How a Digital Workforce Will Save Healthcare

How a Digital Workforce Will Save Healthcare

Enterprises have been digitizing data and processes furiously over the past few decades, and these efforts have unlocked a pantheon of capabilities to offer new products and better experiences, and healthcare is no exception. Partially driven by government mandates and subsidies, healthcare systematically bought large electronic medical record systems (EMRs and EHRs) and other systems to bring them into the digital era. Unfortunately, this tidal wave of adoption, although extraordinarily valuable, had negative side effects as well: 


The digitization of healthcare created silos. Database fortresses were built at every organization. They weren’t built to share. They weren’t built to interoperate – not between software systems and certainly not between organizations. No connection to insurers. No connection to other providers and until recently, almost no connection to patients. 

Instead, healthcare employees have taken on the job of the data router, shifting hours spent from being in front of patients, to being in front of computers, shepherding patient data into the right fields. This administrative burden is driving skyrocketing costs, rising attrition and a backlog of work in an industry already suffering from razor thin margins. Healthcare can’t continue to operate like this – there must be a solution to rescue nearly a trillion dollars of administrative costs and reallocate these precious resources to the delivery of care, the creation of new drugs and therapies, and the research to eradicate diseases.


The answer is an AI-powered digital workforce.

Today, most healthcare executives are familiar with robotic process automation, or RPA – it’s used to automate common workflows or business practices like patient scheduling, supply chain management, claims management, and more. That’s because many of the time-consuming, manual processes that make up healthcare administration are simple, rule-based and high volume – the perfect candidate processes for automation. But for many organizations looking to deploy artificial intelligence, RPA alone will not allow them to realize the full benefits of AI – a digital workforce is required.


A digital workforce goes beyond traditional RPA in 3 very important ways:
  1. A digital workforce has deep learning
  2. Gets smarter over time & adjusts work 
  3. Interacts with human management

Not all automations a digital employee does can be performed by a human – in many cases, a digital employee uses deep learning techniques to accomplish far more complex tasks

Although a digital employee depends on RPA as a building block of their capabilities, they leverage other advanced technologies to handle more complex tasks that RPA can’t accomplish alone. For instance, while RPA can quickly and accurately process large volumes of data, Olive, the first AI-powered digital employee built for healthcare, leverages some degree of artificial cognition on top of an automation, allowing her to make decisions or take action with cognitive “thinking” involved.

The processes involved in deep learning are similar to that of data mining and predictive modeling – this is how a digital employee gets smarter over time. Leveraging deep learning techniques provides better and faster information that improves efficiency, capacity, and reduces costs by providing insights into bottlenecks – and the reason behind these bottlenecks – identifying systemic, recurring issues and making adjustments or recommendations to solve them. 

A digital workforce can learn, adapt to change their work based on new intelligence.

Most of the value of a digital worker is created after a bot is deployed – that’s because, much like a human employee, if a bot is doing the same thing on day 100 of employment as it was on day 1, a huge opportunity is lost. Through predictive analytics, deep learning, and a continual stream of insights, a digital employee gets smarter over time, providing lasting value.

Olive turns insights into actionable intelligence, identifying potential problems from a mile away, so organizations are learning about solutions before they even learn about the problem. By consuming large amounts of historical data already in your system, Olive finds trends and data anomalies in your workflows and learns to respond the same way a human would – only smarter, faster, and more accurately – making continual improvements to provide better, more meaningful data and insight as she learns. And by pairing a digital employee with key hospital administrators, they can streamline and improve the management of data-heavy tasks like insurance eligibility checks or patient scheduling, using data to uncover and resolve recurring issues.


A digital employee interacts with managers to provide business intelligence and recommendations on improved ways to handle tasks, so they continue to generate value after deployment.
 

Olive works with human managers to determine the best way to communicate actionable insights, and that intelligence gives organizations a ‘Decision Advantage’ over where and how they apply their resources towards current workflow improvements or new candidate processes for automation. 

For instance, at one health system, Olive was hired to automate claim status checks. But unlike a traditional RPA bot, as soon as Olive was live she started collecting data that became actionable insights – like dollar amounts associated with denials – to communicate back to her manager for process improvement opportunities. Based on these learnings, her manager recommended that she focus on a specific subset of denials, which lead to another key discovery: millions of dollars of denials stemmed from a specific drug denial due to missing prior authorizations and medical necessity. This insight allowed the hospital to target a specific department in their organization where this recurring issue could be resolved. This “always on” analysis of information allows a digital employee to proactively offer new solutions for workflow improvements as she gets smarter over time.

A digital employee has Global Awareness and can connect disparate sets of information

Lastly, “global awareness” is another important concept that’s core to a digital employee – the understanding or awareness of information across multiple networks, systems, databases, or contexts. Interoperability is a consistent and growing challenge facing healthcare and the ability for our digital employees to transcend those silos opens up great opportunity. One example is quickly identifying a portal outage and alerting managers before a failure, as well as other organizations where Olives are employed. In the future, it could mean knowing a particular patient’s identity across multiple doctors’ offices or hospitals – even across different systems globally. This identification and matching of people is monumentally important to building the interoperability our industry so desperately needs.


That’s why we built Olive: to work side-by-side with healthcare employees with access to a limitless amount of data. 

As AI becomes more advanced – using applications humans have already developed to organize and interpret larger datasets than a human ever could – the opportunity to build and scale a digital workforce is greater than ever before. And at Olive, we think healthcare employees should handle the functions that are uniquely suited to humans, not the job of data entry clerk or data router. Olive can perform these tasks much more accurately and efficiently, working to resolve recurring issues over time and allowing human employees to focus on higher-value initiatives.

 

Working alongside healthcare employees, Olive is trained to think and make complex decisions that are driven by data. She never misses a day of work. She never makes unprogrammed mistakes. And every Olive learns collectively, like a network, so that healthcare organizations never have to solve the same problem twice. 

We’re making healthcare more efficient, more affordable, and more human with a growing digital workforce, so humans finally have the time, energy, and bandwidth to focus on what matters most: the patient experience. Just think of all the time digital employees will give back to our human employees – clinicians, providers, administrators, payers, and more. And with every organization that employs a digital employee, our ability to carve millions of dollars out of the cost of healthcare will become closer to reality.

If you want to learn more about Olive, contact us to schedule a demo.

 

The Importance Of Healthcare Data Security

The Importance Of Healthcare Data Security

Cyberattacks, data breaches, and hacking are key concerns for healthcare executives and a growing problem in the industry. A recent report showed that data breaches were up in 2018, with 503 incidents impacting almost 15.1 million patient records, compared to 477 breaches impacting 5.6 million records in 2017.¹  As hackers get more sophisticated, hospitals need to be increasingly vigilant about their healthcare IT and cybersecurity practices.

Healthcare data security is about more than just regulatory compliance: it needs to be central to a hospital’s ‘patient first’ focus, as it’s critical in maintaining consumer trust and organizational health. 

As anyone who has ever had their financial data stolen can attest, it can be a frustrating, costly, and time-consuming issue to correct. Credit card numbers must be changed, false charges corrected, and checks blocked. But unlike financial data, medical data cannot be corrected. Medical data is personal and can’t be changed or “wiped clean” – once the information is breached, the damage is done. Identity theft, insurance fraud, and extortion are all possibilities after a healthcare data breach, especially when you consider the medical information of CEOs, public figures, and other individuals are key targets for hackers on the black market. 

For hospitals or other healthcare systems, a breach can be financially devastating long-term, too. The service interruptions and potential HIPAA fines sting upfront, but lack of consumer confidence driving patients elsewhere could mean lost revenue for years to come. Overcoming a serious data breach requires extensive image and trust rebuilding in a community, usually in the form of a massive and expensive PR campaign. For these reasons, most hospitals already understand the significant risks involved when handling patient health information – a recent HIMSS survey showed that cybersecurity, privacy, and security are top concerns in healthcare.²

Unfortunately, concern about data security doesn’t always lead to action. 

Despite data security growing in importance, a 2017 Black Book Market Research survey showed that only 15% of organizations reported having a chief information security officer.³  Given the enormous amount of private information hospitals have access to, high employee turnover rates, and the lack of IT leadership, this only adds to the unique challenges healthcare organizations face when implementing cybersecurity measures – many driven by the large number of systems and software vendors that every hospital uses to coordinate care and manage their business. 

The sheer number of disparate IT systems used in healthcare is perhaps unrivaled in any other industry. Every system, every vendor, every connection, and every employee with access and responsibility for transferring sensitive data is a cybersecurity risk. That’s because EMRs and other healthcare interfaces weren’t built to share data – they were built as fortresses to protect the data of patients and to make sure that data was available only within the walls of that system. 

“The ‘walled fortress’ approach to security no longer works,” says Olive Chief Product Officer David Landreman. “Keeping all data within your physical facility is not the end-all of protecting your data, it doesn’t account for human negligence, and it doesn’t make up for a comprehensive approach to security.”

Instead, data must be exchanged seamlessly and securely in order for healthcare organizations to provide better care to people globally, and this can only be achieved through technology.

Technology vendors should be an area of scrutiny for healthcare organizations looking to mitigate risk. 

Implementing data protection strategies and vetting technology vendors thoroughly will enable healthcare organizations to meet regulations and share critical patient data more securely. To limit risk and improve overall IT security strategy, hospitals should perform a security assessment of the vendors they currently use to understand their risk. Every new vendor selection process should weigh security concerns heavily in the evaluation criteria – begin this security evaluation early to ensure your solutions are built with the complexities of your organization in mind.

What happens when a hospital conducts a security assessment and finds that a vendor isn’t measuring up? Hospitals have two real options: put pressure on the company to improve security or switch vendors. As anyone who has switched vendors or implemented new software knows, neither are an easy task. Possible contract cancellation fees, time spent evaluating new solutions, resources spent on re-training employees on new software – it all adds up. 

And what’s the incentive for current vendors to improve security practices if only 10% of their customer base, for instance, needs those security updates – does the cost of potentially losing customers outweigh the cost of upgrading cybersecurity? As mentioned before, switching vendors can be cost-prohibitive, leading many hospitals to stay with current vendors with only vague promises or extended timelines for upgraded security.

Working exclusively with healthcare-specific vendors reduces risk.

When new regulations come out, new medical devices emerge, and new threats develop in healthcare, hospitals need partners that understand their industry-specific needs. Healthcare-only vendors understand the unique challenges facing the industry and will be better positioned to address organizations’ changing needs – especially those around cybersecurity.

 

That’s why at Olive, we’re healthcare first, and healthcare only. 

Unlike other AI solutions on the market, Olive uses her healthcare-specific skills to address common bottlenecks when it comes to automating workflows – most importantly, she does it with unrivaled security measures built for healthcare, working seamlessly within common industry processes and your current IT infrastructure. Instead of adding to your tech stack, Olive helps you run the tools you already have in place more efficiently, handling sensitive data without compromising security, helping to mitigate hospitals’ risk. 

Olive was built from the ground up with the complexities of healthcare data in mind, working seamlessly with the security controls and practices healthcare organizations already have without compromising sensitive health information. We believe industry regulations like HIPAA privacy rules, SOC2 compliance and other bot-related compliance issues should be the least of your team’s worries – we want them focused on more human-like initiatives, like patient care.

Olive automates a variety of healthcare workflows with speed and ease because she was designed to interact with EMRs, insurance portals, and other healthcare applications the same way a human would – only faster, smarter, and more securely. And Olive’s capabilities around industry languages and standards were built specifically for healthcare – that means she’s experienced with HL7 standards (including FHIR), EDI X12 messaging, and more.

Are your current vendors providing the security your organization needs? Contact us today to learn more about how Olive can help your organization limit risk and improve your overall data security.

Sources:

1.https://www.healthcaredive.com/news/data-breaches-compromised-151m-patient-records-last-year/548307/

2.https://www.himss.org/2019-himss-leadership-and-workforce-survey-0

3.https://blackbookmarketresearch.newswire.com/news/84-of-healthcare-organizations-dont-have-a-cybersecurity-leader-as-the-20110145

 

Machine Learning Basics Part 3: Basic model training using Linear Regression and Gradient Descent

Machine Learning Basics Part 3: Basic model training using Linear Regression and Gradient Descent

If you missed part one in the series, you can start here (Machine Learning Basics Part 1: An Overview).

Linear Regression is a straightforward way to find the linear relationship between one or more variables and a predicted target using a supervised learning algorithm. In simple linear regression, the model predicts the relationship between two variables. In multiple linear regression, additional variables that influence the relationship can be included. Output for both types of linear regression is a value within a continuous range.

Simple Linear Regression: Linear Regression works by finding the best fit line to a set of data points.

For example, a plot of the linear relationship between study time and test scores allows the prediction of a test score given the amount of hours studied.


To calculate this linear relationship, use the following:


In this example, ŷ is the predicted value, x is a given data point, θ1 is the feature weight, and θ0 is the intercept point, also known as the bias term. The best fit line is determined by using gradient descent to minimize the cost function. This is a complex way of saying the best line is one that makes predictions closest to actual values. In linear regression, the cost function is calculated using mean squared error (MSE): #331b9

Mean Squared Error for Linear Regression1

In the equation above, the letter m represents the number of data points, ????T is the transpose of the model parameters theta, x is the feature value, and y is the prediction. Essentially, the line is evaluated by the distance between the predicted values and the actual values. Any difference between predicted value and actual value is an error. Minimizing mean squared error increases the accuracy of the model by selecting the line where the predictions and actual values are closest together.

Gradient descent is the method of iteratively adjusting the parameter theta (????) to find the lowest possible MSE. A random parameter is used initially and each iteration of the algorithm takes a small step—the size of which is determined by the learning rate—to gradually change the value of the parameter until the MSE has reached the minimum value. Once this minimum is reached, the algorithm is said to have converged.

 

Be aware that choosing a learning rate that is smaller than ideal will result in an algorithm that converges extremely slowly because the steps it takes with each iteration are too small. Choosing a learning rate that is too large can result in a model that never converges because step size is too large and it can overshoot the minimum.

Learning Rate set too small1

Learning Rate set too large1

 

Multiple Linear Regression: Multiple linear regression, or multivariate linear regression, works similarly to simple linear regression but adds additional features. If we revisit the previous example of hours studied to predict test scores, a multiple linear regression example could be using hours studied and hours of sleep the night before exam to predict test scores. This model allows us to use unrelated features on a single data point to make a prediction about that data point. This can be represented visually as finding the plane that best fits the data. In the example below, we can see the relationship between horsepower, weight, and miles per gallon.

Multiple Linear Regression3

Thanks for reading our machine learning series, and keep and eye out for our next blog!

 

Reference:

  1. Geron, Aurelien (2017). Hands-On Machine Learning with Scikit-Learn & TensorFlow. Sebastopol, CA: O’Reilly.
  2. https://www.mathworks.com/help/stats/regress.html
  3. https://xkcd.com/1725/
Machine Learning Basics Part 2: Regression and Classification

Machine Learning Basics Part 2: Regression and Classification

If you missed part one in the series, you can start here (Machine Learning Basics Part 1: An Overview).

Regression:

Common real-world problems that are addressed with regression models are predicting housing values, financial forecasting, and predicting travel commute times. Regression models can have a single input feature, referred to as univariate, or multiple input features, referred to as multivariate. When evaluating a regression model, performance is determined by calculating the Mean squared error (MSE) cost function. MSE is the average of the squared errors of each data point from the hypothesis, or simply how far each prediction was from the desired outcome. A model that has a high MSE cost function fits the training data poorly and should be revised.

A visual representation of MSE:

In the image above,1 the actual data point values are represented by red dots. The hypothesis, which is used to make any predictions on future data, is represented by the blue line. The difference between the two is indicated by the green lines. These green lines are used to compute MSE and evaluate the strength of the model’s predictions.

Regression Problem Examples:

  • Given BMI, current weight, activity level, gender, and calorie intake, predict future weight.
  • Given calorie intake, fitness level, and family history, predict percent probability of heart disease.

#331b9

Commonly Used Regression Models:

Linear Regression: This is a model that represents the relationship between one or more input variables and a linear scalar response. Scalar refers to a single real number.

Ridge Regression: This is a linear regression model that incorporates a regularization term to prevent overfitting. If the regularization term (????) is set to 0, ridge regression acts as simple linear regression. Note that data must be scaled before performing ridge regression.

Lasso Regression: Lasso is an abbreviation for least absolute shrinkage and selection operator regression. Similar to ridge regression, lasso regression includes a regularization term. One benefit to using lasso regression is that it tends to set the weights of the least important features to zero, effectively performing feature selection.2 You can implement lasso regression in Sci-kit Learn using the built-in model library.

Elastic Net: This model uses a regularization term that is a mix of both ridge and lasso regularization terms. By setting r=0 the model behaves as a ridge regression, and setting r=1 makes it behave like a lasso regression. This additional flexibility in customizing regularization can provide the benefits of both models.2 Implement elastic net in Sci-kit Learn using the built in model library. Select an alpha value to control regularization and an l1_ratio to set the mix ratio r.

ClassificationClassification problems predict a class. They can also return a probability value, which is then used to determine the class most likely to be correct. For classification problems, model performance is determined by calculating accuracy.

model accuracy =  correct predictions / total predictions * 100

Classification Problem Examples: Classification has its benefits for predictions in the healthcare industry.For example, given a dataset with features including glucose levels, pregnancies, blood pressure, skin thickness, insulin, and BMI, predictions can be made on the likelihood of the onset of diabetes. Because this prediction should be a 0 or 1, it is considered a binary classification problem.

Commonly Used Classification Models:

Logistic Regression: This is a model that uses a regression algorithm, but is most often used for classification problems since its output can be used to determine the probability of belonging to a certain class.2 Logistic regression uses the sigmoid function to output a value between 0 and 1. If the probability is >= 0.5 that an instance is in the positive class (represented by a 1), the model predicts 1. Otherwise, it predicts 0.

Softmax Regression: This is a logistic regression model that can support multiple classes. Softmax predicts the class with the highest estimated probability. It can only be used when classes are mutually exclusive.2

Naive Bayes: This is a classification system that assumes that the value of a feature is independent from the value of any other feature and ignores any possible correlations between features in making predictions. The model then predicts the class with the highest probability.4

Support Vector Machines (SVM): This is a classification system that identifies a decision border, or hyperplane, as wide as possible between class types and predicts class based on the side of the border that any point falls on. This system does not use probability to assign a class label. SVM models can be fine-tuned by adjusting kernel, regularization, gamma, and margin. We will explore these hyperparameters further in an upcoming blog post focused solely on SVM. Note that SVM can also be used to perform regression tasks.

Decision Trees and Random Forests: A decision tree is a model that separates data into branches by asking a binary question at each fork. For example, in a fruit classification problem one tree fork could ask if a fruit is red. Each fruit instance would either go to one branch for yes or the other for no. At the end of each branch is a leaf with all of the training instances that followed the same decision path. The common problem of overfitting can often be avoided by combining multiple trees into a random forest and taking the prediction from the tree with the highest probability of accuracy.

Neural Networks (NN): This is a model composed of layers of connected nodes. The model takes information in via an input layer and passes it through one or more hidden layers composed of nodes. These nodes are activated by their input, make some determination, and generate output for the next layer of nodes. Connections between nodes have edges, which have a weight that can be adjusted to influence learning. A bias term can also be added to the edges to create a threshold theta (????), which is customizable and determines if the node’s output will continue to the next layer of nodes. The final layer is the output layer, which generates class probabilities and makes a final prediction. When a NN has two or more hidden layers, it’s called a deep neural network. There are multiple types of neural networks and we will explore this in more detail in later blog posts.

K-nearest Neighbor: This model evaluates a new data point by its proximity to training data points and assigns a class based on the majority class of its closest neighbors as determined by  feature similarity. K is an integer set when the model is built and determines how far out the model should look for neighbors. The boundary circle is set when it includes k neighbors.

Reference:

  1. https://en.wikipedia.org/wiki/Linear_regression
  2. Geron, Aurelien (2017). Hands-On Machine Learning with Scikit-Learn & TensorFlow. Sebastopol, CA: O’Reilly.
  3. https://en.wikipedia.org/wiki/Sigmoid_function
  4. https://en.wikipedia.org/wiki/Naive_Bayes_classifier