Digital public health surveillance: a systematic scoping review.

The ubiquitous and openly accessible information produced by the public on the Internet has sparked an increasing interest in developing digital public health surveillance (DPHS) systems. We conducted a systematic scoping review in accordance with the PRISMA extension for scoping reviews to consolidate and characterize the existing research on DPHS and identify areas for further research. We used Natural Language Processing and content analysis to define the search strings and searched Global Health, Web of Science, PubMed, and Google Scholar from 2005 to January 2020 for peer-reviewed articles on DPHS, with extensive hand searching. Seven hundred fifty-five articles were included in this review. The studies were from 54 countries and utilized 26 digital platforms to study 208 sub-categories of 49 categories associated with 16 public health surveillance (PHS) themes. Most studies were conducted by researchers from the United States (56%, 426) and dominated by communicable diseases-related topics (25%, 187), followed by behavioural risk factors (17%, 131). While this review discusses the potentials of using Internet-based data as an affordable and instantaneous resource for DPHS, it highlights the paucity of longitudinal studies and the methodological and inherent practical limitations underpinning the successful implementation of a DPHS system. Little work studied Internet users' demographics when developing DPHS systems, and 39% (291) of studies did not stratify their results by geographic region. A clear methodology by which the results of DPHS can be linked to public health action has yet to be established, as only six (0.8%) studies deployed their system into a PHS context.

Predicting Acute Kidney Injury after Surgery.

Acute Kidney Injury (AKI) is a common complication after surgery. Recognition of patients at risk of AKI at an earlier stage is a priority for researchers and health care providers. The objective of this study is to develop machine learning prediction models of acute kidney injury (AKI) in patients who undergo surgery. The dataset used in this study consists of in-hospital patients' data of five different cohorts coming from different major procedure types. This data was collected from the SunRiseClinical Manager (SCM) electronic medical records system that is used in the Calgary Zone, Alberta, Canada from 2008 to 2015 where the patients are >=18 years of age. Five classifiers were experimented with: support vector machine, random forest, logistic regression, k-nearest neighbors, and adaptive boosting. The area under the receiver operating characteristics curve (AUROC) ranged between 0.62-0.84 and sensitivity and specificity ranged between 0.81-0.83 and 0.43-0.85, respectively. Predictions from these models can facilitate early intervention in AKI treatment.

Using Machine Learning and Smartphone and Smartwatch Data to Detect Emotional States and Transitions: Exploratory Study.

BACKGROUND: Emotional state in everyday life is an essential indicator of health and well-being. However, daily assessment of emotional states largely depends on active self-reports, which are often inconvenient and prone to incomplete information. Automated detection of emotional states and transitions on a daily basis could be an effective solution to this problem. However, the relationship between emotional transitions and everyday context remains to be unexplored. OBJECTIVE: This study aims to explore the relationship between contextual information and emotional transitions and states to evaluate the feasibility of detecting emotional transitions and states from daily contextual information using machine learning (ML) techniques. METHODS: This study was conducted on the data of 18 individuals from a publicly available data set called ExtraSensory. Contextual and sensor data were collected using smartphone and smartwatch sensors in a free-living condition, where the number of days for each person varied from 3 to 9. Sensors included an accelerometer, a gyroscope, a compass, location services, a microphone, a phone state indicator, light, temperature, and a barometer. The users self-reported approximately 49 discrete emotions at different intervals via a smartphone app throughout the data collection period. We mapped the 49 reported discrete emotions to the 3 dimensions of the pleasure, arousal, and dominance model and considered 6 emotional states: discordant, pleased, dissuaded, aroused, submissive, and dominant. We built general and personalized models for detecting emotional transitions and states every 5 min. The transition detection problem is a binary classification problem that detects whether a person's emotional state has changed over time, whereas state detection is a multiclass classification problem. In both cases, a wide range of supervised ML algorithms were leveraged, in addition to data preprocessing, feature selection, and data imbalance handling techniques. Finally, an assessment was conducted to shed light on the association between everyday context and emotional states. RESULTS: This study obtained promising results for emotional state and transition detection. The best area under the receiver operating characteristic (AUROC) curve for emotional state detection reached 60.55% in the general models and an average of 96.33% across personalized models. Despite the highly imbalanced data, the best AUROC curve for emotional transition detection reached 90.5% in the general models and an average of 88.73% across personalized models. In general, feature analyses show that spatiotemporal context, phone state, and motion-related information are the most informative factors for emotional state and transition detection. Our assessment showed that lifestyle has an impact on the predictability of emotion. CONCLUSIONS: Our results demonstrate a strong association of daily context with emotional states and transitions as well as the feasibility of detecting emotional states and transitions using data from smartphone and smartwatch sensors.

Automatic Identification of Information Quality Metrics in Health News Stories.

Objective: Many online and printed media publish health news of questionable trustworthiness and it may be difficult for laypersons to determine the information quality of such articles. The purpose of this work was to propose a methodology for the automatic assessment of the quality of health-related news stories using natural language processing and machine learning. Materials and Methods: We used a database from the website HealthNewsReview.org that aims to improve the public dialogue about health care. HealthNewsReview.org developed a set of criteria to critically analyze health care interventions' claims. In this work, we attempt to automate the evaluation process by identifying the indicators of those criteria using natural language processing-based machine learning on a corpus of more than 1,300 news stories. We explored features ranging from simple n-grams to more advanced linguistic features and optimized the feature selection for each task. Additionally, we experimented with the use of pre-trained natural language model BERT. Results: For some criteria, such as mention of costs, benefits, harms, and "disease-mongering," the evaluation results were promising with an F1 measure reaching 81.94%, while for others the results were less satisfactory due to the dataset size, the need of external knowledge, or the subjectivity in the evaluation process. Conclusion: These used criteria are more challenging than those addressed by previous work, and our aim was to investigate how much more difficult the machine learning task was, and how and why it varied between criteria. For some criteria, the obtained results were promising; however, automated evaluation of the other criteria may not yet replace the manual evaluation process where human experts interpret text senses and make use of external knowledge in their assessment.

Corrigendum: Fake News or Weak Science? Visibility and Characterization of Antivaccine Webpages Returned by Google in Different Languages and Countries.

[This corrects the article DOI: 10.3389/fimmu.2018.01215.].

What Is Health Information Quality? Ethical Dimension and Perception by Users.

Introduction: The popularity of seeking health information online makes information quality (IQ) a public health issue. The present study aims at building a theoretical framework of health information quality (HIQ) that can be applied to websites and defines which IQ criteria are important for a website to be trustworthy and meet users' expectations. Methods: We have identified a list of HIQ criteria from existing tools and assessment criteria and elaborated them into a questionnaire that was promoted via social media and mainly the University. Responses (329) were used to rank the different criteria for their importance in trusting a website and to identify patterns of criteria using hierarchical cluster analysis. Results: HIQ criteria were organized in five dimensions based on previous theoretical frameworks as well as on how they cluster together in the questionnaire response. We could identify a top-ranking dimension (scientific completeness) that describes what the user is expecting to know from the websites (in particular: description of symptoms, treatments, side effects). Cluster analysis also identified a number of criteria borrowed from existing tools for assessing HIQ that could be subsumed to a broad "ethical" dimension (such as conflict of interests, privacy, advertising policies) that were, in general, ranked of low importance by the participants. Subgroup analysis revealed significant differences in the importance assigned to the various criteria based on gender, language and whether or not of biomedical educational background. Conclusions: We identified criteria of HIQ and organized them in dimensions. We observed that ethical criteria, while regarded highly in the academic and medical environment, are not considered highly by the public.

Fake News or Weak Science? Visibility and Characterization of Antivaccine Webpages Returned by Google in Different Languages and Countries.

The 1998 Lancet paper by Wakefield et al., despite subsequent retraction and evidence indicating no causal link between vaccinations and autism, triggered significant parental concern. The aim of this study was to analyze the online information available on this topic. Using localized versions of Google, we searched "autism vaccine" in English, French, Italian, Portuguese, Mandarin, and Arabic and analyzed 200 websites for each search engine result page (SERP). A common feature was the newsworthiness of the topic, with news outlets representing 25-50% of the SERP, followed by unaffiliated websites (blogs, social media) that represented 27-41% and included most of the vaccine-negative websites. Between 12 and 24% of websites had a negative stance on vaccines, while most websites were pro-vaccine (43-70%). However, their ranking by Google varied. While in Google.com, the first vaccine-negative website was the 43rd in the SERP, there was one vaccine-negative webpage in the top 10 websites in both the British and Australian localized versions and in French and two in Italian, Portuguese, and Mandarin, suggesting that the information quality algorithm used by Google may work better in English. Many webpages mentioned celebrities in the context of the link between vaccines and autism, with Donald Trump most frequently. Few websites (1-5%) promoted complementary and alternative medicine (CAM) but 50-100% of these were also vaccine-negative suggesting that CAM users are more exposed to vaccine-negative information. This analysis highlights the need for monitoring the web for information impacting on vaccine uptake.