Using online search activity for earlier detection of gynaecological malignancy.

BACKGROUND: Ovarian cancer is the most lethal and endometrial cancer the most common gynaecological cancer in the UK, yet neither have a screening program in place to facilitate early disease detection. The aim is to evaluate whether online search data can be used to differentiate between individuals with malignant and benign gynaecological diagnoses. METHODS: This is a prospective cohort study evaluating online search data in symptomatic individuals (Google user) referred from primary care (GP) with a suspected cancer to a London Hospital (UK) between December 2020 and June 2022. Informed written consent was obtained and online search data was extracted via Google takeout and anonymised. A health filter was applied to extract health-related terms for 24 months prior to GP referral. A predictive model (outcome: malignancy) was developed using (1) search queries (terms model) and (2) categorised search queries (categories model). Area under the ROC curve (AUC) was used to evaluate model performance. 844 women were approached, 652 were eligible to participate and 392 were recruited. Of those recruited, 108 did not complete enrollment, 12 withdrew and 37 were excluded as they did not track Google searches or had an empty search history, leaving a cohort of 235. RESULTS: The cohort had a median age of 53 years old (range 20-81) and a malignancy rate of 26.0%. There was a difference in online search data between those with a benign and malignant diagnosis, noted as early as 360 days in advance of GP referral, when search queries were used directly, but only 60 days in advance, when queries were divided into health categories. A model using online search data from patients (n = 153) who performed health-related search and corrected for sample size, achieved its highest sample-corrected AUC of 0.82, 60 days prior to GP referral. CONCLUSIONS: Online search data appears to be different between individuals with malignant and benign gynaecological conditions, with a signal observed in advance of GP referral date. Online search data needs to be evaluated in a larger dataset to determine its value as an early disease detection tool and whether its use leads to improved clinical outcomes.

Neural network models for influenza forecasting with associated uncertainty using Web search activity trends.

Influenza affects millions of people every year. It causes a considerable amount of medical visits and hospitalisations as well as hundreds of thousands of deaths. Forecasting influenza prevalence with good accuracy can significantly help public health agencies to timely react to seasonal or novel strain epidemics. Although significant progress has been made, influenza forecasting remains a challenging modelling task. In this paper, we propose a methodological framework that improves over the state-of-the-art forecasting accuracy of influenza-like illness (ILI) rates in the United States. We achieve this by using Web search activity time series in conjunction with historical ILI rates as observations for training neural network (NN) architectures. The proposed models incorporate Bayesian layers to produce associated uncertainty intervals to their forecast estimates, positioning themselves as legitimate complementary solutions to more conventional approaches. The best performing NN, referred to as the iterative recurrent neural network (IRNN) architecture, reduces mean absolute error by 10.3% and improves skill by 17.1% on average in nowcasting and forecasting tasks across 4 consecutive flu seasons.

Comparative effectiveness of different primary vaccination courses on mRNA-based booster vaccines against SARs-COV-2 infections: a time-varying cohort analysis using trial emulation in the Virus Watch community cohort.

BACKGROUND: The Omicron B.1.1.529 variant increased severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infections in doubly vaccinated individuals, particularly in the Oxford-AstraZeneca COVID-19 vaccine (ChAdOx1) recipients. To tackle infections, the UK's booster vaccination programmes used messenger ribonucleic acid (mRNA) vaccines irrespective of an individual's primary course vaccine type, and prioritized the clinically vulnerable. These mRNA vaccines included the Pfizer-BioNTech COVID-19 vaccine (BNT162b2) the Moderna COVID-19 vaccine (mRNA-1273). There is limited understanding of the effectiveness of different primary vaccination courses on mRNA booster vaccines against SARs-COV-2 infections and how time-varying confounders affect these evaluations. METHODS: Trial emulation was applied to a prospective community observational cohort in England and Wales to reduce time-varying confounding-by-indication driven by prioritizing vaccination based upon age, vulnerability and exposure. Trial emulation was conducted by meta-analysing eight adult cohort results whose booster vaccinations were staggered between 16 September 2021 and 05 January 2022 and followed until 23 January 2022. Time from booster vaccination until SARS-CoV-2 infection, loss of follow-up or end of study was modelled using Cox proportional hazard models and adjusted for age, sex, minority ethnic status, clinically vulnerability and deprivation. RESULTS: A total of 19 159 participants were analysed, with 11 709 ChAdOx1 primary courses and 7450 BNT162b2 primary courses. Median age, clinical vulnerability status and infection rates fluctuate through time. In mRNA-boosted adults, 7.4% (n = 863) of boosted adults with a ChAdOx1 primary course experienced a SARS-CoV-2 infection compared with 7.7% (n = 571) of those who had BNT162b2 as a primary course. The pooled adjusted hazard ratio (aHR) was 1.01 with a 95% confidence interval (CI) of: 0.90 to 1.13. CONCLUSION: After an mRNA booster dose, we found no difference in protection comparing those with a primary course of BNT162b2 with those with a ChAdOx1 primary course. This contrasts with pre-booster findings where previous research shows greater effectiveness of BNT162b2 than ChAdOx1 in preventing infection.

Providing early indication of regional anomalies in COVID-19 case counts in England using search engine queries.

Prior work has shown the utility of using Internet searches to track the incidence of different respiratory illnesses. Similarly, people who suffer from COVID-19 may query for their symptoms prior to accessing the medical system (or in lieu of it). To assist in the UK government's response to the COVID-19 pandemic we analyzed searches for relevant symptoms on the Bing web search engine from users in England to identify areas of the country where unexpected rises in relevant symptom searches occurred. These were reported weekly to the UK Health Security Agency to assist in their monitoring of the pandemic. Our analysis shows that searches for "fever" and "cough" were the most correlated with future case counts during the initial stages of the pandemic, with searches preceding case counts by up to 21 days. Unexpected rises in search patterns were predictive of anomalous rises in future case counts within a week, reaching an Area Under Curve of 0.82 during the initial phase of the pandemic, and later reducing due to changes in symptom presentation. Thus, analysis of regional searches for symptoms can provide an early indicator (of more than one week) of increases in COVID-19 case counts.

Symptom profiles and accuracy of clinical case definitions for COVID-19 in a community cohort: results from the Virus Watch study.

Background: Understanding symptomatology and accuracy of clinical case definitions for community COVID-19 cases is important for Test, Trace and Isolate (TTI) and future targeting of early antiviral treatment.   Methods: Community cohort participants prospectively recorded daily symptoms and swab results (mainly undertaken through the UK TTI system).  We compared symptom frequency, severity, timing, and duration in test positive and negative illnesses.  We compared the test performance of the current UK TTI case definition (cough, high temperature, or loss of or altered sense of smell or taste) with a wider definition adding muscle aches, chills, headache, or loss of appetite.     Results: Among 9706 swabbed illnesses, including 973 SARS-CoV-2 positives, symptoms were more common, severe and longer lasting in swab positive than negative illnesses.  Cough, headache, fatigue, and muscle aches were the most common symptoms in positive illnesses but also common in negative illnesses. Conversely, high temperature, loss or altered sense of smell or taste and loss of appetite were less frequent in positive illnesses, but comparatively even less frequent in negative illnesses.  The current UK definition had 81% sensitivity and 47% specificity versus 93% and 27% respectively for the broader definition. 1.7-fold more illnesses met the broader case definition than the current definition.  Conclusions: Symptoms alone cannot reliably distinguish COVID-19 from other respiratory illnesses. Adding additional symptoms to case definitions could identify more infections, but with a large increase in the number needing testing and the number of unwell individuals and contacts self-isolating whilst awaiting results.

An artificial intelligence approach for selecting effective teacher communication strategies in autism education.

Effective inclusive education is key in promoting the long-term outcomes of children with autism spectrum conditions (ASC). However, no concrete consensus exists to guide teacher-student interactions in the classroom. In this work, we explore the potential of artificial intelligence as an approach in autism education to assist teachers in effective practice in developing social and educational outcomes for children with ASC. We form a protocol to systematically capture such interactions, and conduct a statistical analysis to uncover basic patterns in the collected observations, including the longer-term effect of specific teacher communication strategies on student response. In addition, we deploy machine learning techniques to predict student response given the form of communication used by teachers under specific classroom conditions and in relation to specified student attributes. Our analysis, drawn on a sample of 5460 coded interactions between teachers and seven students, sheds light on the varying effectiveness of different communication strategies and demonstrates the potential of this approach in making a contribution to autism education.

Risk factors, symptom reporting, healthcare-seeking behaviour and adherence to public health guidance: protocol for Virus Watch, a prospective community cohort study.

INTRODUCTION: The coronavirus (COVID-19) pandemic has caused significant global mortality and impacted lives around the world. Virus Watch aims to provide evidence on which public health approaches are most likely to be effective in reducing transmission and impact of the virus, and will investigate community incidence, symptom profiles and transmission of COVID-19 in relation to population movement and behaviours. METHODS AND ANALYSIS: Virus Watch is a household community cohort study of acute respiratory infections in England and Wales and will run from June 2020 to August 2021. The study aims to recruit 50 000 people, including 12 500 from minority ethnic backgrounds, for an online survey cohort and monthly antibody testing using home fingerprick test kits. Nested within this larger study will be a subcohort of 10 000 individuals, including 3000 people from minority ethnic backgrounds. This cohort of 10 000 people will have full blood serology taken between October 2020 and January 2021 and repeat serology between May 2021 and August 2021. Participants will also post self-administered nasal swabs for PCR assays of SARS-CoV-2 and will follow one of three different PCR testing schedules based on symptoms. ETHICS AND DISSEMINATION: This study has been approved by the Hampstead National Health Service (NHS) Health Research Authority Ethics Committee (ethics approval number 20/HRA/2320). We are monitoring participant queries and using these to refine methodology where necessary, and are providing summaries and policy briefings of our preliminary findings to inform public health action by working through our partnerships with our study advisory group, Public Health England, NHS and government scientific advisory panels.

The impact of social and physical distancing measures on COVID-19 activity in England: findings from a multi-tiered surveillance system.

BackgroundA multi-tiered surveillance system based on influenza surveillance was adopted in the United Kingdom in the early stages of the coronavirus disease (COVID-19) epidemic to monitor different stages of the disease. Mandatory social and physical distancing measures (SPDM) were introduced on 23 March 2020 to attempt to limit transmission.AimTo describe the impact of SPDM on COVID-19 activity as detected through the different surveillance systems.MethodsData from national population surveys, web-based indicators, syndromic surveillance, sentinel swabbing, respiratory outbreaks, secondary care admissions and mortality indicators from the start of the epidemic to week 18 2020 were used to identify the timing of peaks in surveillance indicators relative to the introduction of SPDM. This timing was compared with median time from symptom onset to different stages of illness and levels of care or interactions with healthcare services.ResultsThe impact of SPDM was detected within 1 week through population surveys, web search indicators and sentinel swabbing reported by onset date. There were detectable impacts on syndromic surveillance indicators for difficulty breathing, influenza-like illness and COVID-19 coding at 2, 7 and 12 days respectively, hospitalisations and critical care admissions (both 12 days), laboratory positivity (14 days), deaths (17 days) and nursing home outbreaks (4 weeks).ConclusionThe impact of SPDM on COVID-19 activity was detectable within 1 week through community surveillance indicators, highlighting their importance in early detection of changes in activity. Community swabbing surveillance may be increasingly important as a specific indicator, should circulation of seasonal respiratory viruses increase.

Tracking COVID-19 using online search.

Previous research has demonstrated that various properties of infectious diseases can be inferred from online search behaviour. In this work we use time series of online search query frequencies to gain insights about the prevalence of COVID-19 in multiple countries. We first develop unsupervised modelling techniques based on associated symptom categories identified by the United Kingdom's National Health Service and Public Health England. We then attempt to minimise an expected bias in these signals caused by public interest-as opposed to infections-using the proportion of news media coverage devoted to COVID-19 as a proxy indicator. Our analysis indicates that models based on online searches precede the reported confirmed cases and deaths by 16.7 (10.2-23.2) and 22.1 (17.4-26.9) days, respectively. We also investigate transfer learning techniques for mapping supervised models from countries where the spread of the disease has progressed extensively to countries that are in earlier phases of their respective epidemic curves. Furthermore, we compare time series of online search activity against confirmed COVID-19 cases or deaths jointly across multiple countries, uncovering interesting querying patterns, including the finding that rarer symptoms are better predictors than common ones. Finally, we show that web searches improve the short-term forecasting accuracy of autoregressive models for COVID-19 deaths. Our work provides evidence that online search data can be used to develop complementary public health surveillance methods to help inform the COVID-19 response in conjunction with more established approaches.

What on-line searches tell us about public interest and potential impact on behaviour in response to minimum unit pricing of alcohol in Scotland.

AIMS: To investigate whether the introduction of minimum unit pricing (MUP) in Scotland on 1 May 2018 was reflected in changes in the likelihood of alcohol-related queries submitted to an internet search engine, and in particular whether there was any evidence of increased interest in purchasing of alcohol from outside Scotland. DESIGN: Observational study in which individual queries to the internet Bing search engine for 2018 in Scotland and England were captured and analysed. Fluctuations over time in the likelihood of specific topic searches were examined. The patterns seen in Scotland were contrasted with those in England. SETTING: Scotland and England. PARTICIPANTS: People who used the Bing search engine during 2018. MEASUREMENTS: Numbers of daily queries submitted to Bing in 2018 on eight alcohol-related topics expressed as a proportion of queries on that day on any topic. These daily likelihoods were smoothed using a 14-day moving average for Scotland and England separately. FINDINGS: There were substantial peaks in queries about MUP itself, cheap sources of alcohol and online alcohol outlets at the time of introduction of MUP in May 2018 in Scotland, but not England. These were relatively short-lived. Queries related to intoxication and alcohol problems did not show a MUP peak, but were appreciably higher in Scotland than in England throughout 2018. CONCLUSIONS: Analysis of internet search engine queries appears to show that a fraction of people in Scotland may have considered circumventing minimum unit pricing in 2018 by looking for on-line alcohol retailers. The overall higher levels of queries related to alcohol problems in Scotland compared with England mirrors the corresponding differences in alcohol consumption and harms between the countries.

Household serial interval of COVID-19 and the effect of Variant B.1.1.7: analyses from prospective community cohort study (Virus Watch).

Introduction: Increased transmissibility of B.1.1.7 variant of concern (VOC) in the UK may explain its rapid emergence and global spread. We analysed data from putative household infector - infectee pairs in the Virus Watch Community cohort study to assess the serial interval of COVID-19 and whether this was affected by emergence of the B.1.1.7 variant. Methods: The Virus Watch study is an online, prospective, community cohort study following up entire households in England and Wales during the COVID-19 pandemic. Putative household infector-infectee pairs were identified where more than one person in the household had a positive swab matched to an illness episode. Data on whether or not individual infections were caused by the B.1.1.7 variant were not available. We therefore developed a classification system based on the percentage of cases estimated to be due to B.1.1.7 in national surveillance data for different English regions and study weeks. Results: Out of 24,887 illnesses reported, 915 tested positive for SARS-CoV-2 and 186 likely 'infector-infectee' pairs in 186 households amongst 372 individuals were identified. The mean COVID-19 serial interval was 3.18 (95%CI: 2.55-3.81, sd=4.36) days. There was no significant difference (p=0.267) between the mean serial interval for VOC hotspots (mean = 3.64 days, (95%CI: 2.55 - 4.73)) days and non-VOC hotspots, (mean = 2.72 days, (95%CI: 1.48 - 3.96)). Conclusions: Our estimates of the average serial interval of COVID-19 are broadly similar to estimates from previous studies and we find no evidence that B.1.1.7 is associated with a change in serial intervals.  Alternative explanations such as increased viral load, longer period of viral shedding or improved receptor binding may instead explain the increased transmissibility and rapid spread and should undergo further investigation.

Digital technologies in the public-health response to COVID-19.

Digital technologies are being harnessed to support the public-health response to COVID-19 worldwide, including population surveillance, case identification, contact tracing and evaluation of interventions on the basis of mobility data and communication with the public. These rapid responses leverage billions of mobile phones, large online datasets, connected devices, relatively low-cost computing resources and advances in machine learning and natural language processing. This Review aims to capture the breadth of digital innovations for the public-health response to COVID-19 worldwide and their limitations, and barriers to their implementation, including legal, ethical and privacy barriers, as well as organizational and workforce barriers. The future of public health is likely to become increasingly digital, and we review the need for the alignment of international strategies for the regulation, evaluation and use of digital technologies to strengthen pandemic management, and future preparedness for COVID-19 and other infectious diseases.

The added value of online user-generated content in traditional methods for influenza surveillance.

There has been considerable work in evaluating the efficacy of using online data for health surveillance. Often comparisons with baseline data involve various squared error and correlation metrics. While useful, these overlook a variety of other factors important to public health bodies considering the adoption of such methods. In this paper, a proposed surveillance system that incorporates models based on recent research efforts is evaluated in terms of its added value for influenza surveillance at Public Health England. The system comprises of two supervised learning approaches trained on influenza-like illness (ILI) rates provided by the Royal College of General Practitioners (RCGP) and produces ILI estimates using Twitter posts or Google search queries. RCGP ILI rates for different age groups and laboratory confirmed cases by influenza type are used to evaluate the models with a particular focus on predicting the onset, overall intensity, peak activity and duration of the 2015/16 influenza season. We show that the Twitter-based models perform poorly and hypothesise that this is mostly due to the sparsity of the data available and a limited training period. Conversely, the Google-based model provides accurate estimates with timeliness of approximately one week and has the potential to complement current surveillance systems.

Estimating the Population Impact of a New Pediatric Influenza Vaccination Program in England Using Social Media Content.

BACKGROUND: The rollout of a new childhood live attenuated influenza vaccine program was launched in England in 2013, which consisted of a national campaign for all 2 and 3 year olds and several pilot locations offering the vaccine to primary school-age children (4-11 years of age) during the influenza season. The 2014/2015 influenza season saw the national program extended to include additional pilot regions, some of which offered the vaccine to secondary school children (11-13 years of age) as well. OBJECTIVE: We utilized social media content to obtain a complementary assessment of the population impact of the programs that were launched in England during the 2013/2014 and 2014/2015 flu seasons. The overall community-wide impact on transmission in pilot areas was estimated for the different age groups that were targeted for vaccination. METHODS: A previously developed statistical framework was applied, which consisted of a nonlinear regression model that was trained to infer influenza-like illness (ILI) rates from Twitter posts originating in pilot (school-age vaccinated) and control (unvaccinated) areas. The control areas were then used to estimate ILI rates in pilot areas, had the intervention not taken place. These predictions were compared with their corresponding Twitter-based ILI estimates. RESULTS: Results suggest a reduction in ILI rates of 14% (1-25%) and 17% (2-30%) across all ages in only the primary school-age vaccine pilot areas during the 2013/2014 and 2014/2015 influenza seasons, respectively. No significant impact was observed in areas where two age cohorts of secondary school children were vaccinated. CONCLUSIONS: These findings corroborate independent assessments from traditional surveillance data, thereby supporting the ongoing rollout of the program to primary school-age children and providing evidence of the value of social media content as an additional syndromic surveillance tool.

Studying User Income through Language, Behaviour and Affect in Social Media.

Automatically inferring user demographics from social media posts is useful for both social science research and a range of downstream applications in marketing and politics. We present the first extensive study where user behaviour on Twitter is used to build a predictive model of income. We apply non-linear methods for regression, i.e. Gaussian Processes, achieving strong correlation between predicted and actual user income. This allows us to shed light on the factors that characterise income on Twitter and analyse their interplay with user emotions and sentiment, perceived psycho-demographics and language use expressed through the topics of their posts. Our analysis uncovers correlations between different feature categories and income, some of which reflect common belief e.g. higher perceived education and intelligence indicates higher earnings, known differences e.g. gender and age differences, however, others show novel findings e.g. higher income users express more fear and anger, whereas lower income users express more of the time emotion and opinions.

Advances in nowcasting influenza-like illness rates using search query logs.

User-generated content can assist epidemiological surveillance in the early detection and prevalence estimation of infectious diseases, such as influenza. Google Flu Trends embodies the first public platform for transforming search queries to indications about the current state of flu in various places all over the world. However, the original model significantly mispredicted influenza-like illness rates in the US during the 2012-13 flu season. In this work, we build on the previous modeling attempt, proposing substantial improvements. Firstly, we investigate the performance of a widely used linear regularized regression solver, known as the Elastic Net. Then, we expand on this model by incorporating the queries selected by the Elastic Net into a nonlinear regression framework, based on a composite Gaussian Process. Finally, we augment the query-only predictions with an autoregressive model, injecting prior knowledge about the disease. We assess predictive performance using five consecutive flu seasons spanning from 2008 to 2013 and qualitatively explain certain shortcomings of the previous approach. Our results indicate that a nonlinear query modeling approach delivers the lowest cumulative nowcasting error, and also suggest that query information significantly improves autoregressive inferences, obtaining state-of-the-art performance.

Estimating the secondary attack rate and serial interval of influenza-like illnesses using social media.

OBJECTIVES: Knowledge of the secondary attack rate (SAR) and serial interval (SI) of influenza is important for assessing the severity of seasonal epidemics of the virus. To date, such estimates have required extensive surveys of target populations. Here, we propose a method for estimating the intrafamily SAR and SI from postings on the Twitter social network. This estimate is derived from a large number of people reporting ILI symptoms in them and\or their immediate family members. DESIGN: We analyze data from the 2012-2013 and the 2013-2014 influenza seasons in England and find that increases in the estimated SAR precede increases in ILI rates reported by physicians. RESULTS: We hypothesize that observed variations in the peak value of SAR are related to the appearance of specific strains of the virus and demonstrate this by comparing the changes in SAR values over time in relation to known virology. In addition, we estimate SI (the average time between cases) as 2·41 days for 2012 and 2·48 days for 2013. CONCLUSIONS: The proposed method can assist health authorities by providing near-real-time estimation of SAR and SI, and especially in alerting to sudden increases thereof.

Books average previous decade of economic misery.

For the 20(th) century since the Depression, we find a strong correlation between a 'literary misery index' derived from English language books and a moving average of the previous decade of the annual U.S. economic misery index, which is the sum of inflation and unemployment rates. We find a peak in the goodness of fit at 11 years for the moving average. The fit between the two misery indices holds when using different techniques to measure the literary misery index, and this fit is significantly better than other possible correlations with different emotion indices. To check the robustness of the results, we also analysed books written in German language and obtained very similar correlations with the German economic misery index. The results suggest that millions of books published every year average the authors' shared economic experiences over the past decade.