Development and Validation of a Machine Learning Model to Estimate Bacterial Sepsis Among Immunocompromised Recipients of Stem Cell Transplant.

Importance: Sepsis disproportionately affects recipients of allogeneic hematopoietic cell transplant (allo-HCT), and timely detection is crucial. However, the atypical presentation of sepsis within this population makes detection challenging, and existing clinical sepsis tools have limited prognostic value among this high-risk population. Objective: To develop a full risk factor (demographic, transplant, clinical, and laboratory factors) and clinical factor-specific automated bacterial sepsis decision support tool for recipients of allo-HCT with potential bloodstream infections (PBIs). Design, Setting, and Participants: This prognostic study used data from adult recipients of allo-HCT transplanted at the Fred Hutchinson Cancer Research Center, Seattle, Washington, between June 2010 and June 2019 randomly divided into 70% modeling and 30% validation data sets. Tools were developed using the area under the curve (AUC) optimized SuperLearner, and their performance was compared with existing clinical sepsis tools: National Early Warning Score (NEWS), quick Sequential Organ Failure Assessment (qSOFA), and Systemic Inflammatory Response Syndrome (SIRS), using the validation data set. Data were analyzed between January and October of 2020. Main Outcomes and Measures: The primary outcome was high-sepsis risk bacteremia (culture confirmed gram-negative species, Staphylococcus aureus, or Streptococcus spp bacteremia), and the secondary outcomes were 10- and 28-day mortality. Tool discrimination and calibration were examined using accuracy metrics and expected vs observed probabilities. Results: Between June 2010 and June 2019, 1943 recipients of allo-HCT received their first transplant, and 1594 recipients (median [interquartile range] age at transplant, 54 [43-63] years; 911 [57.2%] men; 1242 individuals [77.9%] identifying as White) experienced at least 1 PBI. Of 8131 observed PBIs, 238 (2.9%) were high-sepsis risk bacteremia. Compared with high-sepsis risk bacteremia, the full decision support tool had the highest AUC (0.85; 95% CI, 0.81-0.89), followed by the clinical factor-specific tool (0.72; 95% CI, 0.66-0.78). SIRS had the highest AUC of existing tools (0.64; 95% CI, 0.57-0.71). The full decision support tool had the highest AUCs for PBIs identified in inpatient (0.82; 95% CI, 0.76-0.89) and outpatient (0.82; 95% CI, 0.75-0.89) settings and for 10-day (0.85; 95% CI, 0.79-0.91) and 28-day (0.80; 95% CI, 0.75-0.84) mortality. Conclusions and Relevance: These findings suggest that compared with existing tools and the clinical factor-specific tool, the full decision support tool had superior prognostic accuracy for the primary (high-sepsis risk bacteremia) and secondary (short-term mortality) outcomes in inpatient and outpatient settings. If used at the time of culture collection, the full decision support tool may inform more timely sepsis detection among recipients of allo-HCT.

Automated Real-Time Collection of Pathogen-Specific Diagnostic Data: Syndromic Infectious Disease Epidemiology.

BACKGROUND: Health care and public health professionals rely on accurate, real-time monitoring of infectious diseases for outbreak preparedness and response. Early detection of outbreaks is improved by systems that are comprehensive and specific with respect to the pathogen but are rapid in reporting the data. It has proven difficult to implement these requirements on a large scale while maintaining patient privacy. OBJECTIVE: The aim of this study was to demonstrate the automated export, aggregation, and analysis of infectious disease diagnostic test results from clinical laboratories across the United States in a manner that protects patient confidentiality. We hypothesized that such a system could aid in monitoring the seasonal occurrence of respiratory pathogens and may have advantages with regard to scope and ease of reporting compared with existing surveillance systems. METHODS: We describe a system, BioFire Syndromic Trends, for rapid disease reporting that is syndrome-based but pathogen-specific. Deidentified patient test results from the BioFire FilmArray multiplex molecular diagnostic system are sent directly to a cloud database. Summaries of these data are displayed in near real time on the Syndromic Trends public website. We studied this dataset for the prevalence, seasonality, and coinfections of the 20 respiratory pathogens detected in over 362,000 patient samples acquired as a standard-of-care testing over the last 4 years from 20 clinical laboratories in the United States. RESULTS: The majority of pathogens show influenza-like seasonality, rhinovirus has fall and spring peaks, and adenovirus and the bacterial pathogens show constant detection over the year. The dataset can also be considered in an ecological framework; the viruses and bacteria detected by this test are parasites of a host (the human patient). Interestingly, the rate of pathogen codetections, on average 7.94% (28,741/362,101), matches predictions based on the relative abundance of organisms present. CONCLUSIONS: Syndromic Trends preserves patient privacy by removing or obfuscating patient identifiers while still collecting much useful information about the bacterial and viral pathogens that they harbor. Test results are uploaded to the database within a few hours of completion compared with delays of up to 10 days for other diagnostic-based reporting systems. This work shows that the barriers to establishing epidemiology systems are no longer scientific and technical but rather administrative, involving questions of patient privacy and data ownership. We have demonstrated here that these barriers can be overcome. This first look at the resulting data stream suggests that Syndromic Trends will be able to provide high-resolution analysis of circulating respiratory pathogens and may aid in the detection of new outbreaks.

Can a selfie promote public engagement with skin cancer?

Social media may provide new opportunities to promote skin cancer prevention, but research to understand this potential is needed. In April of 2015, Kentucky native Tawny Willoughby (TW) shared a graphic skin cancer selfie on Facebook that subsequently went viral. We examined the volume of comments and shares of her original Facebook post; news volume of skin cancer from Google News; and search volume for skin cancer Google queries. We compared these latter metrics after TWs announcement against expected volumes based on forecasts of historical trends. TWs skin cancer story was picked up by the media on May 11, 2015 after the social media post had been shared approximately 50,000 times. All search queries for skin cancer increased 162% (95% CI 102 to 320) and 155% (95% CI 107 to 353) on May 13th and 14th, when news about TW's skin cancer selfie was at its peak, and remained higher through May 17th. Google searches about skin cancer prevention and tanning were also significantly higher than expected volumes. In practical terms, searches reached near-record levels - i.e., May 13th, 14th and 15th were respectively the 6th, 8th, and 40th most searched days for skin cancer since January 1, 2004 when Google began tracking searches. We conclude that an ordinary person's social media post caught the public's imagination and led to significant increases in public engagement with skin cancer prevention. Digital surveillance methods can rapidly detect these events in near real time, allowing public health practitioners to engage and potentially elevate positive effects.

The Charlie Sheen Effect on Rapid In-home Human Immunodeficiency Virus Test Sales.

One in eight of the 1.2 million Americans living with human immunodeficiency virus (HIV) are unaware of their positive status, and untested individuals are responsible for most new infections. As a result, testing is the most cost-effective HIV prevention strategy and must be accelerated when opportunities are presented. Web searches for HIV spiked around actor Charlie Sheen's HIV-positive disclosure. However, it is unknown whether Sheen's disclosure impacted offline behaviors like HIV testing. The goal of this study was to determine if Sheen's HIV disclosure was a record-setting HIV prevention event and determine if Web searches presage increases in testing allowing for rapid detection and reaction in the future. Sales of OraQuick rapid in-home HIV test kits in the USA were monitored weekly from April 12, 2014, to April 16, 2016, alongside Web searches including the terms "test," "tests," or "testing" and "HIV" as accessed from Google Trends. Changes in OraQuick sales around Sheen's disclosure and prediction models using Web searches were assessed. OraQuick sales rose 95% (95% CI, 75-117; p < 0.001) of the week of Sheen's disclosure and remained elevated for 4 more weeks (p < 0.05). In total, there were 8225 more sales than expected around Sheen's disclosure, surpassing World AIDS Day by a factor of about 7. Moreover, Web searches mirrored OraQuick sales trends (r = 0.79), demonstrating their ability to presage increases in testing. The "Charlie Sheen effect" represents an important opportunity for a public health response, and in the future, Web searches can be used to detect and act on more opportunities to foster prevention behaviors.

Why do people use electronic nicotine delivery systems (electronic cigarettes)? A content analysis of Twitter, 2012-2015.

The reasons for using electronic nicotine delivery systems (ENDS) are poorly understood and are primarily documented by expensive cross-sectional surveys that use preconceived close-ended response options rather than allowing respondents to use their own words. We passively identify the reasons for using ENDS longitudinally from a content analysis of public postings on Twitter. All English language public tweets including several ENDS terms (e.g., "e-cigarette" or "vape") were captured from the Twitter data stream during 2012 and 2015. After excluding spam, advertisements, and retweets, posts indicating a rationale for vaping were retained. The specific reasons for vaping were then inferred based on a supervised content analysis using annotators from Amazon's Mechanical Turk. During 2012 quitting combustibles was the most cited reason for using ENDS with 43% (95%CI 39-48) of all reason-related tweets cited quitting combustibles, e.g., "I couldn't quit till I tried ecigs," eclipsing the second most cited reason by more than double. Other frequently cited reasons in 2012 included ENDS's social image (21%; 95%CI 18-25), use indoors (14%; 95%CI 11-17), flavors (14%; 95%CI 11-17), safety relative to combustibles (9%; 95%CI 7-11), cost (3%; 95%CI 2-5) and favorable odor (2%; 95%CI 1-3). By 2015 the reasons for using ENDS cited on Twitter had shifted. Both quitting combustibles and use indoors significantly declined in mentions to 29% (95%CI 24-33) and 12% (95%CI 9-16), respectively. At the same time, social image increased to 37% (95%CI 32-43) and lack of odor increased to 5% (95%CI 2-5), the former leading all cited reasons in 2015. Our data suggest the reasons people vape are shifting away from cessation and toward social image. The data also show how the ENDS market is responsive to a changing policy landscape. For instance, smoking indoors was less frequently cited in 2015 as indoor smoking restrictions became more common. Because the data and analytic approach are scalable, adoption of our strategies in the field can inform follow-up survey-based surveillance (so the right questions are asked), interventions, and policies for ENDS.

Leveraging Big Data to Improve Health Awareness Campaigns: A Novel Evaluation of the Great American Smokeout.

BACKGROUND: Awareness campaigns are ubiquitous, but little is known about their potential effectiveness because traditional evaluations are often unfeasible. For 40 years, the "Great American Smokeout" (GASO) has encouraged media coverage and popular engagement with smoking cessation on the third Thursday of November as the nation's longest running awareness campaign. OBJECTIVE: We proposed a novel evaluation framework for assessing awareness campaigns using the GASO as a case study by observing cessation-related news reports and Twitter postings, and cessation-related help seeking via Google, Wikipedia, and government-sponsored quitlines. METHODS: Time trends (2009-2014) were analyzed using a quasi-experimental design to isolate spikes during the GASO by comparing observed outcomes on the GASO day with the simulated counterfactual had the GASO not occurred. RESULTS: Cessation-related news typically increased by 61% (95% CI 35-87) and tweets by 13% (95% CI -21 to 48) during the GASO compared with what was expected had the GASO not occurred. Cessation-related Google searches increased by 25% (95% CI 10-40), Wikipedia page visits by 22% (95% CI -26 to 67), and quitline calls by 42% (95% CI 19-64). Cessation-related news media positively coincided with cessation tweets, Internet searches, and Wikipedia visits; for example, a 50% increase in news for any year predicted a 28% (95% CI -2 to 59) increase in tweets for the same year. Increases on the day of the GASO rivaled about two-thirds of a typical New Year's Day-the day that is assumed to see the greatest increases in cessation-related activity. In practical terms, there were about 61,000 more instances of help seeking on Google, Wikipedia, or quitlines on GASO each year than would normally be expected. CONCLUSIONS: These findings provide actionable intelligence to improve the GASO and model how to rapidly, cost-effectively, and efficiently evaluate hundreds of awareness campaigns, nearly all for the first time.

Revisiting the Rise of Electronic Nicotine Delivery Systems Using Search Query Surveillance.

INTRODUCTION: Public perceptions of electronic nicotine delivery systems (ENDS) remain poorly understood because surveys are too costly to regularly implement and, when implemented, there are long delays between data collection and dissemination. Search query surveillance has bridged some of these gaps. Herein, ENDS' popularity in the U.S. is reassessed using Google searches. METHODS: ENDS searches originating in the U.S. from January 2009 through January 2015 were disaggregated by terms focused on e-cigarette (e.g., e-cig) versus vaping (e.g., vapers); their geolocation (e.g., state); the aggregate tobacco control measures corresponding to their geolocation (e.g., clean indoor air laws); and by terms that indicated the searcher's potential interest (e.g., buy e-cigs likely indicates shopping)-all analyzed in 2015. RESULTS: ENDS searches are rapidly increasing in the U.S., with 8,498,000 searches during 2014 alone. Increasingly, searches are shifting from e-cigarette- to vaping-focused terms, especially in coastal states and states where anti-smoking norms are stronger. For example, nationally, e-cigarette searches declined 9% (95% CI=1%, 16%) during 2014 compared with 2013, whereas vaping searches increased 136% (95% CI=97%, 186%), even surpassing e-cigarette searches. Additionally, the percentage of ENDS searches related to shopping (e.g., vape shop) nearly doubled in 2014, whereas searches related to health concerns (e.g., vaping risks) or cessation (e.g., quit smoking with e-cigs) were rare and declined in 2014. CONCLUSIONS: ENDS popularity is rapidly growing and evolving. These findings could inform survey questionnaire development for follow-up investigation and immediately guide policy debates about how the public perceives the health risks or cessation benefits of ENDS.

US consumer interest in non-cigarette tobacco products spikes around the 2009 federal tobacco tax increase.

OBJECTIVES: This quasi-experimental longitudinal study monitored aggregate Google search queries as a proxy for consumer interest in non-cigarette tobacco products (NTP) around the time of the 2009 US federal tobacco tax increase. METHODS: Query trends for searches mentioning common NTP were downloaded from Google's public archives. The mean relative increase was estimated by comparing the observed with expected query volume for the 16 weeks around the tax. RESULTS: After the tax was announced, queries spiked for chewing tobacco, cigarillos, electronic cigarettes ('e-cigarettes'), roll-your-own (RYO) tobacco, snuff, and snus. E-cigarette queries were 75% (95% CI 70% to 80%) higher than expected 8 weeks before and after the tax, followed by RYO 59% (95% CI 53% to 65%), snus 34% (95% CI 31% to 37%), chewing tobacco 17% (95% CI 15% to 20%), cigarillos 14% (95% CI 11% to 17%), and snuff 13% (95% CI 10% to 14%). Unique queries increasing the most were 'ryo cigarettes' 427% (95% CI 308% to 534%), 'ryo tobacco' 348% (95% CI 300% to 391%), 'best electronic cigarette' 221% (95% CI 185% to 257%), and 'e-cigarette' 205% (95% CI 163% to 245%). CONCLUSIONS: The 2009 tobacco tax increase triggered large increases in consumer interest for some NTP, particularly e-cigarettes and RYO tobacco.

Cancer information seeking in the digital age: effects of Angelina Jolie's prophylactic mastectomy announcement.

OBJECTIVE: . This study used digital surveillance to examine the impact of Angelina Jolie's prophylactic mastectomy announcement on cancer information seeking. METHODS: . We analyzed 4 categories of breast cancer-related Internet search queries from 2010 to 2013 in the United States. RESULTS: . Compared with the preceding 6 weeks, general information queries were 112% (95% confidence interval [CI], 79-146) higher the day of the announcement and remained 35% (95% CI, 22-49) higher over the week after the editorial. Risk assessment queries were 165% (95% CI, 110-222) higher the day of the announcement and 52% (95% CI, 31-75) higher across the week. Genetics and treatment queries showed little volume before the announcement but increased 2154% (95% CI, 1550-7076) and 9900% (95% CI, 3196-1,064,000) the day of, respectively, and remained higher across the week (812% [95% CI, 402-3913] and 2625% [95% CI, 551-317,000]). All query categories returned to normal volumes by the beginning of the second week. CONCLUSION: . Jolie's unique announcement spurred significant information seeking about breast cancer genetic testing and treatment procedures, although the surge in queries returned to preannouncement levels after 1 week. Future research should apply digital methods to advance our understanding of cancer information seeking in the digital age.

Do celebrity cancer diagnoses promote primary cancer prevention?

OBJECTIVE: Celebrity cancer diagnoses generate considerable media coverage of and increase interest in cancer screening, but do they also promote primary cancer prevention? METHODS: Daily trends for smoking cessation-related media (information-availability) and Google queries (information-seeking) around Brazilian President and smoker Lula da Silva's laryngeal cancer diagnosis announcements were compared to a typical period and several cessation awareness events. RESULTS: Cessation media coverage was 163% (95% confidence interval, 54-328) higher than expected the week after the announcement but returned to typical levels the second week. Cessation queries were 67% (95% confidence interval, 40-96) greater the week after Lula's announcement, remaining 153% (95% confidence interval, 121-188), 130% (95% confidence interval, 101-163) and 71% (95% confidence interval, 43-100) greater during the second, third, and fourth week after the announcement. There were 1.1 million excess cessation queries the month after Lula's announcement, eclipsing query volumes for the week around New Years Day, World No Tobacco Day, and Brazilian National No Smoking Day. CONCLUSION: Just as celebrity diagnoses promote cancer screening, they may also promote primary prevention. Discovery of this dynamic suggests the public should be further encouraged to consider primary (in addition to the usual secondary) cancer prevention around celebrity diagnoses, though more cases, cancers, and prevention behaviors must be explored.

Digital detection for tobacco control: online reactions to the 2009 U.S. cigarette excise tax increase.

INTRODUCTION: The Internet is revolutionizing tobacco control, but few have harnessed the Web for surveillance. We demonstrate for the first time an approach for analyzing aggregate Internet search queries that captures precise changes in population considerations about tobacco. METHODS: We compared tobacco-related Google queries originating in the United States during the week of the State Children's Health Insurance Program (SCHIP) 2009 cigarette excise tax increase with a historic baseline. Specific queries were then ranked according to their relative increases while also considering approximations of changes in absolute search volume. RESULTS: Individual queries with the largest relative increases the week of the SCHIP tax were "cigarettes Indian reservations" 640% (95% CI, 472-918), "free cigarettes online" 557% (95% CI, 432-756), and "Indian reservations cigarettes" 542% (95% CI, 414-733), amounting to about 7,500 excess searches. By themes, the largest relative increases were tribal cigarettes 246% (95% CI, 228-265), "free" cigarettes 215% (95% CI, 191-242), and cigarette stores 176% (95% CI, 160-193), accounting for 21,000, 27,000, and 90,000 excess queries. All avoidance queries, including those aforementioned themes, relatively increased 150% (95% CI, 144-155) or 550,000 from their baseline. All cessation queries increased 46% (95% CI, 44-48), or 175,000, around SCHIP; including themes for "cold turkey" 19% (95% CI, 11-27) or 2,600, cessation products 47% (95% CI, 44-50) or 78,000, and dubious cessation approaches (e.g., hypnosis) 40% (95% CI, 33-47) or 2,300. CONCLUSIONS: The SCHIP tax motivated specific changes in population considerations. Our strategy can support evaluations that temporally link tobacco control measures with instantaneous population reactions, as well as serve as a springboard for traditional studies, for example, including survey questionnaire design.

Using digital surveillance to examine the impact of public figure pancreatic cancer announcements on media and search query outcomes.

BACKGROUND: Announcements of cancer diagnoses from public figures may stimulate cancer information seeking and media coverage about cancer. This study used digital surveillance to quantify the effects of pancreatic cancer public figure announcements on online cancer information seeking and cancer media coverage. METHODS: We compiled a list of public figures (N = 25) who had been diagnosed with or had died from pancreatic cancer between 2006 and 2011. We specified interrupted time series models using data from Google Trends to examine search query shifts for pancreatic cancer and other cancers. Weekly media coverage archived on Google News were also analyzed. RESULTS: Most public figures' pancreatic cancer announcements corresponded with no appreciable change in pancreatic cancer search queries or media coverage. In contrast, Patrick Swayze's diagnosis was associated with a 285% (95% confidence interval [CI]: 212 to 360) increase in pancreatic cancer search queries, though it was only weakly associated with increases in pancreatic cancer media coverage. Steve Jobs's death was associated with a 197% (95% CI: 131 to 266) increase in pancreatic cancer queries and a 3517% (95% CI: 2882 to 4492) increase in pancreatic cancer media coverage. In general, a doubling in pancreatic cancer-specific media coverage corresponded with a 325% increase in pancreatic cancer queries. CONCLUSION: Digital surveillance is an important tool for future cancer control research and practice. The current application of these methods suggested that pancreatic cancer announcements (diagnosis or death) by particular public figures stimulated media coverage of and online information seeking for pancreatic cancer.

A novel evaluation of World No Tobacco day in Latin America.

BACKGROUND: World No Tobacco Day (WNTD), commemorated annually on May 31, aims to inform the public about tobacco harms. Because tobacco control surveillance is usually annualized, the effectiveness of WNTD remains unexplored into its 25th year. OBJECTIVE: To explore the potential of digital surveillance (infoveillance) to evaluate the impacts of WNTD on population awareness of and interest in cessation. METHODS: Health-related news stories and Internet search queries were aggregated to form a continuous and real-time data stream. We monitored daily news coverage of and Internet search queries for cessation in seven Latin American nations from 2006 to 2011. RESULTS: Cessation news coverage peaked around WNTD, typically increasing 71% (95% confidence interval [CI] 61-81), ranging from 61% in Mexico to 83% in Venezuela. Queries indicative of cessation interest peaked on WNTD, increasing 40% (95% CI 32-48), ranging from 24% in Colombia to 84% in Venezuela. A doubling in cessation news coverage was associated with approximately a 50% increase in cessation queries. To gain a practical perspective, we compared WNTD-related activity with New Year's Day and several cigarette excise tax increases in Mexico. Cessation queries around WNTD were typically greater than New Year's Day and approximated a 2.8% (95% CI -0.8 to 6.3) increase in cigarette excise taxes. CONCLUSIONS: This novel evaluation suggests WNTD had a significant impact on popular awareness (media trends) and individual interest (query trends) in smoking cessation. Because WNTD is constantly evolving, our work is also a model for real-time surveillance and potential improvement in WNTD and similar initiatives.