Enhanced surveillance of syphilis cases among men who have sex with men in London, October 2016-January 2017.

Syphilis rates have been increasing in men who have sex with men (MSM) in London. To describe risk behaviour and refine public health interventions, we conducted prospective enhanced surveillance of new syphilis cases in MSM attending selected London sexual health clinics (SHCs) between October 2016 and January 2017. Sexual health advisors (SHAs) completed 107 questionnaires. Eighteen per cent of respondents reported always using condoms, with lower use in HIV-positive (8%, 4/53) than HIV-negative men (33%, 14/52). Almost half of respondents reported condomless sero-discordant sex (46%, 33/72). The most frequent means of meeting new partners reported were venues (80%, 76/95), particularly bars or clubs (34%, 32/95), and apps or websites (79%, 75/95). Nearly a third of respondents reported engaging in group sex (32%, 30/95). Almost half reported drug use during sex (47%, 46/98), with HIV-positive men more likely to report use of the three main 'chemsex' drugs. The majority of respondents preferred health promotion information from SHAs (63%, 58/92) compared to other sources such as Google/Wikipedia and apps. Prevention activity should continue to focus on condomless sex, serosorting, multiple and overlapping partners, and chemsex. SHCs, particularly those serving HIV-positive men, are important sources for sexual health promotion advice.

Improving identification of fall-related injuries in ambulatory care using statistical text mining.

OBJECTIVES: We determined whether statistical text mining (STM) can identify fall-related injuries in electronic health record (EHR) documents and the impact on STM models of training on documents from a single or multiple facilities. METHODS: We obtained fiscal year 2007 records for Veterans Health Administration (VHA) ambulatory care clinics in the southeastern United States and Puerto Rico, resulting in a total of 26 010 documents for 1652 veterans treated for fall-related injury and 1341 matched controls. We used the results of an STM model to predict fall-related injuries at the visit and patient levels and compared them with a reference standard based on chart review. RESULTS: STM models based on training data from a single facility resulted in accuracy of 87.5% and 87.1%, F-measure of 87.0% and 90.9%, sensitivity of 92.1% and 94.1%, and specificity of 83.6% and 77.8% at the visit and patient levels, respectively. Results from training data from multiple facilities were almost identical. CONCLUSIONS: STM has the potential to improve identification of fall-related injuries in the VHA, providing a model for wider application in the evolving national EHR system.

Finding falls in ambulatory care clinical documents using statistical text mining.

OBJECTIVE: To determine how well statistical text mining (STM) models can identify falls within clinical text associated with an ambulatory encounter. MATERIALS AND METHODS: 2241 patients were selected with a fall-related ICD-9-CM E-code or matched injury diagnosis code while being treated as an outpatient at one of four sites within the Veterans Health Administration. All clinical documents within a 48-h window of the recorded E-code or injury diagnosis code for each patient were obtained (n=26 010; 611 distinct document titles) and annotated for falls. Logistic regression, support vector machine, and cost-sensitive support vector machine (SVM-cost) models were trained on a stratified sample of 70% of documents from one location (dataset Atrain) and then applied to the remaining unseen documents (datasets Atest-D). RESULTS: All three STM models obtained area under the receiver operating characteristic curve (AUC) scores above 0.950 on the four test datasets (Atest-D). The SVM-cost model obtained the highest AUC scores, ranging from 0.953 to 0.978. The SVM-cost model also achieved F-measure values ranging from 0.745 to 0.853, sensitivity from 0.890 to 0.931, and specificity from 0.877 to 0.944. DISCUSSION: The STM models performed well across a large heterogeneous collection of document titles. In addition, the models also generalized across other sites, including a traditionally bilingual site that had distinctly different grammatical patterns. CONCLUSIONS: The results of this study suggest STM-based models have the potential to improve surveillance of falls. Furthermore, the encouraging evidence shown here that STM is a robust technique for mining clinical documents bodes well for other surveillance-related topics.

Using ensemble models to classify the sentiment expressed in suicide notes.

In 2007, suicide was the tenth leading cause of death in the U.S. Given the significance of this problem, suicide was the focus of the 2011 Informatics for Integrating Biology and the Bedside (i2b2) Natural Language Processing (NLP) shared task competition (track two). Specifically, the challenge concentrated on sentiment analysis, predicting the presence or absence of 15 emotions (labels) simultaneously in a collection of suicide notes spanning over 70 years. Our team explored multiple approaches combining regular expression-based rules, statistical text mining (STM), and an approach that applies weights to text while accounting for multiple labels. Our best submission used an ensemble of both rules and STM models to achieve a micro-averaged F(1) score of 0.5023, slightly above the mean from the 26 teams that competed (0.4875).

Is the recall of men who have sex with men (MSM) diagnosed as having bacterial sexually transmitted infections (STIs) for re-screening a feasible and effective strategy?

OBJECTIVES: To assess the feasibility and outcomes of recalling men who have sex with men (MSM) diagnosed as having a bacterial sexually transmitted infection (STI) for re-screening. METHODS: This evaluation was conducted from December 2008 for a 9-month period. MSM diagnosed as having a bacterial STI in that period were offered recall for re-screening 3 months after their diagnosis. Re-screening rates and infection incidence were calculated. Differences in baseline characteristics by re-screening status and factors predictive of infection at re-screening were assessed using the Mann-Whitney test, χ(2) test and logistic regression. RESULTS: Of the 337 MSM diagnosed as having a bacterial STI, 301 were offered recall. Of these, 206 (68.4%) re-screened after 3 months, 30 (10%) declined and the remainder did not re-attend despite giving verbal consent. Compared with those not re-screening, those re-screening were less likely to be HIV positive (p=0.001), but there was no difference in baseline risk behaviours. There were 15 diagnoses of bacterial STIs at re-screening (29 per 100 person-year follow-up (pyfu); 95% CI 14.3 to 43.7) and five new HIV diagnoses of whom three had a negative test at baseline, one tested negative 6 months earlier and one never tested. Among those testing at both time points, the HIV incidence was 8.3 per 100 pyfu (95% CI 0.0 to 17.7). CONCLUSIONS: This evaluation demonstrates a 'recall for re-screening' strategy is feasible in terms of high re-screening rates and incidence of new infections diagnosed. Experimental evidence is needed to assess cost-effectiveness and whether it achieves its aim of reducing transmission of STIs and HIV.

Throw the bath water out, keep the baby: keeping medically-relevant terms for text mining.

The purpose of this research is to answer the question, can medically-relevant terms be extracted from text notes and text mined for the purpose of classification and obtain equal or better results than text mining the original note? A novel method is used to extract medically-relevant terms for the purpose of text mining. A dataset of 5,009 EMR text notes (1,151 related to falls) was obtained from a Veterans Administration Medical Center. The dataset was processed with a natural language processing (NLP) application which extracted concepts based on SNOMED-CT terms from the Unified Medical Language System (UMLS) Metathesaurus. SAS Enterprise Miner was used to text mine both the set of complete text notes and the set represented by the extracted concepts. Logistic regression models were built from the results, with the extracted concept model performing slightly better than the complete note model.