 81% of cases where the model disagreed with the documented phenotype, a blinded physician panel agreed with the model. Taken together, this suggests that 4.3% of our studied population have either missing or improper diabetes diagnosis. Conclusions This study demonstrates that deep learning methods can improve clinical phenotyping even when patient data are noisy, sparse, and heterogeneous.

The Special Perils of Being Old and Sick in Prison

2020 ◽  
Vol 32 (5) ◽  
pp. 276-284
Author(s):  
William J. Jefferson
Keyword(s):  
United States ◽  
Health Care ◽  
Medical Care ◽  
Health Care Providers ◽  
The United States ◽  
United States Constitution ◽  
Care Providers ◽  
Medical Practitioners ◽  
Medical Needs ◽  
Access To Medical Care

The United States Supreme Court declared in 1976 that deliberate indifference to the serious medical needs of prisoners constitutes the unnecessary and wanton infliction of pain…proscribed by the Eighth Amendment. It matters not whether the indifference is manifested by prison doctors in their response to the prisoner’s needs or by prison guards intentionally denying or delaying access to medical care or intentionally interfering with treatment once prescribed—adequate prisoner medical care is required by the United States Constitution. My incarceration for four years at the Oakdale Satellite Prison Camp, a chronic health care level camp, gives me the perspective to challenge the generally promoted claim of the Bureau of Federal Prisons that it provides decent medical care by competent and caring medical practitioners to chronically unhealthy elderly prisoners. The same observation, to a slightly lesser extent, could be made with respect to deficiencies in the delivery of health care to prisoners of all ages, as it is all significantly deficient in access, competencies, courtesies and treatments extended by prison health care providers at every level of care, without regard to age. However, the frailer the prisoner, the more dangerous these health care deficiencies are to his health and, therefore, I believe, warrant separate attention. This paper uses first-hand experiences of elderly prisoners to dismantle the tale that prisoner healthcare meets constitutional standards.

Nurse Practitioner Challenges to the Orthodox Structure of Health Care Delivery: Regulation and Restraints on Trade

1985 ◽  
Vol 11 (2) ◽  
pp. 195-225
Author(s):  
Karla Kelly
Keyword(s):  
Health Care ◽  
Health Care Providers ◽  
Health Care Delivery ◽  
Nurse Practitioners ◽  
Nurse Practitioner ◽  
Allied Health ◽  
Care Delivery ◽  
The United States ◽  
Care Providers ◽  
Allied Health Care

AbstractUntil recently, physicians have been the primary health care providers in the United States. In response to the rising health care costs and public demand of the past decade, allied health care providers have challenged this orthodox structure of health care delivery. Among these allied health care providers are nurse practitioners, who have attempted to expand traditional roles of the registered nurse.This article focuses on the legal issues raised by several major obstacles to the expansion of nurse practitioner services: licensing restrictions, third party reimbursement policies, and denial of access to medical facilities and physician back-up services. The successful judicial challenges to discriminatory practices against other allied health care providers will be explored as a solution to the nurse practitioners’ dilemma.

Patients' Perceptions of Different Information Exchange Mechanisms: An Exploratory Study in the United States

2020 ◽  
Vol 59 (04/05) ◽  
pp. 162-178
Author(s):  
Pouyan Esmaeilzadeh
Keyword(s):  
United States ◽  
Health Care ◽  
Health Information ◽  
Health Care Providers ◽  
Information Exchange ◽  
The United States ◽  
Exchange Mechanism ◽  
Care Providers ◽  
Security Risks ◽  
Direct Exchange

Abstract Background Patients may seek health care services from various providers during treatment. These providers could serve in a network (affiliated) or practice separately (unaffiliated). Thus, using secure and reliable health information exchange (HIE) mechanisms would be critical to transfer sensitive personal health information (PHI) across distances. Studying patients' perceptions and opinions about exchange mechanisms could help health care providers build more complete HIEs' databases and develop robust privacy policies, consent processes, and patient education programs. Objectives Due to the exploratory nature of this study, we aim to shed more light on public perspectives (benefits, concerns, and risks) associated with the four data exchange practices in the health care sector. Methods In this study, we compared public perceptions and expectations regarding four common types of exchange mechanisms used in the United States (i.e., traditional, direct, query-based, patient-mediated exchange mechanisms). Traditional is an exchange through fax, paper mailing, or phone calls, direct is a provider-to-provider exchange, query-based is sharing patient data with a central repository, and patient-mediated is an exchange mechanism in which patients can access data and monitor sharing. Data were collected from 1,624 subjects using an online survey to examine the benefits, risks, and concerns associated with the four exchange mechanisms from patients' perspectives. Results Findings indicate that several concerns and risks such as privacy concerns, security risks, trust issues, and psychological risks are raised. Besides, multiple benefits such as access to complete information, communication improvement, timely and convenient information sharing, cost-saving, and medical error reduction are highlighted by respondents. Through consideration of all risks and benefits associated with the four exchange mechanisms, the direct HIE mechanism was selected by respondents as the most preferred mechanism of information exchange among providers. More than half of the respondents (56.18%) stated that overall they favored direct exchange over the other mechanisms. 42.70% of respondents expected to be more likely to share their PHI with health care providers who implemented and utilized a direct exchange mechanism. 43.26% of respondents believed that they would support health care providers to leverage a direct HIE mechanism for sharing their PHI with other providers. The results exhibit that individuals expect greater benefits and fewer adverse effects from direct HIE among health care providers. Overall, the general public sentiment is more in favor of direct data transfer. Our results highlight that greater public trust in exchange mechanisms is required, and information privacy and security risks must be addressed before the widespread implementation of such mechanisms. Conclusion This exploratory study's findings could be interesting for health care providers and HIE policymakers to analyze how consumers perceive the current exchange mechanisms, what concerns should be addressed, and how the exchange mechanisms could be modified to meet consumers' needs.

scholarly journals Patient Suffering in Chronic Digestive Diseases: Will Primary Care-Specialist Collaboration With Effective Interactive Communication and Integrative Medicine in the Plan of Care Improve Quality of Life?

2020 ◽  
Vol 7 (6) ◽  
pp. 989-993
Author(s):  
Andrew Thomas ◽  
Annie Thomas
Keyword(s):  
Quality Of Life ◽  
Primary Care ◽  
Health Care ◽  
Health Care Providers ◽  
The United States ◽  
Care Providers ◽  
Physician Visits ◽  
Digestive Diseases ◽  
Care Specialist

Acute and chronic digestive diseases are causing increased burden to patients and are increasing the United States health care spending. The purpose of this case report was to present how nonconfirmatory and conflicting diagnoses led to increased burden and suffering for a patient thus affecting quality of life. There were many physician visits and multiple tests performed on the patient. However, the primary care physician and specialists could not reach a confirmatory diagnosis. The treatment plans did not offer relief of symptoms, and the patient continues to experience digestive symptoms, enduring this burden for over 2 years. The central theme of this paper is to inform health care providers the importance of utilizing evidence-based primary care specialist collaboration models for better digestive disease outcomes. Consistent with patient’s experience, the authors propose to pilot/adopt the integrative health care approaches that are proven effective for treating digestive diseases.

Pediatric Collections: Vaping: Effects and Solutions

2020 ◽  
Author(s):  
Keyword(s):  
Public Health ◽  
United States ◽  
Health Care ◽  
Health Care Providers ◽  
Electronic Cigarettes ◽  
The United States ◽  
Care Providers ◽  
Tobacco Products ◽  
Pediatric Health ◽  
Pediatric Health Care

Electronic cigarettes are the tobacco products most commonly used by youths in the United States. The use of e-cigarettes, also known as vaping or JUULing, is a public health epidemic. This collection offers reviews and research to assist pediatric health care providers in identifying and treating adolescent use and exposure to e-cigarettes. https://shop.aap.org/pediatric-collections-vaping-effects-and-solutions-paperback/

Fraud and Abuse: United States ex rel Merena v. SmithKline Beecham Corp.; United States ex rel Spear v. SmithKline Beecham Clinical Lab.; United States ex rel Grossenbacher v. SmithKline Beecham Clinical Lab.

2000 ◽  
Vol 28 (2) ◽  
pp. 191-193 ◽  
Author(s):  
Allyson Behm
Keyword(s):  
United States ◽  
Health Care ◽  
Health Care Providers ◽  
Laboratory Tests ◽  
The United States ◽  
Care Providers ◽  
Individual Analysis ◽  
Court Of Appeals ◽  
The Third ◽  
The Government

The United States Court of Appeals for the Third Circuit held that when quitam relators file a multi-claim complaint under the Fraudulent Claims Act (FCA), their share of the proceeds must be based on an individual analysis of each claim. More importantly, the court held that relators are not entitled to any portion of the settlement of a specific claim if that claim was subject to dismissal under section 3730(e)(4) Relator Merena filed a quitam suit against his employer, SmithKline Beecham (SKB), claiming, among other things, that SKB defrauded the government by billing for laboratory tests that were not performed, paying illegal kickbacks to health care providers, and participating in an “automated chemistry” scheme. Soon thereafter, additional relators filed suit.

scholarly journals Community awareness of which seizure type should present to healthcare providers; a potential risk factor of the epilepsy treatment gap

2021 ◽  
Author(s):  
Ismat Babiker ◽  
Mohamed K. Elnaeim ◽  
Awab K.Elnaeim
Keyword(s):  
Health Care ◽  
Health Care Providers ◽  
Demographic Data ◽  
Healthcare Providers ◽  
Seizure Type ◽  
Absence Seizure ◽  
Care Providers ◽  
Treatment Gap ◽  
Cross Sectional ◽  
Epilepsy Treatment

Abstract Objective: the objective of this study was to assess the awareness of the community in Sudan of which seizure type(s) should present to health care providers.Methods: This is a cross-sectional descriptive internet-based survey that was conducted in Sudan during the period from January to April 2018, using google forms. The survey consisted of demographic data (age, gender, educational level), a statement evaluating participants’ sources of obtaining information regarding epilepsy, a statement assessing awareness about the primary care provider for people with epilepsy (PWE), and a statement describing the symptomatology of different seizure types in simple Arabic, asking what description(s) participants thought should present to health care providers. We included participants residing in Sudan, and those with a college degree or higher education. Four hundred sixty-seven participants completed the survey.Results: 467 participants were included, of whom, 279 (60%) were females. The mean age of participants was 28 years. Two-thirds of participants obtained their information from non-scientific sources. 84% of the participants were aware that doctors are the primary health care providers for people with epilepsy.The majority (92.%) of participants were aware that patients with symptoms corresponding to the generalized tonic-clonic seizure description should present to doctors, compared with two-thirds of participants for focal seizure symptom description, and only 30.6 % of participants for absence seizure symptom description.Conclusion: This study demonstrated poor awareness about the necessity of presentation for focal and absence seizures. We hypothesize that this lack of awareness may contribute to the epilepsy treatment gap, and we recommend further studies to examine this hypothesis.

Disparities in Pediatric Oncology: The 21st Century Opportunity to Improve Outcomes for Children and Adolescents With Cancer

2021 ◽  
pp. e315-e326
Author(s):  
Paula Aristizabal ◽  
Lena E. Winestone ◽  
Puja Umaretiya ◽  
Kira Bona
Keyword(s):  
United States ◽  
Health Care ◽  
Children And Adolescents ◽  
Health Care Providers ◽  
21St Century ◽  
Low Socioeconomic Status ◽  
Pediatric Cancer ◽  
The United States ◽  
Cancer Disparities ◽  
Care Providers

Adult cancer disparities have been documented for decades and continue to persist despite clinical advancements in cancer prevention, detection, and treatment. Pediatric cancer survival has improved significantly in the United States for the past 5 decades to over 80%; however, disparate outcomes among children and adolescents with cancer still affect many populations in the United States and globally, including racial and ethnic minorities, populations with low socioeconomic status, and residents of underserved areas. To achieve equitable outcomes for all children and adolescents with cancer, it is imperative that concerted multilevel approaches be carried out to understand and address health disparities and to ensure access to high-quality cancer care. Addressing social determinants of health, such as removing barriers to health care access and ensuring access to social supports, can reduce pediatric cancer disparities. Nevertheless, public health policy, health system interventions, and innovative delivery of evidence-based services are critically needed. Partnerships among patients, caregivers, and health care providers, and among health care, academic, and governmental institutions, have a pivotal role in reducing cancer disparities and improving outcomes in the 21st century.

Sign in / Sign up

Export Citation Format

Share Document