Category Archives: Healthcare IT

Virtual Health Services

Sustaining Virtual Health Services triggered by COVID:

Introduction:

Covid-19 was a challenge like no other. With a world connected like never before and intertwined economies the virus spread like wildfire across the globe. However, as they say, every new challenge is an opportunity to create a better and more secure tomorrow. Devastating as it was, the aftermath of Covid-19 toes the line. The pandemic saw academics, scientific community, medical professionals and data scientists come together to assess unique methods that are rapid and secure to tackle the crisis with virtual health services. Data sharing, a key component in creating solutions was incentivised along with model training and testing without the hurdles of conventional collaborations. Healthcare providers and researchers focused on addressing the challenges of meeting the critical clinical needs created by the crisis, with remarkable results.

As per the article Federated learning for predicting clinical outcomes in patients with COVID-19 published in Nature Medicine “The pandemic has emphasized the need to expeditiously conduct data collaborations that empower the clinical and scientific communities when responding to rapidly evolving and widespread global challenges.”

Since the Covid-19 outbreak, Investment in digital health has skyrocketed, Venture Capitalists are queueing up to invest in the digital healthcare more than ever before. Thus providing the impetus for further innovation. Artificial Intelligence(AI) is another sector which proves to be a strong pillar of support for the Data Scientists, Academicians, Healthcare Professionals and Regulatory Authorities.

Regulatory Changes:

There was a slew of regulatory changes brought in by the US Government to tackle the pandemic and ensure faster care to the patients. The regulations aim to improve the safety of the healthcare professionals. We look at some of the blanket waivers brought in during the Pandemic:

Emergency Medical Treatment & Labor Act (EMTALA): By waiving off the section 1867(a) of the act, it facilitates hospitals to screen patients offsite. This helps to prevent the spread of Covid-19.

Telemedicine: By waiving of certain sections related to 42 CFR, virtual health services became accessible to patients through an agreement with offsite hospital.

Quality Assurance and Performance Improvement (QAPI): This enabled the healthcare facilities to develop, implement, maintain and evaluate an effective and exhaustive data-driven QAPI. Thereby the hospital can solely focus on treating patients during COVID-19.

Electronic Case Reporting (eCR): The automated generation and dissemination of case reports from the electronic health record (EHR) to public healthcare agencies makes disease reporting faster and easier. It moves data securely and seamlessly—from the EHR at the point of care, to data systems at state, territorial, and local agencies. This also allows public health to provide information back to healthcare professionals. The timely data sharing provides a real time picture of COVID-19 to support outbreak management.

To cover the entire set of regulatory changes and waivers is beyond the scope of this article. For more details do go through the link.

Trends during the Pandemic:

The pandemic brought forth the need for an alternative method of healthcare and allied health services. While this blog is being written, digital technologies are being harnessed to help prepare for future challenges.

Dissemination of information from credible sources – IT platforms were widely used by regulatory authorities to deal with the misinformation and educate the masses about Covid-19. WHO rolled out the ‘Stop the Spread’ campaign across platforms. They also rolled out another campaign within the campaign Playbook to tackle the wastage of resources. The aim is to document and share innovative and good vaccination practices  to educate the countries and communities at large.

One sector which emerged as the sunshine sector during the Pandemic is the Telehealth. With regulatory changes which facilitated the accessibility becoming permanent like for eg; the reimbursable telehealth codes for the 2021 fees schedule for physicians, the sector is witnessing an expansion in terms of services that it can offer.

According to a report by McKinsey, Tele Health services has increased 38 times since pre Covid days. The report mentions that consumers continue to view telehealth as an important modality for their future care needs. But the view varies widely depending on the type of care.

In 2020, Mckinsey had estimated that the virtual enabled healthcare industry would become a $250 billion industry. Going by the recent trends the prediction is well and truly on course.

During the Pandemic the usage of Telehealth services surged as patients sought the safe access to seek virtual health services. Likewise for healthcare professionals it provided the luxury of discharging their duties without being on the frontline.

The Future Scenario:

During the outbreak of Ebola in 2015, workshops were organised by White House Office of Science & Technology Policy and the National Science Foundation broadly defined three areas where Robotics can make a significant difference. As a result, it set a precedence for handling Covid-19 pandemic.

• Clinical Care – Telemedicine & Decontamination

• Logistics – Delivery & handling of contaminated waste

• Reconnaissance – Monitoring Compliance

Covid-19 introduced a fourth area – contactless consultancy services. This opens up the future for Tele Health services with the possibility of remotely controlled robotic systems deployed to the frontline.

With 5G bandwidth and smart phones entering the public domain, the day won’t be far when Medical Conferences and seminars will be held virtually. As a result, this opens the door for virtual reality in the field of Medicine. Not only will such an initiative reduce infection rates, it will help in reducing carbon footprint as well.

During the pandemic, there has been an increase interest in decentralized and digitally connected rapid diagnostic tests to widen access to testing. As a result, this increase capacity and eases the strain on healthcare systems and diagnostic laboratories.

There is an urgent need for creating applications to predict future eventualities, availability of essential medical services and optimising medical resources. IT and IT based solutions is a force multiplier for the healthcare sector. The applications are efficient, fast and accurate. The other important aspect is that IT based solutions are cost effective. This makes healthcare accessible with virtual health services and reduces the burden on the Government and Hospitals. It is the future of medical services to meet the global demand of equitable healthcare.

Technology trends shaping the post Covid world:

Over a period of time, Artificial intelligence (AI) has evolved by leaps and bounds in detection, diagnosis, and treatment of diseases. In India, City Scan has helped in proof reading for Radiologist’s and reduced the time lapse for diagnosis. Similarly, eye testing etc. are widely using AI for faster diagnosis and treatment. Artificial Intelligence applications with proper implementation can address the global health care inequalities that exists today.

During Covid-19, Artificial Intelligence based technical models provided the following:

• Helped in reducing the response time to patients.

• Giving predictive models of mortality.

• Inventory management.

• Predictive model for scanning the wave of Covid-19.

• Predicting the end and resurgence of the wave.

Deep learning, a facet of machine learning, is based on artificial neural networks. It provides the healthcare industry with the ability to analyse data efficiently with pinpoint accuracy. It has the ability to reduce admin work and increase insights into the patient’s condition and requirements. This helps medical professionals to focus on their job – that is to save lives.

Along with AI and ML, Semantic analysis and Deep learning will be the buzz words in the medical field in the near future. Together they open up a possibility of transforming the sector altogether.

Digital technology can aid in the clinical research with symptom based case identification. During the Pandemic, online symptom reporting was done in Singapore and UK.

Final Thoughts:

With the global population going Tech Savvy, it has enabled virtual health business models to include a range of services. For eg: enabling longitudinal virtual care, integration of telehealth with other virtual health solutions, and hybrid virtual/in-person care models. It has the potential to improve consumer experience/convenience, access, outcomes, and affordability – Digital Healthcare is one for the future.

With increased awareness, the world is now more than ready to move from the norm and embrace the new.

Like other businesses, if you too are looking for IT Solutions for Healthcare Services, Mindfire Solutions can be your partner of choice. We have significant experience over the years working with Healthcare IT Companies. We have a team of highly skilled and certified software professionals, who have developed many custom virtual healthcare solutions for our global clients over the years.

Here are a few interesting projects we have done to develop virtual health solutions. Click here to know more: Case study on managing high risk patients.

Case study on PWA for mental health.

Spread the love
  •  
  •  
  •  
  •  
  •  
  •  
  •  
  •  
  •  
Sentiment Analysis

Sentiment Analysis in Healthcare

Introduction:

Sentiment Analysis refers to analyzing text data and assigning some kind of sentiment to it. For e.g., we see a movie review on the IMDB website such as – “It was a good movie”. We can understand that the viewer liked the movie and we can go on to say that this review can be assigned a positive sentiment. Similarly, If the review was “It was a bad movie”, we can consider this as negative feedback for the movie and say that it generates a negative sentiment. So how do we go about creating a model that takes in a review/ statement as input and gives out the corresponding sentiment ?

One way to go about it is to create a dictionary of all words that correspond to positive feedback, and another of all words that provide negative feedback. Run a search through the statement and see which words are present. This is a very very simple example of how Sentiment analysis can be done. More on this later, but why would we need a Sentiment Analysis model?

Most companies provide their customers a platform, which could be social media or a company website, to express their feelings about a product or service so that the company can then use this data to improve the quality of their product / services. Since people can post feedback at ease with just their mobile phones, this generates a huge amount of data. Going through all data manually is a labor-intensive process. Hence, sentiment analysis has become an important tool for companies to track and monitor their online feedback and brand value. This is just one example; there are other areas as well where one can use a tool such as sentiment analysis. Let’s look at how it can help to solve some challenges in the Healthcare Industry.

Defining our Input to the model:

Before we discuss the details of the model, we need to find a way to represent sentences for a model to understand. The first approach is bag of words. The way this approach works is we first create a vocabulary of all words we have in our training data. This vocabulary then forms our feature space, or our X’s for the training. Given the number of words in the English language, we could have 10000 words in our vocabulary. We will get to reduce our feature space later.

So now that we have our X’s, we define a way to represent a sentence. We can do so by assigning the count of each word to our feature space. Coming back to our previous example, “It was a good movie”, we will have the following counts or word frequencies- It:1 , was: 1, a: 1, good:1, movie:1. The values for all other words will be 0. Each word will have a fixed position on our feature space, so for all other words, if we substitute zero then we have 0, 0,0,…,1,0,,…1,0…0. Note we have counts only at the position of the words in our current example. This type of encoding is also called one hot encoding.

We can limit the number of words our vocabulary has by using a few tricks, for instance removing words like a, the, this, is, etc. These words do not generally add any meaning to our sentences. These are stop words. Next, to further limit our vocabulary, we can keep only those words that have a frequency above a certain threshold. Doing this, we can reduce our vocabulary to 1/10th of our initial size. Now coming to encoding our target variable. Since this is a good review, we have 1 as our target variable. Note that we are only trying to classify good or bad reviews and having a 1 for good and 0 for bad is sufficient for training our model. All of these can be achieved by a few lines of code using python’s NLTK (Natural Language ToolKit) library and python’s Scikit-learn library.

Defining our model:

Machine learning can broadly be categorized into two parts, supervised and unsupervised learning. Supervised learning is one where we give both input and targets as training data. This is generally used for classification or regression tasks. Unsupervised learning contains just input data, no output is associated with it, and this is used for clustering problems, where the algorithm tries to group the input data into clusters. Since this is a classification problem, we will be classifying the review into one of the good or bad classes, we will rely on either Logistic regression or Random Forest classifier.

We will go into the details of logistic regression or Random Forest in a different article. But for the purpose of this venture, we will pass a python list (arrays) to the model. This is the input list that we get using one hot encoding as defined above, and get a one or zero as an output. Let’s assume the model we build has around 80% chance for classifying a given review accurately. This may not necessarily be difficult to achieve for a task such as this. All of these can be achieved fairly easily using python’s Scikit Learn library.

Problems faced by the service Industry and Solution with Sentiment Analysis:

An insurance company wants to find out whether imparting behavioral training to their service staff has an impact on the overall feedback they receive as reviews.

We start by defining a metric for valuation. Let our performance indicator be the number of positive reviews/ total number of reviews. Assuming there are at least 30 reviews for each staff under consideration. We get the reviews for all staff before and after behavioral training has been imparted. Put them through our model and generate positive and negative outcomes for these reviews. Then do a comparison of percentage positive and negative reviews before and after the training. This will establish a correlation between training and change in reviews. To establish causation, we also need to create treatment and control groups. The treatment group will have the staff that receives the training and control will be the staff that doesn’t. Comparing the change between treatment and control groups will tell us whether the training has an impact.

Like other businesses, if you too are looking for solutions in Sentiment Analysis, Mindfire Solutions can be your partner of choice. We have deep expertise in AI and ML Capabilities. With a team of highly skilled and certified software professionals, that have developed many custom solutions for our global clients over the years.

Spread the love
  •  
  •  
  •  
  •  
  •  
  •  
  •  
  •  
  •  
AI in Healthcare

AI in Healthcare Insurance

AI has transformed industries and has immense potential to reshape the healthcare landscape. Medical data like patient visits, prescriptions contain valuable information which can be extracted to create a more structured data format. This has become possible with Artificial Intelligence and Machine Learning. This in turn offers insights into the trends and facilitates collaboration between different healthcare units. AI applications range from early detection of symptoms to potential diagnosis at a fraction of the cost and increased accuracy.

What is Optical Character Recognition?

Artificial intelligence refers to the use of Machine Learning algorithms to mimic human behavior. Say we want to create a program that takes an input and gives an output. The program uses some decision-making mechanism to arrive at an output. This is primitively done by something called IF-ELSE statements. The limitation of these statements is that one needs to know the exact condition that will produce the desired output. For example, we know the marks of a student and we want to assign a grade, we can hardcode the same using if-else statements – IF marks > 90 then grade = ‘A’. In this case, we have a clearly defined boundary that helps us arrive at our output. But what happens when we don’t have a clearly defined boundary?

Let me explain this with an example. Suppose we have an image of a letter. And we want our program to tell us which letter it is. What kind of code shall we write? This is an example of a problem that doesn’t have a clearly defined boundary. One way to solve this problem is to build a model, which does not use if-else statements but works quite differently. The idea is to feed the program an input image (say an image of ‘A’) and tell the program that it’s an ‘A’. We do this repetitively and try to get the program to learn what ‘A’ looks like. Hence, the term “Machine Learning”. We do the same for every letter or number. This falls under the computer vision category, namely Optical Character Recognition.

Overview of Natural Language Processing :

Natural language Processing is an area of AI and Linguistics and it deals with the application of computational techniques and models to the analysis of human languages. NLP deals with processing written text including but not limited to extracting useful information such as named entities, etc. This requires an understanding of what a word means, which is not something computers generally have. This too is done by learning, where a huge amount of text is fed to the model, and it will try to learn patterns and dependencies between words. In the next section, we will define a problem statement and see how an application of these two concepts can help us make better decisions faster, way faster.

Problems faced by the Healthcare Industry :

Insurance companies have certain parameters to account for when finalizing the premiums they charge for their insurance. One of the most important parameters is the medical history of the member/ insurance holder. The idea is that if a member has more cases of medical history then that member is more likely to raise a claim in the future, thereby costing more.

So the insurance companies need to know relevant details of the medical history and assign risk scores (this could be a topic for another article) corresponding to the medical history. But medical histories are generally stored in paper form. Suppose you had a doctor’s visit, everything there is generally stored in paper format. One might have had any number of tests, and these are in most cases available in paper form. Thus, going through all the paperwork of a member’s medical history is an engaging task. This might take a person anywhere between 30mins – 1 hour. So, is there a way to automate the task?

How can AI help to resolve the issue?

The first step in the process is to get the images of all our documents. The idea is to use OCR to extract the text information from images and subsequently use NLP to extract relevant information, such as diagnosis, procedure or operation, medications that the member is on, etc. There are many open-source OCR engines, one such engine is Tesseract OCR.

Tesseract is used for text detection within large documents or used in concurrence with an external text detector. It can be used directly or through an API to extract text from images. It supports Unicode and has the ability to discern more than 100 languages and can also be trained to recognize multiple languages. The current model, Tesseract 4 focuses on line recognition. It also supports the legacy Tesseract 3 in recognizing character patterns. It is compatible with many programming languages and frameworks. CNN (Convolutional Neural network) is typically used for single character whereas RNN is used for multi-characters.

The next step is to feed the image to the tesseract engine. It will give a file output that contains text extracted from the image. There are various Open source NLP engines. We then feed lines from the text file to our NLP engine which will read each line and use dependencies between words to figure out what our diagnosis, procedure or medications will be. Most NLP engines offer phrase matching capabilities, so we can look for particular phrases as well. We can narrow our search to a specific diagnosis (or any other information of relevance) as well.

Final Steps :

Once we have extracted output from the NLP engine, we can create a database that will have fields such as member name, document type, extracted information, etc. We can use the above pipeline and feed it numerous files at once and after every output, we can append the same to our database.

This process takes a mere few seconds to go through all the files of a member. Using this, we will be able to read through the medical history of thousands of members in a matter of hours.

Like other businesses, if you too are looking for Application development in AI, Mindfire Solutions can be your partner of choice. We have deep expertise in AI and ML Capabilities. With a team of highly skilled and certified software professionals, that have developed many custom solutions for our global clients over the years.

Spread the love
  •  
  •  
  •  
  •  
  •  
  •  
  •  
  •  
  •  
NLP Image

Impact of NLP on Healthcare Industry

Natural language processing (NLP), along with machine learning, deep learning, computer vision, and image recognition, are all branches of artificial intelligence (AI). The goal of NLP software is to build computer systems that will accept input in the form of spoken or written language and will provide spoken or written output i.e. communicate as if the computer system were a human.

Thanks to devices and applications like Alexa, Siri, Google Assistant and Cortana, much of the world’s population has at least a passing familiarity with NLP. It is being used today to perform a wide range of tasks across many industries. Until recently though, healthcare organizations have lagged behind others in capturing the benefits NLP delivers. However, it’s beginning to catch up.

Here are several use cases for NLP in healthcare that are already enhancing the field. Each of these will contribute to the larger digital transformation of healthcare as technology continues to advance.

……………………………………………………………………………………………………

Medical Coding and Billing

NLP streamlines the way medical coders extract diagnostic, procedural and other clinical information. Rather than a coder reading documents and converting them to alphanumeric codes, NLP reads them and submits the codes to the coder for verification. This allows the human coder to work on documents that NLP cannot process accurately, and reduces the overall expense of coding medical information. In the end, more accurate and thorough coding results in more accurate and timely billing.

Virtual Nursing Assistants

The rise of virtual nursing assistants capable of communicating with patients using NLP is underway. Regular communication between patients and the nursing bot extends care beyond the walls of the clinic room without burdening existing resources. Adherence to the patient’s care plan can be monitored, and triggers can notify providers of issues that need human attention. Patients can receive round-the-clock access to support and answers, including help with medication. Researchers in this field estimate virtual nursing assistants will reduce U.S. healthcare costs $20 billion by 2026.

Robot-Assisted Surgery

Some surgical robots use AI to apply information obtained from prior surgeries to the current case, leading to progressively better outcomes. Beyond the many well-known advantages, robotic surgery delivers, adding an NLP component allows surgeons to query the system and to direct its actions verbally.

Reducing “EHR Burnout”

Recent studies have indicated that healthcare providers spend nearly half of each day updating electronic health records and doing other administrative work, which is a matter of concern. It leaves them with very less time to perform their core functions of examining and discussing clinical, diagnostic and treatment information with patients in a face-to-face environment.

Entering and managing patient information is a major contributor to physician burnout. More than half of physicians surveyed in a Physician’s Foundation 2018 study, reported entering data into the EHR reduces their efficiency and detracts them from their interaction with patients. Systems that use NLP allow physicians to enter notes into the EHR by speaking to it. This saves time versus having to type. Besides, it also allows patients to amend or correct what the doctor is entering into the EHR.

Other Important Use Cases

While improving the clinical value of EHRs and reducing physician burnout is one of the most pressing challenges among healthcare organizations, NLP is contributing to the digital transformation of healthcare in several other ways. For example, NLP is helpful in

While improving the clinical value of EHRs and reducing physician burnout is one of the most pressing challenges among healthcare organizations, NLP is contributing to the digital transformation of healthcare in several other ways. For example, NLP is helpful in

  • Comforting patients who become confused and anxious because they do not understand the data being presented to them through a portal website. For instance, NLP can explain the meaning of abbreviations and medical terminology. Rather than leaving the patient to worry or call the physician to explain the report, NLP can educate and possibly also calm the patient.
  • Offering summarized updates of key ideas, concepts, and conclusions contained in large volumes of clinical notes, journal articles and other narrative texts gives practitioners quick access to volumes of information that would otherwise require a lot of time to read through.
  • Easy extraction of data from free-form text and insertion into fixed-field data files, such as the structured fields in an EHR.
  • Handling a physician’s free-form spoken or text query, which is especially useful for queries that require gathering and organizing data from multiple sources.
  • NLP and other AI components can also accelerate the movement away from fee-for-service models and toward value-based healthcare by organizing unstructured health data derived from EHRs and other sources. Much of that “hidden” big data can shed light on health outcomes for entire populations of patients, which has been impractical until recently.

 

……………………………………………………………………………………………………

If you have any queries in this field, talk to Mindfire Solutions. For over 20+ years now, we have been the preferred Software Development Partner of over 1000+ Small and Medium-sized enterprises across the globe.

Spread the love
  •  
  •  
  •  
  •  
  •  
  •  
  •  
  •  
  •  

Healthcare IT Trends in 2018

Healthcare IT Trends in 2018In 2017, worldwide healthcare IT market grew steadily despite cost pressure and political uncertainty. Many enterprises leveraged latest digital technologies to provide remote and mobile healthcare services in an efficient and timely way. At the same time, the new healthcare applications and solutions introduced by various startups even made it easier for medical practitioners to provide mhealth and telehealth services to patients regardless of their current geographic locations. But the rapid advancement in digital technologies has made some of the hottest healthcare IT trends of 2017 obsolete. The healthcare service providers must adopt new healthcare IT trends in 2018 to stay relevant and competitive in the short run. Continue reading Healthcare IT Trends in 2018

Spread the love
  • 7
  • 1
  •  
  • 1
  • 1
  •  
  •  
  •  
  •  
    10
    Shares