China
Africa
Explore chapters and articles related to this topic
Machine Learning Results for High Utilizers
Published in Chengliang Yang, Chris Delcher, Elizabeth Shenkman, Sanjay Ranka, Data-Driven Approaches for Health care, 2019
Chengliang Yang, Chris Delcher, Elizabeth Shenkman, Sanjay Ranka
For this study, we used administrative insurance claims from the Texas Medicaid program and included adults (ages 18-65) whose enrollment status was maintained for more than two-thirds of the time for any period-of-interest (either observed or forecasted). Likewise, we excluded patients who were enrolled for very short periods of time or who had highly-variable health care profiles relative to the general Medicaid population. This study aimed to predict total medical expenditures, including professional, institutional, and dental claims. Pharmacy expenditures were not included. For both models, we used the final paid amounts to represent expenditures. Variables available included diagnosis codes (International Classification of Diseases, Ninth Revision, Clinical Modification, ICD-9-CM), procedure codes (ICD-9-CM procedure codes, Current Procedural Terminology [CPT] and Healthcare Common Procedure Coding System [HCPCS]), and medication codes (National Drug Codes [NDC]). During the study period, 3,233 unique ICD-9-CM procedure codes, 21,374 unique ICD-9-CM diagnosis codes, 21,603 unique CPT and HCPCS codes, and 28,366 NDC codes were identified.
Services
Published in Emmanuel Tsekleves, Rachel Cooper, Design for Health, 2017
Seventy thousand diagnosis codes for presented illnesses and incidents are distinguished in the recently institutionalised International Classification of Diseases Rev. 10 (ICD-10; World Health Organization, 2010) used as standard references for diagnoses, procedures and billing. ICD codes are useful for aggregating descriptive statistics of measured health problems in a community, based on presentation and diagnosis. They include a significant section on psychosocial problems (health hazards related to socioeconomic and psychosocial circumstances) which support epidemiological and public health statistics. The codes also constrain the range of the care envelope, in that while social conditions might be identified by codes, only certain codes and procedures are amenable to billing reimbursement by payers, and social determinants are not among these. In practice, physicians record the codes that define the illness at hand, and even if there might be psychosocial drivers (unemployment or low income, environmental hazards) these are often rendered secondary and not considered options for intervention.
Selected characteristics and injury patterns by age group among pedestrians treated in North Carolina emergency departments
Published in Traffic Injury Prevention, 2020
Katherine J. Harmon, Kari A. Hancock, Anna E. Waller, Laura S. Sandt
The NC Division of Public Health (NC DPH) provided ED visit data. NC DPH captures information on all patients treated at 24/7 acute care hospital-affiliated civilian NC EDs, as part of NC DETECT, NC’s legislatively mandated statewide syndromic surveillance system (Carolina Center for Health Informatics 2020). For inclusion in the study, the pedestrian ED visit record had to contain an International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) injury diagnosis code (800–999) or external cause of injury code (E-code; National Center for Health Statistics, Centers for Disease Control and Prevention 2015). To avoid one-to-many linkages, patient transfers to other health care institutions were excluded.