Contact Us

Home

About us

Services

AI Excellence

case studies

publications

HEOR Certificationheor Certification

AI for Medical Writing

Contact

  • How to Improve Healthcare Outcomes with Key Analytic Tools?

    How to Improve Healthcare Outcomes with Key Analytic Tools?

    Healthcare outcomes are defined as the changes observed and/or recorded in health status of individual or population patient/s usually due to an intervention, measures or specific healthcare investment. (1) The goal is to save the lives, shorten hospital stays and build healthier communities relying on preventative measures. (2) The fundamental steps of improving outcomes are measuring, reporting and analysing the outcomes. The efficient synthesis, organization and analysis of healthcare data offer the healthcare providers and other healthcare stakeholders with systematic and insightful treatment, measures and diagnosis. This may lead to higher patient care quality and better outcomes at lower costs.

    Healthcare industries generate a huge amount of information known as ‘big data’, driven by record keeping, compliance and regulatory requirement, potential to improve healthcare deliveries, and digitalization of historic data. (3) It include the clinical data from hospitals, clinics, pharmacies, pathological laboratories, diagnostic/imaging reports, healthcare insurances, and administrative data; individual patient data in electronic patient records (EPR) during various phases of clinical trials; pre-clinical data; hospitalization frequency data; research articles and reviews in scientific and medical journal; and information from various healthcare data resources; social media posts on different platforms; and less patient-specific information such as emergency care, news feed and healthcare magazines. (4) As per reports the data of U.S. alone may reach 1024 gigabyte soon. (3) There is need of rapidly transforming the volumes of aggregated healthcare data to value-based healthcare. 

    The analysis and assessment of huge healthcare data can be performed using advance platforms and tools with ability to handle structured, semi-structured or unstructured data. The data from random sources need to connect, match, cleanse and prepared for processing using three main steps of extract, transform and load. (4) The key platforms and tools to handle ‘big data’ are the Hadoop Distributed File System, MapReduce, PIG and PIG Latin, Hive, Jaql, Zookeeper, HBase, Cassandra, Oozie, Lucene, Avro, Mahout. (3) The analytic tools combine knowledge and data driven insights for identifying risks-factor and augmentation. These analytic tools have important applications for queries, reports, online analytical processing (OLAP) and data mining. (3) These analytic tools can search and analyse massive quantity of information from past treatments, latest published researches and healthcare databases to predict outcomes for individual patient. (5)

    Data analytic tools benefit all the components of healthcare system to improve healthcare outcomes. These components are healthcare service providers, patients, payers, stakeholders and managements. (6) Healthcare providers can develop new strategies and plan to care for patients such as reduce unnecessary hospitalizations and expenses. The patients at greatest risk of readmission can be identified and get guidance on follow ups for efficient resource utilization to save a huge amount of money spent each year on unnecessary hospitalization.

    The time gap always exists between a clinical event and the information to reach healthcare decision makers which could have bring the positive outcomes. The near real-time health surveillance can be performed using the information from social media blogs, micro-blogging on social networking sites such as Twitter and Facebook, and newspaper articles. (7) These social media networks provide information on the current locations by geo-tagged alerts. Real time analytic tools bring together the disparate information from various resources to the point of patient care, where the benefit can really be life-saving. It offers healthcare system access the most up-to date information. It realigns task based on priorities of healthcare providers, stakeholders, and insurers to improve healthcare outcomes. It addresses the gaps in care, quality, risk, utilization and regulatory requirement to support the improvements in clinical and quality outcomes; and financial performances. It provides a real-time report stating the real healthcare status of a patient and suggestions on improvement of the quality, achievement of compliance and realization of full reimbursement for their services. (8)

    It is often difficult for patients and clinician to keep the track of various healthcare organization-specific programs. The analytic tools may provide clinicians the information on a right program an eligible patient may enrol at a right time to help improve care and decrease costs. (8) The healthcare providers can assess patient-specific eligibility, gaps in care, risk scores, and historical medical information at the point of care which can be easily integrated into their existing operational model.

    The analytic tools improve healthcare outcomes by reducing the efforts and time required to handle ‘big data’ and conversion of volume to value-based information. These tools help encourage quality care to the patients benefitting payers as well as investors. The analytic tools would significantly support the advancement of medical and health science.

    Become an Certified HEOR Professional – Enrol yourself here!

    References

    1. Velentgas P., Dreyer N.A., and Wu W. A. (eds) Outcome Definition and Measurement. In ‘Developing a Protocol for Observational Comparative Effectiveness research: A User’s Guide’. Rockville,MD: Agency for Healthcare Research and Quality; AHRQ Publication No. 12(13)-EHC099, 2013.
    2. Kumar P. How real time analytics improves outcomes in healthcare. Published online on ‘IBM Cloud Blog’ dated June 19, 2017.
    3. Raghupathi W. and Raghupathi V. (2014). Big data analytics in healthcare: promise and potential. Health Information Science and Systems 2, 3
    4. Gandomi A., and Haider M. (2015). Beyond the hype: Big data concepts, methods, and analytics. International Journal of information Management 35, 137-144.
    5. Winters-Miner L.A. (2014) Seven ways predictive analytics can improve healthcare. Medical predictive analytics have the potential to revolutionize healthcare around the world. Published online on ‘Elsevier’s Daily stories for the science, Technology and health communities’ on Oct 06, 2014.
    6. Sun J. and Reddy C.K. (2013). Big data analytics for healthcare. Published in ‘KDD 2013 Proceedings of the 19th ACM SIAM International Conference on Knowledge Discovery and Data Mining’ held at Austin, TX, pg 1525-1525.
    7. Lee K., Agrawal A., and Choudhary A. (2013) Real-time disease surveillance using Twitter data: demonstration on flu and cancer. Published in ‘KDD 2013 proceedings of the 19th ACM SIGKDD international conference on knowledge discovery and data mining’, held at Chicago, Illinois, USA, pg 1474-1477.
    8. Rizzo D. The power of real-time analytics at the point of care. Published online on ‘Health IT Outcomes: Guest Column’ dated Dec 14, 2015.

    MarksMan Healthcare

    , , , , , , , ,

  • How to Elicit Expert Opinion to Understand Missing Health Outcomes?

    How to Elicit Expert Opinion to Understand Missing Health Outcomes?

    Missing data are a big concern in any research project and are often unavoidable in spite of investigators’ best efforts. Missing outcomes have two effects: reduced precision and power, and bias. Also, the loss of precision is inevitable, except the possible use of the available data; e.g. to be sure not to exclude from the analysis individuals who dropped out before the end of the study but who nevertheless reported intermediate values of the outcome. However, the statistician can aim to reduce bias through suitable choice of an analysis. (1)

    Randomized controlled trials (RCTs) typically have missing outcome data for some participants. Patient-reported outcomes (PROs) such as health-related quality of life (QoL) are mostly prone to missing data due to patients failing to complete follow-up questionnaires. Assumptions are often applied in case of statistical analyses for missing data to explicitly specify the values of the missing data: e.g. missing values being failures, as in smoking cessation trials. Other assumptions are inherent statements about the similarity of distributions, such as ‘last observation carried forward’. (1,2)

    In the primary trial analysis, an approach is often proposed which is valid under plausible assumptions for studies with the missing data. Instead of assuming that the data are ‘missing completely at random’ (MCAR), the primary analysis should suppose them to be ‘missing at random’ (MAR), i.e. the probability of missing data does not depend on the patient’s outcome, after conditioning on the observed variables (e.g. the patients’ baseline characteristics). However, the MAR assumption is unlikely to be used in many settings; for example, patients in relatively poor health are less likely to complete the requisite questionnaires, thus making the outcome data ‘missing not at random’ (MNAR). (2)

    The US National Research Council (NRC) report on missing data in clinical trials advocates sensitivity analyses for recognizing the data to be MNAR, in accordance with general methodological guidance for dealing with missing data and previous specific advice for intention-to-treat (ITT) analysis in RCTs. (3) On the other hand, systematic reviews show that in practice RCTs do not handle missing data appropriately. (4) Sensitivity analysis can be approached with either statistical modeling of parameters that represent outcome differences between individuals with complete versus missing data and/or exploring varying inferences with respect to the ‘sensitivity parameters’ assuming specific values. (5) The final output, i.e. results and conclusion, can then be compared over a reasonable range of values, possibly including a ‘tipping-point’ when results change. However, this approach does have a set of shortcomings. (2)

    An alternative is to allow experts to quantify their views. This is not only more intuitive and attractive for them, but it also considers a fully Bayesian approach and properly captures and reflects expert opinion (and associated uncertainty) about the missing data in the subsequent estimate of the treatment effect and its credible interval. This is particularly useful for those needing a quantitative summary of the trial, such as systematic reviewers, decision makers and health providers, as it provides a quantitative synopsis of interpretation of results by experts, given the missing data. When reviewing the study, experts will implicitly ‘fill in’ the gaps created by the missing data to arrive at their conclusions. The proposed elicitation approach, together with a Bayesian analysis, allows the study to comprehensibly quantify the impact of incorporating expert knowledge through to the estimates of treatment effectiveness.(1,2)

    Sensitivity analyses using Bayesian approach require practical tools for easier expert elicitation, and recent research focuses on elicitation approaches within group meetings. Group level elicitation has benefits for training and clarification and facilitates behavioral aggregation for achieving consensus. (6) However, because of the ‘feedback’ loop, these approaches are costly in both money and time. Thus, in many RCTs, it may not be viable to elicit opinion from a sufficient number and range of experts. Easier uptake of recommended approaches for sensitivity analysis for missing data within RCTs requires more accessible, practical tools for eliciting and synthesizing expert opinion to be developed and exemplified. (2)

    Using open source software like face-to-face or online ones to elicit beliefs from reasonably large number of experts without imposing an undue burden is one option that has been recently suggested. With this tool, the elicited views can be converted into informative priors for the sensitivity parameters in a pattern-mixture model which will allow for correlation in the elicited values across the trial arms. After this, the trial data can be re-evaluated under different MNAR assumptions to explore the robustness of the results. These methods, along with the expected level of loss to follow-up, could provide an improved estimate of the probable impact of missing data on the trial’s results. Therefore, this approach can significantly help improve trial design, so that the study results are more robust to anticipated levels of missing data.

    Become an Certified HEOR Professional – Enrol yourself here!

    References

    1. Jackson D, White IR, Leese M. How much can we learn about missing data?: an exploration of a clinical trial in psychiatry. Journal of the Royal Statistical Society Series A, (Statistics in Society). 2010; 173(3):593-612.
    2. Mason AJ, Gomes M, Grieve R, et al. Development of a practical approach to expert elicitation for randomized controlled trials with missing health outcomes: Application to the IMPROVE trial. Clinical Trials 2017; 14(4):357–367.
    3. Little RJ, D’Agostino R, Cohen ML, et al. The prevention and treatment of missing data in clinical trials. N Engl J Med 2012; 367(14):1355–1360.
    4. Bell ML, Fiero M, Horton NJ, et al. Handling missing data in RCTs; a review of the top medical journals. BMC Med Res Methodol 2014; 14:118.
    5. Little RJA. A class of pattern-mixture models for normal incomplete data. Biometrika 1994; 81(3):471–483.
    6. O’Hagan A, Buck CE, Daneshkhah A, et al. Uncertain judgments: eliciting experts’ probabilities. 1st ed. Hoboken, NJ: John Wiley & Sons, 2006.

    MarksMan Healthcare

    , , , , , , , ,

  • How Data Visualization is Helping in Healthcare Decision Making?

    How Data Visualization is Helping in Healthcare Decision Making?

    Health informatics systems are evolving with an aim to revolutionize health and healthcare programs worldwide. However, turning this hope-filled vision into a reality will take enormous effort from thousands of designers, analysts, software engineers, usability specialists, and medical professionals. Albeit challenging, the role of information visualization and visual analytics processes is gaining importance. These algorithms, interactive designs, and analytic processes support exploration, monitoring, insight discovery, professional collaboration, and comprehensible presentations to patients, clinicians, policy makers, and the general public.

    Data visualization is the art of representing data in a pictorial or graphical format. Analyzing patterns and trends from large data sets can be a herculean process. Data visualization helps in simplifying this process and allows decision-makers to derive analytical results from information presented visually. Patterns, trends and correlations that might go undetected in text-based data can be exposed and recognised easier with data visualization.

    Critical building blocks of healthcare analytics are data analytics and visual analytics. Both consist of systematic approaches, techniques and tools, clinical and business resources, used to interpret and analyze high volumes of dynamic patient data, clinical records, financial and other business data, and present findings to various audiences from the clinicians, hospital administration and management, to government and the public. Visual analysis refers to “the science of analytical reasoning facilitated by interactive visual interfaces”. Healthcare providers increasingly explore various visual and interactive techniques in generating and examining large graphs and charts, interactive visualizations, and 2D/3D visualization of discrete event simulation (DES) to understand complex and large datasets, identify and connections and trends, model and simulate healthcare events, and communicate and interpret the findings. Expected outcomes include more efficient and effective clinical performance monitoring and improvement, patient flow modeling and management, better patient care quality, safety and efficiency, better support for clinical costing and resource coordination, better planned growth and competitive advantage.

    Conventional visualization methods often require significant processing time, which limits high-throughput analysis. Interactive visualization systems maintain a closed loop between the user and the system and, thus, need to be very fast. Building such a system requires the development of new visualization methods; and there exists the need to design new and effective interaction techniques which are being developed by researchers. One of such techniques is ‘R’ that is being extensively used for statistical computing and graphics. Informatics for Integrating Biology and the Bedside (i2b2), an initiative sponsored by the NIH Roadmap National Centers for Biomedical Computing is another such program that provides a query tool that supplies aggregate counts and basic analyses of patient populations from clinical data warehouses (CDWs). i2b2 (i2b2 to Tableau) is effective at estimating patient cohort sizes and has an extendable architecture where plug-ins with additional features can be developed. Similarly, Hadoop is an open source program; which, according to researchers, is the most significant data processing platform for big data analytics in healthcare. It supports the processing and storage of extremely large data sets in a distributed computing environment, and will open up entire new research domains for discovery. To add to this list is Python, which is yet another solid and open scientific computing and visualization framework. Python is often known as the Swiss Army knife of programming languages–it can, among many things, support machine learning, web development, web scraping, desktop applications. While R is more narrowly focused on statistics compared to Python, it is also great at several things. First, it offers well-documented algorithms and tools for whatever you want to do in statistics. Second, it has fantastic visualization software (better than Python, it could be argued), and thirdly it is great at professional document generation for both reports and data education. Furthermore, recent developments in the R language, and in particular the Shiny package for R, have allowed R programmers to interactively show the output for R programs to Web browsers. The R and Shiny package reactively updates output in response to changing input by means of widgets (such as sliders and radio buttons) but owing to the flexible R language and combination with extension packages, the pharmacometrician has control in coding all elements of a population model, the appearance of the application’s user interface, and generated output.

    Today, data visualization solutions can be found everywhere in healthcare systems from hospital operations monitoring and patient profiling to demand projection and capacity planning. However, recent technological developments have made it easier to work with data than it has ever been in the past in case of business intelligence as well.Business Intelligence (BI) can be described as “a set of techniques and tools for the acquisition and transformation of raw data into meaningful and useful information for business analysis purpose”.

    Now, it’s not necessary to work with complex data sets that take a long time to sort and make sense of. Contemporary data dashboards allow users to access data in a visual manner that allows for faster and more accurate business decisions to be made. The payoff from joining the big-data and advanced-analytics management revolution is no longer in doubt.

    India also is witnessing healthcare analytics being rapidly adopted. Data coming from variety of sources are being recorded in different forms like patient records, patient satisfaction surveys, patient complaint registers, quality of care assessments, etc. Researchers in India feel that effective analysis of these large amounts of organizational data can lead to better decision making.

    Additionally, social media are opening remarkable possibilities for health and healthcare researchers. For the first time in history much of what we do is recorded online, and for the first time in history we have the tools to capture, analyze, and visualize these data. Moreover, health informatics databases and networks have amplified benefits with information visualization as it dramatically expands the capacity of patients, clinicians, and public health policy makers to make better decisions.

    To put them together in one sentence, “Visualizing business data (data visualization), the right way helps to find meaningful patterns in data (analytics) to analyze the business and make decisions (business intelligence) accordingly”.

    Become an Certified HEOR Professional – Enrol yourself here!

    MarksMan Healthcare

    , , ,