The evolution of Health & Place: Text mining papers published between 1995 and 2018

Trends in major intensive care medicine journals: A machine learning approach

PURPOSE

Intensive care medicine (ICM) has the particularity of being a multidisciplinary specialty and its literature reflects this multidisciplinarity. However, the proportion of each field in this literature and its trend dynamics are not known. The objective of this study was to analyze the ICM literature, extract latent topics and search for the presence of research trends.

MATERIAL AND METHODS

Abstracts of original articles from the top ICM journals, from their inception until December 31st, 2019, were included. This corpus was fed into a structural topic modeling algorithm to extract latent semantic topics. The temporal distribution was then analyzed and the presence of trends was searched by Mann-Kendall trends tests.

RESULTS

Finally, 49,276 articles from 10 journals were included. After topic modeling analysis and experts' feedback, 124 research topics were selected and labeled. Topics were categorized into 19 categories, the most represented being respiratory, fundamental and neurological research. Increasing trends were observed for research on mechanical ventilation and decreasing trends for cardiopulmonary resuscitation.

CONCLUSIONS

This study reviewed all articles from major ICM journals in a comprehensive way. It provides a better understanding of ICM research landscape by analyzing the temporal evolution of latent research topics in the ICM literature.

Clinical notes as prognostic markers of mortality associated with diabetes mellitus following critical care: A retrospective cohort analysis using machine learning and unstructured big data

BACKGROUND

Clinical notes are ubiquitous resources offering potential value in optimizing critical care via data mining technologies.

OBJECTIVE

To determine the predictive value of clinical notes as prognostic markers of 1-year all-cause mortality among people with diabetes following critical care.

MATERIALS AND METHODS

Mortality of diabetes patients were predicted using three cohorts of clinical text in a critical care database, written by physicians (n = 45253), nurses (159027), and both (n = 204280). Natural language processing was used to pre-process text documents and LASSO-regularized logistic regression models were trained and tested. Confusion matrix metrics of each model were calculated and AUROC estimates between models were compared. All predictive words and corresponding coefficients were extracted. Outcome probability associated with each text document was estimated.

RESULTS

Models built on clinical text of physicians, nurses, and the combined cohort predicted mortality with AUROC of 0.996, 0.893, and 0.922, respectively. Predictive performance of the models significantly differed from one another whereas inter-rater reliability ranged from substantial to almost perfect across them. Number of predictive words with non-zero coefficients were 3994, 8159, and 10579, respectively, in the models of physicians, nurses, and the combined cohort. Physicians' and nursing notes, both individually and when combined, strongly predicted 1-year all-cause mortality among people with diabetes following critical care.

CONCLUSION

Clinical notes of physicians and nurses are strong and novel prognostic markers of diabetes-associated mortality in critical care, offering potentially generalizable and scalable applications. Clinical text-derived personalized risk estimates of prognostic outcomes such as mortality could be used to optimize patient care.

Twenty-five years of Health & Place: Citation classics, internationalism and interdisciplinarity

To mark 25 years of Health & Place Health & Place, we identify and appraise some key contributions to the journal over this period. We use citation data to identify 'classics' from the journal's back catalogue. We also examine trends in the international reach and disciplinary homes of our authors. We show that there has been a near 7-fold increase in the number of published papers between the early and most recent years of the journal and that the journal's citation levels are amongst the top 2% of social science journals. Amongst the most cited papers, some clear themes are evident such as physical activity, diet/food, obesity and topics relating to greenspace. The profile of the journal's authors is becoming more internationally diverse, represents a broader range of disciplines, and increasingly demonstrating cross/interdisciplinary ways of working. Although Anglophone countries have led the way, there is an increasing number of contributions from elsewhere including emerging economies such as China. We conclude with some comments on likely future directions for the journal including enduring concerns such as greenspace, obesity, diet and unhealthy commodities (alcohol, tobacco, ultra-processed food) as well as more recent directions including planetary health, longitudinal and lifecourse analyses, and the opportunities (and challenges) of big data and machine learning. Whatever the thematic concerns of the papers over next 25 years, we will continue to welcome outstanding research that is concerned with the importance place makes to health.