Posts Tagged ‘business intelligence’
by December 15th, 2015on
TREND #6: USE PREDICTIVE ANALYTICS TO REDUCE READMISSIONS AND IMPROVE OUTCOMES
Predictive Analytics solutions uncover insights from trends and patterns to determine the impact of operational adjustments and market forces on healthcare organizations. Statistical analysis and predictive modeling expand on the findings gained through business intelligence solutions to answer “What will happen?” given certain business and/or clinical situations. Predictive analytics combs through massive amounts of data and analyzes it to find patterns, assess probability of occurrence, and predict outcomes. Healthcare organizations are leveraging predictive analytics to:
- Reduce patient readmissions
- Increase the accuracy of patient diagnosis
- Deliver more targeted care to high-risk patients
- Provide better overall outcomes for the individuals they serve
by December 8th, 2015on
INTEGRATE CLINICAL AND CLAIMS DATA TO ENABLE POPULATION HEALTH MANAGEMENT INSIGHT
Technology-enabled population health initiatives have traditionally relied solely on either clinical data or claims data. While this method has value, there is a tremendous opportunity for healthcare organizations to take population health efforts to the next level by integrating both clinical and claims data. Integrating clinical data from electronic medical records with claims data can help develop a more complete patient view and improve overall care. Merging clinical and claims data provides healthcare organizations with a more complete picture and delivers the insights needed to address their most complex challenges.When combined, clinical and claims data can be used to:
- Compare recommended care against evidence-based practices
- Improve overall care management and population health efforts
- Reduce unnecessary clinical procedures
- Help patients avoid hospitalization by identifying early risk factors
The integration of clinical and claims data empowers healthcare providers to delivery higher quality and more proactive care for their patients.
Read the rest of this post »
by August 28th, 2014on
In a recent issue of PC Today (www.pctoday.com), there was a quote by Cindi Howson of BI Scorecard that really stuck in my mind: “There are far too many cases of companies having good data, good tools, but a culture that’s a barrier to using that data for action.” Frequently, outside consultants are brought into an organization, especially in healthcare, to pull data out of silo’ed applications, cleanse it and land it in an enterprise data warehouse (EDW). Then the real fun begins as the organization tries to determine what their expectations are from this treasure trove of data. More importantly, this struggle to determine the value of the integration of clinical, operational and financial data can stall the return on investment for this important and difficult effort.
In conducting a business intelligence (BI) strategy, it is very important to investigate those silo’ed data sources to determine which elements can benefit which part of the organization and to notify internal groups of the new resources. In other words, the Enterprise Data Warehouse needs exploration and promotion to the key stakeholders or by the key stakeholders to gain new insights and derive the new value. Matching data to the right people is fundamental to success and deserves its own tracking mechanism in data governance. Moving beyond the original stakeholders and their requirements in a BI strategy and getting down to who really will use the data and how it is used helps drive stronger outcomes for the use of the integrated data. It truly isn’t just start with the end in mind, but exploring how the new integrated views of information can drive improved operational processes and solve daily problems in a real-time manner.
It is often frustrating to data warehouse builders because they understand the value stored inside but don’t know who needs the information to take action. It is worth educating and promoting this big investment! If a key data source is overlooked for real improvements in an important corporate process, then find it and add it. If data has moved past its useful life, then it should be moved to an archive to keep the enterprise data warehouse relevant and in step with the organization. Many organizations set up BI Competency Centers to help govern and develop the enterprise data warehouse, but my suggestion would be to make those centers a place for brainstorming, exploring and deriving value on an ongoing basis.
In healthcare, as we strive to lower costs and adopt a lean process improvement methodology, our process of using high-quality data should help identify new revenue opportunities, serve our communities more effectively and encourage us to explore possibilities. That exploration should start with the data that we work hard to acquire, extract, transform and load in our enterprise view. As data comes in faster, we need to respond quickly by connecting the data with the right users.
To summarize, in moving beyond the build stage of an enterprise data warehouse and gaining the return on investment, there are four key steps:
- Identify the “new” stakeholders that will use the EDW in their daily jobs
- Help the new stakeholders explore and learn what data is available to streamline clinical, operational or financial processes, possibly in a BI Competency Center to master tools
- Promote the success stories to create action from all parts of the organization
- Realize the return on investment from your EDW – celebrate!
by July 23rd, 2014on
In my last blog post, I introduced the fundamentals and importance of healthcare benchmarking. I highlighted the benefits of benchmarking as well as the advantages and disadvantages of various types of benchmarking. The main point I hope you took away was that regardless of the type of benchmarking, the purpose is the same – to help healthcare organizations identify ways to improve their overall performance.
Now that you are aware of what healthcare benchmarking is and why it is important, in this blog post, we will focus on the key steps to implementing an effective benchmarking project to begin reaping those benefits.
Benchmarking Process and Key Steps
It is not secret that a well thought out process is essential to the success of any major project. Implementing a benchmarking project is no different. Below are the key areas of focus to consider before undertaking any benchmarking initiative. I have derived many of the specifics using a variety of resources, such as Six Sigma, the Juran Model, etc., to provide further context around each step. You might say, I have taken the “best of the best” from each resource…coincidence, I think not.
Plan and Prepare
Identify Opportunities and Prioritize1 – Top management must decide which processes are critical to the success of the organization and select projects from these. Once a shortlist of processes to be bench-marked is ready, the processes need to be prioritized as per a predetermined set of criteria to fulfill the requirements of all customers (stakeholders), especially the end customer1.
Deciding the Benchmarking Organization1 – The next step in the process is to decide the organization whose processes will serve as the benchmark. The benchmark can be a single entity or a collective group of companies, which operate at optimal efficiency2. Information on their processes should be gathered from various sources and the most suitable organization selected1. It is always important to ensure that more detailed information about the selected organization will be accessible and that comparison with the organization’s process will be relevant and useful1.
Organize a Benchmarking Team – The most successful benchmarking projects involve a team approach3. The organization should leverage existing teams that may be involved in similar topics to those that are being bench-marked, if possible. In the event a new team needs to be created for a benchmarking project, The Joint Commission, suggests that the organization seek the following when building the team3:
- Individuals closest to and most knowledgeable about the process or issues under investigation
- Individuals critical to implementation of any potential changes
- Individuals likely to be directly affected by any changes that result from a project
- A respected and credible leader who has a broad knowledge base
- An individual who has the authority to make decisions
- Individuals with diverse knowledge base and strong analytical skills
- Individuals familiar with benchmarking and how it can be used in performance improvement
- Individuals who are skeptical, resistant or even opposed to certain ideas and who can service as sounding boards or provide alternative viewpoints.
This step is perhaps the most important, most difficult and most time consuming activity in the process1. It involves creating a plan for collecting data from selected targets, conducting site visits and creating a site visit report4. Many times the information on processes and procedures followed at another company are confidential, and it is not always easy to gather authentic information, even after making a planned and approved visit at another organization1. The preparation for collecting necessary information and documenting this information in a systematic way has to be carefully planned and executed.
Validation and Normalization5 – The key activities here are the validation and normalization of data. Before any meaningful analysis can be performed, it’s essential that all data be validated to establish its accuracy and completeness. Some form of data normalization is usually required for direct comparisons to be made.
Identify Gaps5 – To be of value, the analysis must indicate the benchmarker’s strengths and weaknesses, determine (and, where possible, quantify) gaps between the benchmarker’s performance and the leaders’, and provide recommendations for the focus of performance improvement efforts. Based on this thorough analysis, an improved process(s) should be developed. Properly identifying the gaps will result in a clear picture of the organization’s processes in comparison with others within the business or industry.
Communicating Results – Communicating the benchmarking results and their implications to significant audiences in the organization and motivating them to carry out changes is vital4. It will result in a complete understanding by the target audiences of the necessity for changes in the processes involved and a desire to carry them out4. The communication must be delivered in a very clear, concise, and easily understood format via an appropriate medium5.
Create Goals – The project team’s next step is to set/revise goals for the improvement of the organization’s existing process, close the performance gap(s) identified in step 3 and create realistic and unambiguous new standards for the processes involved1&4. These goals can, and probably should, be stretch goals that will result in a process even better than the other organization’s best-in-class process1. Make sure management has approved and that all in the organization/business area understand.
Develop and Execute Action Plan1 – After the improved process and goals are accepted by all concerned or likely to be affected by it, a formal, detailed action plan is drawn with all key activities taken as inputs as well as the organization’s culture. The detailed action plan should carry the important things like a time line, individuals responsible for carrying out the tasks, any short-fall in the completion of tasks and what stretch targets are taken to compensate the short-falls. Those responsible should be committed enough to ensure that the tasks and assignments are completed on time.
Monitor Process – As with most projects, in order to reap the maximum benefits of the benchmarking process, a systematic evaluation should be carried out on a regular basis2. Senior management must be committed enough to ensure proper coordination of various activities, monitor the progress of implementation of the plan and work as a barrier-remover in the implementation process1. When the revised process is in place, a complete report has to be prepared, showing the benefits of the revised process compared with the expectations at the time of approval of the proposed revision of the process1.
Recalibrate as Necessary4– The organization needs to ensure it remains on the cutting edge by continuously evaluating the bench-marked practices and re-instituting the benchmarking process when necessary. This will prevent complacency by creating the habit of evaluating procedures to identify opportunities to improve.
Benchmarking is a very powerful performance improvement tool. However, it is vital to understand the basis behind it, follow a proven implementation methodology and gain organization-wide commitment to the cause. Benchmarking is critical for healthcare organizations to achieve and sustain the clinical effectiveness and operational performance they so desperately need.
Does your healthcare organization benchmark? Does the organization have a process that is followed similar to the aforementioned process? Has it proven successful?
Resources for this blog post:
by July 8th, 2014on
Starting in 2015 all issuers of Qualified Health Plans (QHPs) on the Healthcare Marketplace will need to provide Quality Rating System (QRS) measurements that will be aggregated and scored to provide consumers with a star rating for each product offered.
Although there are still details to be worked out by CMS, the required measures for the 2015 beta test are in place. All issuers that wish to continue providing QHPs on the Marketplace will need to provide the required measures. There are two different sets of measures included in the beta specifications.
The first is a set of clinical quality measurements that are mostly taken from the current NCQA HEDIS accreditation process. Many issuers already collect the data for these measures; especially, if they are meeting the requirement to be accredited for the Marketplace today and are using NCQA for that process.
The second is set of measures derived from an enrollee satisfaction survey (ESS) that needs to be performed by an accredited third party survey vendor. Most of the questions in the ESS are drawn from CAHPS. The survey processes requires that a sample of data is drawn, audited by a third party and provided to the survey vendor. The vendor then performs the survey and reports the results to CMS. Questions focus on rating an enrollee’s satisfaction with a plan over a six month period.
While the QRS initiative driven by the ACA attempts to provide transparency, it also creates a competitive market that will force issuers to look at ways to increase the quality of care and enrollee satisfaction to deliver better scores. The prize? For consumers, better products. For issuers, a larger share of the market.
Want to participate and win? Then you need a solution that not only provides the required measures, but also provides insight and the ability to drive quality improvements. This can be accomplished with a well thought out solution architecture that provides processes for delivering the measures and the means for analyzing data to drive improvements.
by April 21st, 2014on
This month, we completed an interview with our healthcare analytics strategist, Juliette Silver. We wanted to understand how enterprise information management strategies can specifically optimize business performance, reduce costs, mitigate risks and improve quality of care.
From the interview, I take away at least 10 major benefits to establishing and leveraging an enterprise information management strategy in healthcare settings:
- Help manage access to enterprise information in a secure, HIPAA-compliant manner.
- Allow healthcare professionals to turn mountains of data into real-time decisions.
- Help focus people, process, policies, frameworks and foundational technologies toward how to best leverage enterprise data.
- Set forth the framework that will be used to provide the information delivery capability,whether the information is in the form of data (structured or unstructured) or unstructured content, or a combination of both.
- Help an organization respond to evolving regulatory requirements and reimbursement models.
- Define the information management model that will be used to harmonize the delivery of both content and data specific to a healthcare organization’s goals and objectives.
- Ensure the delivery of information in the form of a trustworthy source that can be interpreted, used and managed consistently across the enterprise.
- Give a clinician or healthcare knowledge worker the access they need to the many sources or types of information from which to make decisions.
- Ensure information is timely, accurate, valid, verified and generally fit for purpose.
- Produce a more holistic view of the patient, derived from structured data stored in an electronic health record and other clinical systems, as well as unstructured information or content made available in some of the forms previously stated.
by February 26th, 2014on
HIE, clinical data, quality measures, financial and claims data along with healthcare analytics – what does it take to decrease readmission rates in nursing homes?
There is so much attention these days on making the most of all of the clinical and financial data regarding healthcare, hospital readmission costs and reimbursement, but do we really know what changes can or will make a difference?
It has been a long time since I have done bedside nursing, but I can remember how often I would have one or more patients assigned to me who had come from a skilled nursing facility, long-term care facility or “nursing home.”
The American Health Care Association (AHCA), the largest association representing skilled nursing care centers in the country, reports that every year, nearly 2 million Medicare beneficiaries are readmitted to the hospital within 30 days of being discharged, at a cost of $17.5 billion. Of readmissions, one fourth are skilled nursing care patients, receiving post-acute care (recuperative or rehabilitative services).
According to the recent Office of Inspector General (OIG), Medicare Nursing Home Resident Hospitalization Rates Merit Additional Monitoring report, in Fiscal Year 2011, one quarter (24.8%) of Medicare residents in nursing homes were transferred to hospitals for inpatient admissions, at a cost of $14.3 billion for the hospitalizations. The hospitalizations were required for a wide range of conditions with septicemia the most common. While the majority (67.8%) were transferred to hospitals only once, 20% transferred two times, 7.2% transferred three times, and the remaining 5% transferred four or more times. Of the Medicare costs for hospitalizations in FY2011, care for a nursing home resident cost an average of $11,255 per hospitalization, which is 33.2% higher than the average Medicare hospitalization ($8,447). Read the rest of this post »
by February 26th, 2014on
A few years ago, I transplanted my family from the south to Washington DC. I love the Capital, for its history, its influence, but we quickly realized we had left Mayberry and arrived on Jupiter. Horns honked and people moved around briskly. Maybe it was us – our naiveté — or maybe it was the community we had arrived in. But we quickly realized: “If you order french fries, you get french fries.” And only french fries. Months of dining out were spent, only to find that our presumed “condiments” were not standard with our order. We would have to ask for them and specify the quantity. French Fries and 2 ketchups, please.
Well I clicked my heels three times and eventually moved us back to our Mayberry. It’s been three years and my son and I will still giggle together when we order french fries and see someone going out of his or her way to offer ketchup. And when we say “Yes, Please”, we get several packets.
Consulting in Healthcare is no different. We’ve grown accustomed to the “build to spec” approach. You get exactly what you asked for.
I’m thankful to be a part of Perficient and the Oracle Healthcare Business Intelligence team. We share a common philosophy – understand what the customer wants to achieve, coach and advise available options, design and deliver a solution that fulfills their NOW problem and simultaneously prepared them for the next 5 years. It’s not just a report – it’s Healthcare Analytics. Read the rest of this post »
by February 25th, 2014on
Do you remember therbligs from your Operations Management class?
The word therblig was the creation of Frank Bunker Gilbreth and Lillian Moller Gilbreth, American industrial psychologists who invented the field of time and motion study. It is a reversal of the name Gilbreth, with ‘th’ transposed. Therbligs are 18 kinds of elemental motions used in the study of motion economy in the workplace. A workplace task is analyzed by recording each of the therblig units for a process, with the results used for optimization of manual labor by eliminating unneeded movements. (Wikipedia)
I remember, and it was a lifetime ago. But then again, the Gilbreth’s were turn-of-the-century industrial psychologists who invented the field of time and motion study. I consider them the founding parents of Industrial Engineering.
So why are we talking about therbligs in Healthcare?
Ah, young Jedi, the time has come to learn our lessons much the same way that the industrial giants like Ford, Carnegie Steel and General Electric learned 100 years ago during Teddy Roosevelt’s administration. These early lessons became the standards of the mid-century boom in manufacturing and production output.
So the healthcare technology space has finally gotten to its tipping point. In order to survive, the healthcare industry will need to invest in Industrial Engineering principles and it will need to do product line, service line, episodic, acute and outpatient time and motion studies.
by February 24th, 2014on
I’ve waited 20 years for my Treasure Map. Yes, a map with hidden passages, remote islands and an “X” to mark the spot. As kids, some of us hunted in our yards looking for buried treasures. Kids today use smart phone apps for activities like “Geocaching” to explore public and urban spaces. What do we use in Healthcare?
Many of us desire a chest full of clinical outcomes, protocol conformity, activity based costing, provider scorecard, genomic studies, Pharmacogenomic markers, Adverse Event analysis, and coordination of care analytics.
But lately, we have been lost – adrift at sea, hopping from one raft to another, and from one stranded island to the next more barren island. We’ve bought point solutions that offered the holy grail for a niche activity, all while knowing the vendor or the quick fix would evaporate before we had achieved broad-based adoption.
Oh, I’ve been there – tasked with implementing the pet project for a clinical director or department chair. I’ve no sooner got the data in and one cycle of analysis out, than the provider champion would change their focus and the solution implemented didn’t transfer to the next project. (Sigh.) Read the rest of this post »
by February 17th, 2014on
While my interest is always in the convergence of technology like the Internet of Things and healthcare IT, the role of sensors in managing health and wellness is just exploding.
“The most popular device functionality in the wearable tech market is heart rate monitoring, with nearly 12 million such devices shipped in 2013. Pedometers and activity trackers accounted for a combined 16 million shipments over the same period.” (According to a report released Thursday by ABI Research)
You can’t turn anywhere without reading about the latest running gadgets, fitness bands, Bluetooth blood pressure cuffs, etc. In the inevitable rush to wearable computing, one key idea can get lost: what are we doing with all of that data?
The data produced by these devices and sensors has to be interpreted and turned into information that is actionable. The fitness band that looks at your goal of 10,000 steps, sees that you are at 8,000 steps right after dinner and encourages you for one final walk around the neighborhood, will ultimately win out over all others. In order to pull off that trick, we need analytics and, sometimes, predictive analytics.
Just as the sensors are working in the background without us even taking notice, the role of analytics, especially healthcare analytics, should be to inform, encourage and drive healthcare consumers to improve our behaviors or decisions without being intrusive. The goal of healthcare analytics or informatics should be to create an environment for the healthcare consumer that makes life better, easier and more enjoyable.
An example is when the running app sees your pace slowing down towards the end of a run, then it kicks in a song with a faster pace to help you finish strong. Today those apps require you to recognize that situation and take action of pressing a button. It’s all there but it’s not automated. What we need is that invisible intelligence that recognizes the situation and then takes action to assist us.
At HIMSS 2014, we will be seeing this jump in interest in predictive analytics as it applies to healthcare, especially two distinct types of predictive analytics.
- One type is the traditional forecasting model of advanced analytics that trends past information to predict future states.
- The second type of predictive analytics is statistical models that encompass multiple feeds or variables to predict a future outcome. This modeling is rapidly moving past the arena of data scientists who create the models and is moving more within the grasp of smart business analysts. These models can predict your longevity based on multiple factors like your BMI, blood sugar readings for diabetics and other factors from your medical history.
Of course, we want to be able to predict health outcomes, especially when faced with several choices for changing our behaviors or lifestyle. It will be exciting to see how healthcare application vendors are addressing this important next step in analytics.
The use of predictive analytics could really change the nature of a patient engagement with your doctor. How will we react when we see the outcome of our current lifestyle? Will we shut off Netflix bingeing and head to the gym? See you at HIMSS 2014 to find out! Stop by Perficient’s booth #2035 and tell us what you found out!