Is Google Trends a reliable tool for digital epidemiology? Insights from different clinical settings.

Internet-derived information has been recently recognized as a valuable tool for epidemiological investigation. Google Trends, a Google Inc. portal, generates data on geographical and temporal patterns according to specified keywords. The aim of this study was to compare the reliability of Google Trends in different clinical settings, for both common diseases with lower media coverage, and for less common diseases attracting major media coverage. We carried out a search in Google Trends using the keywords "renal colic", "epistaxis", and "mushroom poisoning", selected on the basis of available and reliable epidemiological data. Besides this search, we carried out a second search for three clinical conditions (i.e., "meningitis", "Legionella Pneumophila pneumonia", and "Ebola fever"), which recently received major focus by the Italian media. In our analysis, no correlation was found between data captured from Google Trends and epidemiology of renal colics, epistaxis and mushroom poisoning. Only when searching for the term "mushroom" alone the Google Trends search generated a seasonal pattern which almost overlaps with the epidemiological profile, but this was probably mostly due to searches for harvesting and cooking rather than to for poisoning. The Google Trends data also failed to reflect the geographical and temporary patterns of disease for meningitis, Legionella Pneumophila pneumonia and Ebola fever. The results of our study confirm that Google Trends has modest reliability for defining the epidemiology of relatively common diseases with minor media coverage, or relatively rare diseases with higher audience. Overall, Google Trends seems to be more influenced by the media clamor than by true epidemiological burden.

Analyzing health insurance claims on different timescales to predict days in hospital.

Health insurers maintain large databases containing information on medical services utilized by claimants, often spanning several healthcare services and providers. Proper use of these databases could facilitate better clinical and administrative decisions. In these data sets, there exists many unequally spaced events, such as hospital visits. However, data mining of temporal data and point processes is still a developing research area and extracting useful information from such data series is a challenging task. In this paper, we developed a time series data mining approach to predict the number of days in hospital in the coming year for individuals from a general insured population based on their insurance claim data. In the proposed method, the data were windowed at four different timescales (bi-monthly, quarterly, half-yearly and yearly) to construct regularly spaced time series features extracted from such events, resulting in four associated prediction models. A comparison of these models indicates models using a half-yearly windowing scheme delivers the best performance on all three populations (the whole population, a senior sub-population and a non-senior sub-population). The superiority of the half-yearly model was found to be particularly pronounced in the senior sub-population. A bagged decision tree approach was able to predict 'no hospitalization' versus 'at least one day in hospital' with a Matthews correlation coefficient (MCC) of 0.426. This was significantly better than the corresponding yearly model, which achieved 0.375 for this group of customers. Further reducing the length of the analysis windows to three or two months did not produce further improvements.

Resilient Systemics to Telehealth Support for Clinical Psychiatry and Psychology.

Reliably expanding our clinical practice and lowering our overhead with telepsychiatry, telepsychology, distance counseling and online therapy, requires resilient and antifragile system and tools. When utilized appropriately these technologies may provide greater access to needed services to include more reliable treatment, consultation, supervision, and training. The wise and proper use of technology is fundamental to create and boost outstanding social results. We present, as an example, the main steps to achieve application resilience and antifragility at system level, for diagnostic and therapeutic telepractice and telehealth support, devoted to psychiatry and psychology application. This article presents a number of innovations that can take psychotherapy treatment, supervision, training, and research forward, towards increased effectiveness application.

Predicting days in hospital using health insurance claims.

Health-care administrators worldwide are striving to lower the cost of care while improving the quality of care given. Hospitalization is the largest component of health expenditure. Therefore, earlier identification of those at higher risk of being hospitalized would help health-care administrators and health insurers to develop better plans and strategies. In this paper, a method was developed, using large-scale health insurance claims data, to predict the number of hospitalization days in a population. We utilized a regression decision tree algorithm, along with insurance claim data from 242 075 individuals over three years, to provide predictions of number of days in hospital in the third year, based on hospital admissions and procedure claims data. The proposed method performs well in the general population as well as in subpopulations. Results indicate that the proposed model significantly improves predictions over two established baseline methods (predicting a constant number of days for each customer and using the number of days in hospital of the previous year as the forecast for the following year). A reasonable predictive accuracy (AUC =0.843) was achieved for the whole population. Analysis of two subpopulations-namely elderly persons aged 63 years or older in 2011 and patients hospitalized for at least one day in the previous year-revealed that the medical information (e.g., diagnosis codes) contributed more to predictions for these two subpopulations, in comparison to the population as a whole.

A study on quality assessment for medical ultrasound video compressed via HEVC.

The quality of experience and quality of service provided in the healthcare sector are critical in evaluating the reliable delivery of the healthcare services provided. Medical images and videos play a major role in modern e-health services and have become an integral part of medical data communication systems. The quality evaluation of medical images and videos is an essential process, and one of the ways of addressing it is via the use of quality metrics. In this paper, we evaluate the performance of seven state-of-the-art video quality metrics with respect to compressed medical ultrasound video sequences. We study the performance of each video quality metric in representing the diagnostic quality of the video, by evaluating the correlation of each metric with the subjective opinions of medical experts. The results indicate that the visual information fidelity, structural similarity index, and universal quality index metrics show good correlation with the subjective scores provided by medical experts. The tests also investigate the performance of the emerging video compression standard, high-efficiency video coding-HEVC, for medical ultrasound video compression. The results show that, using HEVC with the considered ultrasound video sequences, a diagnostically reliable compressed ultrasound video can be obtained for compression with values of the quantization parameter up to 35.

The promise of data-driven care.

The growing adoption of electronic medical records and advances in health information technology are fueling an explosion of new health data. Expectations are high that new data resources will guide the transformation of the health care industry and positively influence population health. There have been challenges and opportunities at every turn, and progress has been slow, but mounting evidence suggests that better use of data is moving health care in the right direction.

Navigating an ocean of information: how Community Care of North Carolina uses data to improve care and control costs.

Community Care of North Carolina's 14 networks use data analysis to provide relevant solutions that are responsive to unique regional environments. This article describes some of the ways that these networks use data to improve patient self-management, to meet providers' needs, to improve quality of care, and to control costs.

Growth in health care data causing an evolution in the pharmaceutical industry.

A health care ecosystem is evolving in which all stakeholders will need to work together, apply new technologies, and use disparate data sources to gain insights, increase efficiencies, and improve patient outcomes. The pharmaceutical industry is leveraging its experience and analytics capabilities to play an important role in this evolution.

Use of big data by Blue Cross and Blue Shield of North Carolina.

The health care industry is grappling with the challenges of working with and analyzing large, complex, diverse data sets. Blue Cross and Blue Shield of North Carolina provides several promising examples of how big data can be used to reduce the cost of care, to predict and manage health risks, and to improve clinical outcomes.

The value of all-payer claims databases to states.

All-payer claims databases are being developed in states across the nation to fill gaps in information about the health care system. The value of such databases is becoming more apparent as these databases mature and are used more frequently to help states better understand their health care utilization and costs.

The utility of imputed matched sets. Analyzing probabilistically linked databases in a low information setting.

OBJECTIVE: To compare results from high probability matched sets versus imputed matched sets across differing levels of linkage information. METHODS: A series of linkages with varying amounts of available information were performed on two simulated datasets derived from multiyear motor vehicle crash (MVC) and hospital databases, where true matches were known. Distributions of high probability and imputed matched sets were compared against the true match population for occupant age, MVC county, and MVC hour. Regression models were fit to simulated log hospital charges and hospitalization status. RESULTS: High probability and imputed matched sets were not significantly different from occupant age, MVC county, and MVC hour in high information settings (p > 0.999). In low information settings, high probability matched sets were significantly different from occupant age and MVC county (p < 0.002), but imputed matched sets were not (p > 0.493). High information settings saw no significant differences in inference of simulated log hospital charges and hospitalization status between the two methods. High probability and imputed matched sets were significantly different from the outcomes in low information settings; however, imputed matched sets were more robust. CONCLUSIONS: The level of information available to a linkage is an important consideration. High probability matched sets are suitable for high to moderate information settings and for situations involving case-specific analysis. Conversely, imputed matched sets are preferable for low information settings when conducting population-based analyses.

How to exploit twitter for public health monitoring?

OBJECTIVES: Detecting hints to public health threats as early as possible is crucial to prevent harm from the population. However, many disease surveillance strategies rely upon data whose collection requires explicit reporting (data transmitted from hospitals, laboratories or physicians). Collecting reports takes time so that the reaction time grows. Moreover, context information on individual cases is often lost in the collection process. This paper describes a system that tries to address these limitations by processing social media for identifying information on public health threats. The primary objective is to study the usefulness of the approach for supporting the monitoring of a population's health status. METHODS: The developed system works in three main steps: Data from Twitter, blogs, and forums as well as from TV and radio channels are continuously collected and filtered by means of keyword lists. Sentences of relevant texts are classified relevant or irrelevant using a binary classifier based on support vector machines. By means of statistical methods known from biosurveillance, the relevant sentences are further analyzed and signals are generated automatically when unexpected behavior is detected. From the generated signals a subset is selected for presentation to a user by matching with user queries or profiles. In a set of evaluation experiments, public health experts assessed the generated signals with respect to correctness and relevancy. In particular, it was assessed how many relevant and irrelevant signals are generated during a specific time period. RESULTS: The experiments show that the system provides information on health events identified in social media. Signals are mainly generated from Twitter messages posted by news agencies. Personal tweets, i.e. tweets from persons observing some symptoms, only play a minor role for signal generation given a limited volume of relevant messages. Relevant signals referring to real world outbreaks were generated by the system and monitored by epidemiologists for example during the European football championship. But, the number of relevant signals among generated signals is still very small: The different experiments yielded a proportion between 5 and 20% of signals regarded as "relevant" by the users. Vaccination or education campaigns communicated via Twitter as well as use of medical terms in other contexts than for outbreak reporting led to the generation of irrelevant signals. CONCLUSIONS: The aggregation of information into signals results in a reduction of monitoring effort compared to other existing systems. Against expectations, only few messages are of personal nature, reporting on personal symptoms. Instead, media reports are distributed over social media channels. Despite the high percentage of irrelevant signals generated by the system, the users reported that the effort in monitoring aggregated information in form of signals is less demanding than monitoring huge social-media data streams manually. It remains for the future to develop strategies for reducing false alarms.

Access to digital technology among families coming to urban pediatric primary care clinics.

OBJECTIVE: Digital technologies offer new platforms for health promotion and disease management. Few studies have evaluated the use of digital technology among families receiving care in an urban pediatric primary care setting. METHODS: A self-administered survey was given to a convenience sample of caregivers bringing their children to 2 urban pediatric primary care centers in spring 2012. The survey assessed access to home Internet, e-mail, smartphone, and social media (Facebook and Twitter). A "digital technology" scale (0-4) quantified the number of available digital technologies and connections. Frequency of daily use and interest in receiving medical information digitally were also assessed. RESULTS: The survey was completed by 257 caregivers. The sample was drawn from a clinical population that was 73% African American and 92% Medicaid insured with a median patient age of 2.9 years (interquartile range 0.8-7.4). Eighty percent of respondents reported having Internet at home, and 71% had a smartphone. Ninety-one percent reported using e-mail, 78% Facebook, and 27% Twitter. Ninety-seven percent scored ≥1 on the digital technology scale; 49% had a digital technology score of 4. The digital technology score was associated with daily use of digital media in a graded fashion (P < .0001). More than 70% of respondents reported that they would use health care information supplied digitally if approved by their child's medical provider. CONCLUSIONS: Caregivers in an urban pediatric primary care setting have access to and frequently use digital technologies. Digital connections may help reach a traditionally hard-to-reach population.

Costs of cloud computing for a biometry department. A case study.

BACKGROUND: "Cloud" computing providers, such as the Amazon Web Services (AWS), offer stable and scalable computational resources based on hardware virtualization, with short, usually hourly, billing periods. The idea of pay-as-you-use seems appealing for biometry research units which have only limited access to university or corporate data center resources or grids. OBJECTIVES: This case study compares the costs of an existing heterogeneous on-site hardware pool in a Medical Biometry and Statistics department to a comparable AWS offer. METHODS: The "total cost of ownership", including all direct costs, is determined for the on-site hardware, and hourly prices are derived, based on actual system utilization during the year 2011. Indirect costs, which are difficult to quantify are not included in this comparison, but nevertheless some rough guidance from our experience is given. To indicate the scale of costs for a methodological research project, a simulation study of a permutation-based statistical approach is performed using AWS and on-site hardware. RESULTS: In the presented case, with a system utilization of 25-30 percent and 3-5-year amortization, on-site hardware can result in smaller costs, compared to hourly rental in the cloud dependent on the instance chosen. Renting cloud instances with sufficient main memory is a deciding factor in this comparison. CONCLUSIONS: Costs for on-site hardware may vary, depending on the specific infrastructure at a research unit, but have only moderate impact on the overall comparison and subsequent decision for obtaining affordable scientific computing resources. Overall utilization has a much stronger impact as it determines the actual computing hours needed per year. Taking this into ac count, cloud computing might still be a viable option for projects with limited maturity, or as a supplement for short peaks in demand.

[Assessment of the quality of medical assistance for patients with acute ST elevation coronary syndrome for 2009-2010 in regions of the Russian Federation participating in the "vascular program" (by the data of the Russian ACS Register)].

AIM: To assess quality of medical assistance for patients with acute ST elevation coronary syndrome (aSTeCS) for the period from 2009 to 2010 in 23 administrative regions of the Russian Federation (RF) realizing the "vascular program". MATERIAL AND METHODS: We analysed management of aSTeCS patients treated in the regional vascular centers and/or primary vascular departments of 23 administrative regions of the RF for the period from January 1, 2009 to January 1, 2011. Mean age of the patients was 64 (56-75) years, 65.8% were males. For the above period computer medical information was available for 45407 acute coronary syndrome (ACS) patients, of them the diagnosis of aSTeCS was in 17514 patients. RESULTS: We found that most aSTeCS patients seek medical advice late, prehospital aspirin was prescribed only in 50-60% cases. Thrombolytic therapy (TLT) was performed, on the average, in 22 and 27% cases in 2009 u 2010, respectively A definite positive trend in TLT administration in 2009-2010 was seen only in 5 regions. In 2010, frequency of TLT conduction was below the evarage for all the sample in 8 regions of the RE Procedures of urgent percutaneous coronary intervention (UPCI) in 2009 were made, on the average, in aSTeCS patients, in 2010--in 22,6%. A positive trend in application of UPCI in aSTeCS patients was registered in 9 RF regions. The number of UPCI procedures under 100 in 2010 was seen in 5 RF regions. CONCLUSION: CS Register provided data on application of high-tech treatment and pharmacotherapy in 2009 u 2010 in medical institutions of 23 RF regions realizing "vascular program".

Mobile Medical Education (MoMEd) - how mobile information resources contribute to learning for undergraduate clinical students - a mixed methods study.

BACKGROUND: Mobile technology is increasingly being used by clinicians to access up-to-date information for patient care. These offer learning opportunities in the clinical setting for medical students but the underlying pedagogic theories are not clear. A conceptual framework is needed to understand these further. Our initial questions were how the medical students used the technology, how it enabled them to learn and what theoretical underpinning supported the learning. METHODS: 387 medical students were provided with a personal digital assistant (PDA) loaded with medical resources for the duration of their clinical studies. Outcomes were assessed by a mixed-methods triangulation approach using qualitative and quantitative analysis of surveys, focus groups and usage tracking data. RESULTS: Learning occurred in context with timely access to key facts and through consolidation of knowledge via repetition. The PDA was an important addition to the learning ecology rather than a replacement. Contextual factors impacted on use both positively and negatively. Barriers included concerns of interrupting the clinical interaction and of negative responses from teachers and patients. Students preferred a future involving smartphone platforms. CONCLUSIONS: This is the first study to describe the learning ecology and pedagogic basis behind the use of mobile learning technologies in a large cohort of undergraduate medical students in the clinical environment. We have developed a model for mobile learning in the clinical setting that shows how different theories contribute to its use taking into account positive and negative contextual factors.The lessons from this study are transferable internationally, to other health care professions and to the development of similar initiatives with newer technology such as smartphones or tablet computers.