The Effects of Tobacco Coverage in the Public Communication Environment on Young People's Decisions to Smoke Combustible Cigarettes

In today's complex media environment, does media coverage influence youth and young adults' (YYA) tobacco use and intentions? We conceptualize the "public communication environment" and effect mediators, then ask whether over time variation in exogenously measured tobacco media coverage from mass and social media sources predicts daily YYA cigarette smoking intentions measured in a rolling nationally representative phone survey (N = 11,847 on 1,147 days between May 2014 and June 2017). Past week anti-tobacco and pro-tobacco content from Twitter, newspapers, broadcast news, Associated Press, and web blogs made coherent scales (thetas = 0.77 and 0.79). Opportunities for exposure to anti-tobacco content in the past week predicted lower intentions to smoke (Odds ratio [OR] = 0.95, p < .05, 95% confidence interval [CI] = 0.91-1.00). The effect was stronger among current smokers than among nonsmokers (interaction OR = 0.88, p < .05, 95% CI = 0.77-1.00). These findings support specific effects of anti-tobacco media coverage and illustrate a productive general approach to conceptualizing and assessing effects in the complex media environment.

A Deep Learning Framework for Automated ICD-10 Coding

The International Statistical Classification of Diseases and Related Health Problems (ICD) is one of the widely used classification system for diagnoses and procedures to assign diagnosis codes to Electronic Health Record (EHR) associated with a patient's stay. The aim of this paper is to propose an automated coding system to assist physicians in the assignment of ICD codes to EHR. For this purpose, we created a pipeline of Natural Language Processing (NLP) and Deep Learning (DL) models able to extract the useful information from French medical texts and to perform classification. After the evaluation phase, our approach was able to predict 346 diagnosis codes from heterogeneous medical units with an accuracy average of 83%. Our results were finally validated by physicians of the Medical Information Department (MID) in charge of coding hospital stays.

Computer-Based Coding of Occupation Codes for Epidemiological Analyses

Mapping job titles to standardized occupation classification (SOC) codes is an important step in evaluating changes in health risks over time as measured in inspection databases. However, manual SOC coding is cost prohibitive for very large studies. Computer based SOC coding systems can improve the efficiency of incorporating occupational risk factors into large-scale epidemiological studies. We present a novel method of mapping verbatim job titles to SOC codes using a large table of prior knowledge available in the public domain that included detailed description of the tasks and activities and their synonyms relevant to each SOC code. Job titles are compared to our knowledge base to find the closest matching SOC code. A soft Jaccard index is used to measure the similarity between a previously unseen job title and the knowledge base. Additional information such as standardized industrial codes can be incorporated to improve the SOC code determination by providing additional context to break ties in matches.