Search

Objectives: Natural language processing (NLP) represents one of the adjunct technologies within artificial intelligence and machine learning, creating structure out of unstructured data. This study aims to assess the performance of employing NLP to identify and categorize unstructured data within the emergency medicine (EM) setting. Methods: We systematically searched publications related to EM research and NLP across databases including MEDLINE, Embase, Scopus, CENTRAL, and ProQuest Dissertations & Theses Global. Independent reviewers screened, reviewed, and evaluated article quality and bias. NLP usage was categorized into syndromic surveillance, radiologic interpretation, and identification of specific diseases/events/syndromes, with respective sensitivity analysis reported. Performance metrics for NLP usage were calculated and the overall area under the summary of receiver operating characteristic curve (SROC) was determined. Results: A total of 27 studies underwent meta‐analysis. Findings indicated an overall mean sensitivity (recall) of 82%–87%, specificity of 95%, with the area under the SROC at 0.96 (95% CI 0.94–0.98). Optimal performance using NLP was observed in radiologic interpretation, demonstrating an overall mean sensitivity of 93% and specificity of 96%. Conclusions: Our analysis revealed a generally favorable performance accuracy in using NLP within EM research, particularly in the realm of radiologic interpretation. Consequently, we advocate for the adoption of NLP‐based research to augment EM health care management. [ABSTRACT FROM AUTHOR]

In health economics, the use of patient recall of health care utilisation information is common, including in national health surveys. However, the types and magnitude of measurement error that relate to different recall periods are not well understood. This study assessed the accuracy of recalled doctor visits over 2-week, 3-month, and 12-month periods by comparing self-report with routine administrative Australian Medicare data. Approximately 5,000 patients enrolled in an Australian study were pseudo-randomised using birth dates to report visits to a doctor over three separate recall periods. When comparing patient recall with visits recorded in administrative information from Medicare Australia, both bias and variance were minimised for the 12-month recall period. This may reflect telescoping that occurs with shorter recall periods (participants pulling in important events that fall outside the period). Using shorter recall periods scaled to represent longer periods is likely to bias results. There were associations between recall error and patient characteristics. The impact of recall error is demonstrated with a cost-effectiveness analysis using costs of doctor visits and a regression example predicting number of doctor visits. The findings have important implications for surveying health service utilisation for use in economic evaluation, econometric analyses, and routine national health surveys. [ABSTRACT FROM AUTHOR]

The Food Intake Recording Software System, version 4 ( firsst 4), is a web-based 24-h dietary recall (24 hdr) self-administered by children based on the Automated Self-Administered 24-h recall (ASA24) (a self-administered 24 hdr for adults). The food choices in firsst 4 are abbreviated to include only those reported by children in US national surveys; and detailed food probe questions are simplified to exclude those that children could not be expected to answer (e.g. questions regarding food preparation and added fats). ASA24 and firsst 4 incorporate 10 000+ food images, with up to eight images per food, to assist in portion size estimation. We review the formative research conducted during the development of firsst 4. When completed, firsst 4 will be hosted and maintained for investigator use on the National Cancer Institute's ASA24 website. [ABSTRACT FROM AUTHOR]

Implantable cardioverter-defibrillator (ICD) malfunctions sometimes need recall. Despite the increasing number of device implantation, ICD recalls and advisories' impacts have been little studied. The aim of this study was to determine the rate of ICD generator advisory in our center and to examine its clinical and financial implication. We analyzed weekly Food and Drug Administration (FDA) Enforcement Reports issued between January 2000 and December 2008 to identify all advisories involving ICD generators and leads. We performed a retrospective analysis of all implanted patients affected by an advisory in our Cardiology department. During the 8 years of the study period, 13 advisories were issued for generators and one for leads, leading to a total number of 278 of 1,051 (26.4%) device with recall alerts, divided into 196 generator failures and 82 lead failures. Premature generator replacement was performed in 11 patients, whereas nine patients underwent lead replacement. There was no major complications attributable to advisory device replacement, and minor complications occurred only in one patient (lead extraction failure). Recalls accounted for 593 extra outpatient visits with a mean number of 2.20 ± 2.19 per patient. The total estimated cost of the device advisories in our population was 334,528 €. ICD recalls and safety alerts frequently occur in ICD recipients and tend to increase in number and rate. Although potentially serious, they do not appear to be associated with substantial complications. Financial implications are important. (PACE 2011; 96-103) [ABSTRACT FROM AUTHOR]

The article presents a study which examines the systematic progress of an occupational history calendar (OHC) in working population and compares the traditional questionnaire method and OHC in terms of data quality. The study illustrates the design of an OHC which involves occupational accounts of farmers in the U.S. Results of the study reveal that OHC has improved work recall while data conformity was observed on both OHC and questionnaire method.

Purpose: This study surveyed program directors of Advanced Education Programs in Prosthodontics (AEPP) in the United States to determine the extent, type, incidence, and perceived effectiveness of implemented recall systems. Material and Methods: Surveys were sent to AEPP directors across the United States to assess their program's recall protocol. This survey first identified whether an active recall program existed. For programs with recall systems, rigor in promoting ongoing oral health was surveyed by focusing on recall frequency, patient tracking protocol, involved personnel, interaction with other university departments, provided clinical procedures, and therapy completion protocol. Whether the directors perceived that their recall system was successful was also investigated. Results: Thirty-three of 46 programs responded, giving a response rate of 72%. Of these 33 programs, only 21 (64%) had an active recall system, although 30 (91%) believed recall to be important. Twelve (57%) directors with recall programs considered their system to be effective. Conclusions: Prosthodontic program directors felt their program's recall effectiveness could be improved. Due to the numerous potential benefits of an active recall system, AEPPs should consider implementing or enhancing their recall programs. Further studies are indicated to determine specific criteria that describe an effective recall system for prosthodontic programs within the context of patient health promotion, program curriculum, and financial ramifications. [ABSTRACT FROM AUTHOR]