This post is just a brief introduction of forms of analytics that exists and how they can be used by healthcare organizations. The mostly used form of analytics are:
1. Descriptive Analytics: This is the most common of all forms. In business, it provides the analyst with a view of key metrics and measures within the company. This field of analytics is invoked to know about the answers to questions for projects that have already happened, such as “What is the status of X Project?”
An example of this could be a monthly profit and loss statement. Similarly, an analyst could have data on a large population of customers. Understanding demographic information on their customers (e.g. 30% of our customers are self-employed) would be categorized as “descriptive analytics”. Utilizing useful visualization tools enhances the message of descriptive analytics.
Suppose a client is interested to know whether a healthcare institution was using racial discrimination practices in its operations. For such detection descriptive analytics can be used. We'll be given data on the patient records and their backgrounds. Patient data will be given with their racial orientation, such as Asian, Native American, etc., along with data on admissions to the ICU, operations, and admissions to hospital wards and private rooms.
We have to analyze and give conclusive evidence using statistical techniques as to whether there was any racial bias. By using descriptive analytics and looking at the patient records,we'll able to say with confidence that there was or was not much evidence of such acts in the data. These findings can later be used for evidence in legal proceedings as well.
Thus we have to be careful to analyze data from all angles to confirm that there was or wasn't such
pattern present in the data set.
2. Diagnostic Analytics: This field of analytics is used to know the root cause of a phenomenon, such as a project’s success or failure. Why did the X Project fail? What are the positive lessons we can learn from this project’s success? All such questions can be answered using diagnostic analytics.
Thus this is the next step in complexity in data analytics. On the assessment of the descriptive data, diagnostic analytical tools will empower an analyst to drill down and in so doing isolate the root-cause of a problem.
Well-designed business information (BI) dashboards incorporating reading of time-series data (i.e. data over multiple successive points in time) and featuring filters and drill down capability allow for such analysis.
Diagnostic analytics is used in the life of every healthcare professional. The industry is very diagnostic-driven, as it tries to diagnose the disease based on symptoms. So building systems that diagnose issues and problems is not very difficult. Genomics is a field where much diagnostic research is taking place at IBM Watson project for Genomics is at the forefront in such research. IBM Watson is an analytics engine built by IBM for use in machine learning and artificial intelligence. The machine learning engine IBM Watson is helping find solutions for individual treatment of cancer
patients using its huge data sets comprised of medical literature, clinical study results, pharmacopeia, etc., to find cures for cancer patients. This is public research available to oncologists worldwide and is helping unearth possible new cures for various forms of cancer.
3. Predictive Analytics: Predictive analytics is all about forecasting. Whether it’s the likelihood of an event happening in future, forecasting a quantifiable amount or estimating a point in time at which something might happen - these are all done through predictive models.
Predictive models typically utilise a variety of variable data to make the prediction. The variability of the component data will have a relationship with what it is likely to predict (e.g. the older a person, the more susceptible they are to a heart-attack – we would say that age has a linear correlation with heart-attack risk). These data are then compiled together into a score or prediction.
In a world of significant uncertainty, being able to predict allows one to make better decisions. Predictive models are some of the most important utilised across many fields. This type of analytics is used for determining the outcome of an event in the future, such as project success or failure, project budget overrun, or a schedule slippage for an ongoing project.
Predictive analytics is the next level of implementation of machine learning in the healthcare industry. In such an implementation, for example, the focus would be on predicting the likely group of people who could develop cancer. A system so developed would be able to predict accurately the age and type of people who are likely to develop a particular type of cancer. It would have the ability to create a profile of cancer patients, and as such a person comes in contact with this type of analytical system, it would throw up an alarm on the likely case of developing cancer.
4. Prescriptive Analytics: In this field of analytics the maximum value of analytics is achieved as it builds upon the prediction made based on predictive analytics, and it prescribes actions that should be taken for the future. The prescriptive model utilizes an understanding of what has happened, why it has happened and a variety of “what-might-happen” analysis to help the user determine the best course of action to take. A prescriptive analysis is typically not just with one individual response but is, in fact, a host of other actions.
An excellent example of this is a traffic application helping you choose the best route home and taking into account the distance of each route, the speed at which one can travel on each road and, crucially, the current traffic constraints. Another example might be producing an exam time-table such that no students have clashing schedules.
Prescriptive analytics is being used by an IBM Watson for Genomics project, where it not just diagnoses the disease but also gives a prediction and then a likely prescription for the type of cancer by looking at clinical drug trials and their results. Although this system is undergoing rigorous testing, it will yield significant results when it is able to increase its predictive and prescriptive accuracy.
We thus conclude that while different forms of analytics may provide varying amounts of value to a business, they all have their place.In the next post we shall look how machine learning is transforming healthcare. Till we meet again keep exploring and learning Python as Python is easy to learn!
1. Descriptive Analytics: This is the most common of all forms. In business, it provides the analyst with a view of key metrics and measures within the company. This field of analytics is invoked to know about the answers to questions for projects that have already happened, such as “What is the status of X Project?”
An example of this could be a monthly profit and loss statement. Similarly, an analyst could have data on a large population of customers. Understanding demographic information on their customers (e.g. 30% of our customers are self-employed) would be categorized as “descriptive analytics”. Utilizing useful visualization tools enhances the message of descriptive analytics.
Suppose a client is interested to know whether a healthcare institution was using racial discrimination practices in its operations. For such detection descriptive analytics can be used. We'll be given data on the patient records and their backgrounds. Patient data will be given with their racial orientation, such as Asian, Native American, etc., along with data on admissions to the ICU, operations, and admissions to hospital wards and private rooms.
We have to analyze and give conclusive evidence using statistical techniques as to whether there was any racial bias. By using descriptive analytics and looking at the patient records,we'll able to say with confidence that there was or was not much evidence of such acts in the data. These findings can later be used for evidence in legal proceedings as well.
Thus we have to be careful to analyze data from all angles to confirm that there was or wasn't such
pattern present in the data set.
2. Diagnostic Analytics: This field of analytics is used to know the root cause of a phenomenon, such as a project’s success or failure. Why did the X Project fail? What are the positive lessons we can learn from this project’s success? All such questions can be answered using diagnostic analytics.
Thus this is the next step in complexity in data analytics. On the assessment of the descriptive data, diagnostic analytical tools will empower an analyst to drill down and in so doing isolate the root-cause of a problem.
Well-designed business information (BI) dashboards incorporating reading of time-series data (i.e. data over multiple successive points in time) and featuring filters and drill down capability allow for such analysis.
Diagnostic analytics is used in the life of every healthcare professional. The industry is very diagnostic-driven, as it tries to diagnose the disease based on symptoms. So building systems that diagnose issues and problems is not very difficult. Genomics is a field where much diagnostic research is taking place at IBM Watson project for Genomics is at the forefront in such research. IBM Watson is an analytics engine built by IBM for use in machine learning and artificial intelligence. The machine learning engine IBM Watson is helping find solutions for individual treatment of cancer
patients using its huge data sets comprised of medical literature, clinical study results, pharmacopeia, etc., to find cures for cancer patients. This is public research available to oncologists worldwide and is helping unearth possible new cures for various forms of cancer.
3. Predictive Analytics: Predictive analytics is all about forecasting. Whether it’s the likelihood of an event happening in future, forecasting a quantifiable amount or estimating a point in time at which something might happen - these are all done through predictive models.
Predictive models typically utilise a variety of variable data to make the prediction. The variability of the component data will have a relationship with what it is likely to predict (e.g. the older a person, the more susceptible they are to a heart-attack – we would say that age has a linear correlation with heart-attack risk). These data are then compiled together into a score or prediction.
In a world of significant uncertainty, being able to predict allows one to make better decisions. Predictive models are some of the most important utilised across many fields. This type of analytics is used for determining the outcome of an event in the future, such as project success or failure, project budget overrun, or a schedule slippage for an ongoing project.
Predictive analytics is the next level of implementation of machine learning in the healthcare industry. In such an implementation, for example, the focus would be on predicting the likely group of people who could develop cancer. A system so developed would be able to predict accurately the age and type of people who are likely to develop a particular type of cancer. It would have the ability to create a profile of cancer patients, and as such a person comes in contact with this type of analytical system, it would throw up an alarm on the likely case of developing cancer.
4. Prescriptive Analytics: In this field of analytics the maximum value of analytics is achieved as it builds upon the prediction made based on predictive analytics, and it prescribes actions that should be taken for the future. The prescriptive model utilizes an understanding of what has happened, why it has happened and a variety of “what-might-happen” analysis to help the user determine the best course of action to take. A prescriptive analysis is typically not just with one individual response but is, in fact, a host of other actions.
An excellent example of this is a traffic application helping you choose the best route home and taking into account the distance of each route, the speed at which one can travel on each road and, crucially, the current traffic constraints. Another example might be producing an exam time-table such that no students have clashing schedules.
Prescriptive analytics is being used by an IBM Watson for Genomics project, where it not just diagnoses the disease but also gives a prediction and then a likely prescription for the type of cancer by looking at clinical drug trials and their results. Although this system is undergoing rigorous testing, it will yield significant results when it is able to increase its predictive and prescriptive accuracy.
We thus conclude that while different forms of analytics may provide varying amounts of value to a business, they all have their place.In the next post we shall look how machine learning is transforming healthcare. Till we meet again keep exploring and learning Python as Python is easy to learn!
0 comments:
Post a Comment