Explore chapters and articles related to this topic
Machine Learning for Disease Classification: A Perspective
Published in Kayvan Najarian, Delaram Kahrobaei, Enrique Domínguez, Reza Soroushmehr, Artificial Intelligence in Healthcare and Medicine, 2022
Jonathan Parkinson, Jonalyn H. DeCastro, Brett Goldsmith, Kiana Aran
It is of course crucial that the data is labeled correctly, and this may represent a challenge for biomedical applications in general. International Classification of Disease (ICD) codes, for example, are often used to indicate diagnoses in electronic health records (EHR). Errors in ICD code assignment are however not infrequent – estimates of the accuracy of ICD coding vary widely – and may arise from multiple possible sources of error (O’Malley et al., 2005). Physicians sometimes for example use abbreviations in their notes whose meaning may be ambiguous to the medical coder responsible for selecting and entering an appropriate diagnosis code (Sheppard et al., 2008).
Study Limitations to Consider
Published in Lisa Chasan-Taber, Writing Grant Proposals in Epidemiology, Preventive Medicine, and Biostatistics, 2022
Almost all forms of outcome assessment are subject to some degree of misclassification. Potential misclassification (error) includes inaccuracies in outcome measurement. These include reliance on proxy respondents, self-report, or recall. Even medical records or International Classification of Diseases (ICD) codes, often considered a gold standard, are subject to error. For example, medical records may be completed by a variety of personnel including residents, attending physicians, and nurse midwives. In addition, coders assign ICD codes based on notes recorded in the medical record. Any of these personnel can make an error in recording key information in the medical record or in selecting the appropriate diagnostic code. There may also be error associated with the technique used to abstract data from the medical record.
STATISTICAL EVALUATION OF THE RISK OF CANCER MORTALITY AMONG INDUSTRIAL POPULATIONS
Published in Richard G. Cornell, Statistical Methods for Cancer Studies, 2020
Michael J. Symons, John D. Taulbee
(3) Tabulate the deaths into categories of the various variables of interest. For these deaths, Tables 2 and 3 are sufficient. Table 3 corresponds to the categorization of the professionally nosologized death certificates. The International Classification of Diseases Adapted (ICDA), 8th Revision was considered appropriate given that the study period runs from 1 January 1950 through 31 December 1977. U.S. general population figures for 1968 were used. The choice of the comparison population is discussed more with the next example and in Section III C.
Colombian ocular infectious epidemiology study (COIES): presumed ocular tuberculosis incidence and sociodemographic characterization, 2015–2020
Published in Ophthalmic Epidemiology, 2023
Carlos Cifuentes-González, Doménico Barraquer-López, Germán Mejía-Salgado, Juliana Reyes-Guanes, William Rojas-Carabali, Diego Polanía-Tovar, Alejandra de-la-Torre
The information and data in this study were obtained from the national database created by the Colombian Ministry of Health, known as the System of Information of Social Protection (SISPRO).17 Its function is to store, process, and systematize Colombian citizens’ information to make decisions that support the development of effective policies and monitoring in sectors, such as health, pensions, occupational risks, and social promotion. Health data is collected and codified by medical staff during each medical contact (inpatient or outpatient) from private and public health providers and insurers using the International Classification of Diseases (ICD-10). All this demographic and clinical data are grouped in the Individual Records of Health Service Provision (RIPS).18 Also, it should be noted that the Colombian Health System has one of the most prominent coverages in Latin America, encompassing 49 million inhabitants that represent the 97.78% of the population in 2020, according to the most recent measurement.19
Werewolves and Two-Headed Monsters: An Exploration of Coping, Sharing, and Processing of Premenstrual Distress Among Individuals With PMDD on an Anonymous Internet Message Board
Published in Women's Reproductive Health, 2023
Autumn Winslow, Laura Hooberman, Lisa Rubin
PMDD is characterized in the DSM-5 by a wide range of symptoms similar to those seen in other mood disorders (e.g., affective lability, irritability/anger, increased interpersonal conflict, depressed mood, anxiety, sleep difficulties), occurring in the week before menses, improving in the first few days of menses, and subsiding or become minimal in the week post-menses (APA, 2013). Furthermore, symptoms must be associated with “clinically significant distress or interference with work, school, usual social activities, or relationships with others” (APA, 2013, p. 172). In addition to the American Psychiatric Association’s definition, the International Classification of Diseases 11th Revision (ICD-11) includes a code for PMDD with comparable criteria (World Health Organization, 2018). Although many potential biological correlates of PMDD have been explored in research (O’Brien et al., 2007), at this time a conclusive biological cause has not been identified (Freeman, 2017).
Trends in Endogenous Endophthalmitis in Rural and Urban Settings in the United States
Published in Ophthalmic Epidemiology, 2023
Aditya Uppuluri, Marco A. Zarbin, Neelakshi Bhagat
For each included admission, the NIS Database provides information on demographic data, hospitalization details (cost of stay, length of stay, insurance status, etc.), chronic health conditions, acute medical conditions, and in-hospital procedures. Documentation of medical diagnoses and inpatient procedures is limited to those coded by the International Classification of Diseases, Ninth Revision (ICD-9). The NIS Database does not include diagnoses from outpatient health records unless they are coded again during the inpatient stay by the provider. Similarly, records from long-term care facilities and rehabilitation centers are not included in the NIS Database’s data collection process. Furthermore, the NIS Database does not follow patients longitudinally and does not provide information regarding a patient’s healthcare after discharge.