scholarly journals Automated identification of diagnostic labelling errors in medicine

Diagnosis ◽  
2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Wolf E. Hautz ◽  
Moritz M. Kündig ◽  
Roger Tschanz ◽  
Tanja Birrenbach ◽  
Alexander Schuster ◽  
...  

Abstract Objectives Identification of diagnostic error is complex and mostly relies on expert ratings, a severely limited procedure. We developed a system that allows to automatically identify diagnostic labelling error from diagnoses coded according to the international classification of diseases (ICD), often available as routine health care data. Methods The system developed (index test) was validated against rater based classifications taken from three previous studies of diagnostic labeling error (reference standard). The system compares pairs of diagnoses through calculation of their distance within the ICD taxonomy. Calculation is based on four different algorithms. To assess the concordance between index test and reference standard, we calculated the area under the receiver operating characteristics curve (AUROC) and corresponding confidence intervals. Analysis were conducted overall and separately per algorithm and type of available dataset. Results Diagnoses of 1,127 cases were analyzed. Raters previously classified 24.58% of cases as diagnostic labelling errors (ranging from 12.3 to 87.2% in the three datasets). AUROC ranged between 0.821 and 0.837 overall, depending on the algorithm used to calculate the index test (95% CIs ranging from 0.8 to 0.86). Analyzed per type of dataset separately, the highest AUROC was 0.924 (95% CI 0.887–0.962). Conclusions The trigger system to automatically identify diagnostic labeling error from routine health care data performs excellent, and is unaffected by the reference standards’ limitations. It is however only applicable to cases with pairs of diagnoses, of which one must be more accurate or otherwise superior than the other, reflecting a prevalent definition of a diagnostic labeling error.

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Tanvi Garg ◽  
Navid Kagalwalla ◽  
Shubha Puthran ◽  
Prathamesh Churi ◽  
Ambika Pawar

Purpose This paper aims to design a secure and seamless system that ensures quick sharing of health-care data to improve the privacy of sensitive health-care data, the efficiency of health-care infrastructure, effective treatment given to patients and encourage the development of new health-care technologies by researchers. These objectives are achieved through the proposed system, a “privacy-aware data tagging system using role-based access control for health-care data.” Design/methodology/approach Health-care data must be stored and shared in such a manner that the privacy of the patient is maintained. The method proposed, uses data tags to classify health-care data into various color codes which signify the sensitivity of data. It makes use of the ARX tool to anonymize raw health-care data and uses role-based access control as a means of ensuring only authenticated persons can access the data. Findings The system integrates the tagging and anonymizing of health-care data coupled with robust access control policies into one architecture. The paper discusses the proposed architecture, describes the algorithm used to tag health-care data, analyzes the metrics of the anonymized data against various attacks and devises a mathematical model for role-based access control. Originality/value The paper integrates three disparate topics – data tagging, anonymization and role-based access policies into one seamless architecture. Codifying health-care data into different tags based on International Classification of Diseases 10th Revision (ICD-10) codes and applying varying levels of anonymization for each data tag along with role-based access policies is unique to the system and also ensures the usability of data for research.


PEDIATRICS ◽  
1986 ◽  
Vol 78 (6) ◽  
pp. 1148-1149
Author(s):  

The Apgar score, devised in 1952 by Dr Virginia Apgar, is a quick method of assessing the state of the newborn infant.1,2 The ease of scoring has led to its use in many studies of outcome. However, its misuse, as in current International Classification of Diseases, revision 9, coding, has led to an erroneous definition of asphyxia.* Although the Apgar score continues to provide a convenient shorthand for reporting the state of the baby and the effectiveness of resuscitation, the purpose of this statement is to place the Apgar score in its proper perspective as a tool for assessing asphyxia and for prognostication of future neurologic deficit. The Apgar score is comprised of five components: heart rate, respiratory effort, tone, reflex irritability, and color, each of which can be given a score of 0, 1, or 2 (Table). FACTORS THAT MAY AFFECT THE APGAR SCORE Although rarely stated, it is important to recognize that elements of the score such as tone, color, and reflex irritability are partially dependent on the physiologic maturity of the infant. The normal premature infant may thus receive a low score purely because of immaturity with no evidence of anoxic insult or cerebral depression. Maternal sedation or analgesia may decrease tone and responsiveness. Neurologic conditions such as muscle disease or cerebral malformations may decrease tone and interfere with respiration. Cardiorespiratory conditions may interfere with heart rate, respiration, and tone. Thus, to equate the presence of a low Apgar score solely with asphyxia represents a misuse of the score.


2017 ◽  
Vol 25 (6) ◽  
pp. 287-290 ◽  
Author(s):  
GIOVANNA DAMM RAPHAEL JUNQUEIRA ◽  
ANDRÉ LUIZ MACHADO LIMA ◽  
ROBISON BONI ◽  
JOELMAR CÉSAR DE ALMEIDA ◽  
RAFAEL SOUZA RIBEIRO ◽  
...  

ABSTRACT Objectives: A retrospective statistical data gathering of wrist and hand complaints assisted over two years in the orthopedic emergency department of a regional referral hospital, seeking to know the profile of these patients. Methods: Information obtained by analysis of 31.356 orthopedic visits from May 2013 to April 2015, of which 6.754 related to hand complaints and/or wrist, at the Hospital Estadual Doutor Jayme dos Santos Neves (HDJSN) and analyzed by IBM SPSS Statistics software version 21. Results: The data revealed that the average age was 37,5 ± 15,7 years and the male gender was predominant (60,72%). Bruises (52,58%) and fractures (30,49%) were the most common diagnoses. Conclusion: The complaints of wrist and hand accounted for 21,44% of all orthopedic emergency room visits. Detailed data description and correct definition of the International Classification of Diseases (ICD-10) are needed to better define the epidemiological profile of patients seeking orthopedic emergency. Level of Evidence III, Retrospective Study.


2011 ◽  
Vol 58 (3) ◽  
pp. 127-138 ◽  
Author(s):  
Milena Gajic-Stevanovic ◽  
Snezana Dimitrijevic ◽  
Slavoljub Zivkovic ◽  
Nevenka Teodorovic ◽  
Darinka Perisic-Rajnicke

Introduction. As the part of research on costs in the health care system, there is a growing interest in the world for the estimating costs for the treatment of disease. This value represents the burden that a particular disease or group of diseases puts on the society. Until the year 2000, when the Organization for Economic Countries Development (OECD) established a System of Health Accounts (SHA), there was not even approximate methodological guide for calculating the cost of the disease. The aim of this study was to determine the costs of health care in the Republic of Serbia according to the major International Classification of Diseases (ICD-10) and to provide a comparative cost analysis for the treatment of diseases in the period from 2004 to 2009. Material and Methods. A retrospective and comparative analysis of health statistics from the database of the Institute of Public Health of Serbia and financial information provided by the Health Insurance Fund in the period 2004-2009 was performed. Financial information and data on hospital services, outpatient, home health care, ancillary health care services, drug consumption and consumer goods in healthcare were analyzed using SHA methodology. Results. Results showed that during the observation period, the maximum cost of health care in Serbia by main classification of ICD-10 was achieved in 2009 and it was RSD 144,150,456,906.00 (? 1,503,321,134; $ 2,160,253,219) and the minimal cost was achieved in 2004 - the amount being RSD 49,546,211,470.00 (? 628,086,723; $ 855,203,134). Results showed that in 2004 the highest costs were allocated to circulatory diseases (18.98%), followed by neoplasm (11.12%), and lowest for congenital anomalies (0.64%). In 2009, the highest costs were allocated to circulatory diseases (18.87%), infectious and parasitic diseases (11.20%), diseases of digestive system (9.26%) nervous system diseases (9.20%), and neoplasm (8.88%), whereas the minimal funds were allocated for congenital anomalies (0.33%). Conclusion. Comparative analysis showed that the value of overall spending in healthcare increased three times in 2009 as compared to 2004.


Author(s):  
Jan Willer

Understanding the symptoms of adult ADHD is an essential starting place. Diagnostic and Statistical Manual of Mental Disorders symptoms of ADHD are reviewed, including inattention/distractibility, impulsiveness, and hyperactivity, as well as other adult ADHD symptoms that have been well documented in multiple research studies. Suggested interview questions for each symptom are presented. Additional adult ADHD symptoms include executive functioning deficits, emotional dysregulation, atypical reward sensitivity, and time perception differences. Sluggish cognitive tempo is also defined and a case example given. Last, progress towards a new definition of ADHD is presented, and the practicalities of diagnosing ADHD using the International Classification of Diseases, 10th Revision, are discussed.


Trauma ◽  
2018 ◽  
Vol 21 (4) ◽  
pp. 301-309
Author(s):  
Mattias Sterner ◽  
Jonatan Attergrim ◽  
Alice Claeson ◽  
Vineet Kumar ◽  
Monty Khajanchi ◽  
...  

Introduction Trauma accounts for 9% of all deaths worldwide, killing almost five million people annually. As India accounts for more than one million of these deaths, research on local trauma care is of great importance. A key aspect of such research is outcome comparisons between contexts. One tool to adjust these comparisons for trauma severity is the International Classification of Diseases Injury Severity Score. The aim was to assess two versions of this score in India. Methods The data used were from the project Towards Improved Trauma Care Outcomes in India. Published survival risk ratios were used to calculate multiplicative-International Classification of Diseases Injury Severity Score and single-worst-injury-International Classification of Diseases Injury Severity Score for the 200 most recent non-surviving patients and the surviving patients during the same period. Score performance was measured in discrimination and calibration. Results The 30-day prediction single-worst-injury-International Classification of Diseases Injury Severity Score discriminated best with an area under the receiver operating characteristics curve of 0.668 (95% CI 0.645–0.690) and a calibration slope of 0.830 (95% CI 0.708–0.940). Conclusions The single-worst-injury-International Classification of Diseases Injury Severity Score applied on 30-day mortality was the only score to calibrate on a satisfactory level. None of the scores had an acceptable discrimination. In interpreting these findings, we see that none of the tested scores can currently be implemented in the studied hospitals.


2021 ◽  
Vol 10 (1) ◽  
pp. 149-158
Author(s):  
Susumu Higuchi ◽  
Hideki Nakayama ◽  
Takanobu Matsuzaki ◽  
Satoko Mihara ◽  
Takashi Kitayuguchi

AbstractBackground and aimsThe World Health Organization included gaming disorder (GD) in the eleventh revision of International Classification of Diseases in 2019. Due to the lack of diagnostic tools for GD, a definition has not been adequately applied. Therefore, this study aimed to apply an operationalized definition of GD to treatment-seekers. The relationship between the diagnoses of GD and Internet gaming disorder (IGD) in the fifth edition of the Diagnostic and Statistical Manual of Mental Disorders was also examined. Methods: Study participants comprised 241 treatment-seekers who had engaged in excessive gaming and experienced related problems. Psychiatrists applied the GD diagnostic criteria to the participants using a diagnostic form developed for this study. Information on gaming behavior and functional impairment was obtained through face-to-face interviews conducted by clinical psychologists. Results: In total, 78.4 and 83.0% of the participants fulfilled the GD and IGD diagnostic criteria, respectively. The sensitivity and specificity of GD diagnosis were both high when the IGD diagnosis was used as the gold standard. Participants with GD preferred online PC and console games, spent significantly more time gaming, and showed a higher level of functional impairment compared to those who did not fulfill the GD diagnostic criteria. Discussion and Conclusion: The definition of GD can be successfully applied to treatment-seekers with excessive gaming and related problems. A high concordance of GD and IGD diagnoses was found in those participants with relatively severe symptoms. The development and validation of a diagnostic tool for GD should be explored in future studies.


1989 ◽  
Vol 154 (S4) ◽  
pp. 42-46 ◽  
Author(s):  
Juan E. Mezzich

The facts that neither the International Classification of Diseases (ICD) nor any other major standard diagnostic system have offered a full definition of psychiatric illness and that earnest definitional attempts reported in the literature (e.g. Spitzer & Endicott, 1978) have not received wide acceptance, have led distinguished nosologists (e.g. Kendell, 1985) to suggest that all we can say about psychiatric classifications is that they are classifications of kinds of problems which psychiatrists currently deal with. However, one immediate difficulty with this characterisation is that it is based on what psychiatrists do, when in fact psychiatric problems are dealt with also by other professionals of various types and levels of training. Another difficulty is that it implies that there is not even an approximate common denominator or core concept underlying the various forms of psychiatric disorder listed in the ICD or other standard diagnostic systems.


Sign in / Sign up

Export Citation Format

Share Document