HOW DEEP LEARNING IS TREATING HEALTH-BASED ISSUES

our consultant managing the role
Author: Mark Proud
Posting date: 8/30/2018 8:00 AM
Hospitals are a complicated system of many moving parts both human and machine. In recent years, the role of humans driving the process, entering information, gathering individual records, or arranging medical and billing follow ups, has shifted.

Paper records have become electronic health records and AI is helping streamline bulky processes. AI bots and programs free up time when it comes to arranging follow up medication or helping to make diagnoses and, in some cases, can assist physicians or surgeons making remote calls and decisions.

As Machine Learning and AI enter healthcare, the application of Deep Learning, using data rather than task-based algorithms, is coming into its own. At this year’s KDD event, both Healthcare and Deep Learning were hot topics, with a day of programming dedicated to each.

The Three Ingredients Driving AI Advances:


  • Supply of digital data which can now be created.
  • Development of algorithms to make artificial neural networks.
  • Graphics Processing Unit (GPU) chip architecture pioneered by NVIDIA.

GPUs are used by anyone working in Deep Learning and can be used in any number of ways, such as videos, graphics, and audio recordings to name a few. This type of usage has huge impact on Healthcare’s image, clinical data interpretation, and management. 

For example, Radiology requires consultants to look at medical imagery to determine whether or not there are abnormalities. With the inclusion of Deep Learning, this process could be done in minutes or seconds rather than hours. This is especially important as a diagnosis made is based on findings in the radiological images.

However, Radiology, is not the only instance where health management can utilise Deep Learning and AI. From helping to identify ideal treatments for patients, to helping administrators utilise their resources more effectively and efficiently, there is huge potential for implementation. 

Predictive Analytics in Deep Learning


Healthcare can be hard to predict. But, with the application of Machine Learning, there are some things we can focus on, starting by asking ourselves the following:

  • Is it scalable? This may differ based on different hospital systems and how much data wrangling is involved. But, the more straightforward the answer, the better.
  • Is it accurate?  Using Deep Learning data for electronic health records can greatly improve accuracy and avoid the distraction of false alarms.

Predictive modelling can help Healthcare professionals answer the questions above more accurately, including determining which patient will have a particular outcome versus which patient will not. Though this model does not diagnose the patient, it does use the information from data gathered to identify the conditions in which the patient was being treated and predict outcomes. Like a human might pick up nonverbal signals, AI picks up signals based on the data it receives to and helps inform physician’s decisions.

The Patient Journey 


Whether it’s the customer journey or the patient journey, there is a path that needs to be followed. As Deep Learning helps fuel the use of AI in Healthcare, our patient journey becomes less stressful and more streamlined. 

Below are a few ways Deep Learning is helping to facilitate a more efficient health management system:

  • At Home: You go to a doctor because you don’t know what’s wrong. But, how do you know which doctor you should make an appointment with? AI can help. From your home PC, a few clicks and few questions can direct you to the correct provider for your needs.
  • In the Waiting Room: To avoid long wait times, you can check in via an app, have an AI bot ask a number of questions for you to answer to help better prepare the physician for your visit with the goal of a quicker diagnosis.
  • With the Doctor: Referrals are great. But, having to explain your health issue or record, can be daunting. In addition, the doctor to whom you’re referred may have to call your traditional physician and discuss, or he or she may have papers to read cutting into their time with you. Instead, AI standardises how the doctor reads the notes and can lay it out the way the doctor prefers, increasing your time with them and streamlining their process.
  • Patient Follow Up: An AI bot based on Deep Learning algorithms can become part of a provider’s team, checking in, asking a few questions, and sending a friendly reminder email, text, or phone call to remind patients to take continue their course of treatment. 

The introduction of Deep Learning into Data & Analytics has made an impact across many industries, but especially Healthcare. not the least of which has been healthcare. From speech recognition to Natural Language Processing, the effects have been informative and transformational.

If you’re interested in Deep Learning, predictive analytics, or AI we may have a role for you. We specialise in Junior and Senior roles.  To learn more, check out our vacancies. You can also call us at +44 20 8408 6070 or email us at info@harnham.com.

Related blog & news

With over 10 years experience working solely in the Data & Analytics sector our consultants are able to offer detailed insights into the industry.

Visit our Blogs & News portal or check out the related posts below.

3 questions to ask yourself before your next BI hire

Data & Analytics are a vital part of every organisation nowadays, so it is not surprising that the importance of Business Intelligence keeps growing. With increasing demands from executive management, operations, and sales, a stronger and better BI team is essential.  The responsibilities of the BI team include but are not limited to: performing Data validation and Data Analysis, delivering KPI related reports and dashboards, and working with end users to define business requirements and needs. However, as every company is different, every BI department is different as well. This means that from one BI team to another, the needed skills can vary completely. To get the most out of your team, it is important to have a clear understanding of what skills you already have, which skills you need to add with your next hire, and whether this is realistic for your business.  Here are three important questions to ask yourself before your next BI hire:  1) What does your team look like at this moment? To be successful in expanding your team, it is vital to take a closer look at the type of profiles and skillsets you already have. This is a good time to map out where the skills are in your team and see what is lacking, or what can be improved. To do so, you should consider three key elements: how (much) Data is used and made available, how this Data is structured and what is being done with this Data. The following three questions are important here:  Do you get the right Data out of your Datawarehouse/Data Lake? How is the Data structured now, and do you get the reports and dashboards needed?  Are you able to provide stakeholders with the right insights? These questions can function as starting point of deciding what skills you have now, and which areas to focus on with your next BI hire to fill in gaps or improve the areas where needed. 2) What does your Data Roadmap look like?  It is important to have a clear vision of where you want to go with your BI team and how to leverage your Data. At the highest level, your vision will be determined in a Data Strategy. On a more practical, day-to-day level, the steps to take are outlined in a Data Roadmap, with every part of the process requiring a different skillset. 
 What we often see is that companies who are at the start of their Data Roadmap, first hire a Data Analyst. Typically, a Data Analyst knows how to work with the Data and has a strong business sense but is not a specialist in either field. On the other hand, when the Data infrastructure has been set up, the need is higher for someone who can make sense of the Data and present this in reports and dashboards.  Two key points to consider: What is the next step in your Data Roadmap?  What type of skillset is needed to get to that next step? For example, this can be technical skills such as building Data Pipelines or stronger analytical skills to get insights from the Data.  By having a clear understanding what phase of your Data roadmap is next, it will be easier to hire the next member of your team. 3) What is realistic for your business? While you may know what type of profile(s) to hire next, it is important to determine whether this is feasible. The following factors are important to consider: As with every field of expertise, the salary ranges depend on which type of profile you are looking to hire. It is vital here to ask yourself where to invest your money best. For example, it is great to have an Insights Analyst in the team, but is this type of profile the main priority? You might want to first hire a Data Analyst to structure the Data and build useful reports. The candidate market within Data & Analytics is tight, so think about what you can give them in return to attract the best talent. A training program for personal development and the possibility to work flexible hours are two selling points that make your company stand out from the rest.  Location is key for many candidates. Businesses in larger cities are more popular with strong candidates in comparison to more remote businesses.  It is clear, therefore, that multiple factors are involved in determining what your next BI hire should be in terms of skillset and profile.  If you are looking to expand your BI function but not sure where to start, get in touch and I can advise you on the best next steps.  

Thank You, Next: How Machine Learning Is Revolutionising The Way We Make Music

From Vinyl to Tidal; we all know that the way we consume music has changed. Technological advances have made Steve Job’s claim that he would put “1,000 songs in our pockets” seem antiquated, whilst Spotify’s algorithms serve us tracks that we’ll love before we’ve discovered them ourselves.  But can the technologies that have brought us these advancements change the way we make music? Whether it’s leading to new instruments or creating a song without our input, Artificial Intelligence is a game changer.  Make Some Noise Until recently, the best way to imitate a sound was by experimenting with the different settings on a keyboard. However, this is no longer the case, thanks to Google’s research arm Magenta. They’ve created the NSynth Super, an instrument that generates sounds based upon Deep Neural Network techniques.  These algorithms allow the NSynth to not only imitate a sound, but consistently learn more and more about the specificities of that pitch, creating something closer to reality. Users can then combine those individual sounds to create something unique and entirely original. This is potentially just the beginning of a new wave of music, and in a decade’s time the NSynth could end up having as big an impact as autotune.  Talking About AI Generation Whilst we’re still waiting to see the impact of instruments akin to the NSynth, machine-led compositions are becoming more and more commonplace. Using a Recurrent Neural Network (RNN), one can feed a model existing music and ask it to generate something new. By learning the patterns and rhythms of notes from a variety of compositions, the model should be able to output an original and melodical sequence. Although these may not be the most amazing tracks in the world, they do serve a purpose. Music production platform Jukedeck allows users to input their requirements for a piece of music (genre, temp, mood, length, instruments etc.) that can then be automatically generated using AI. Obviously these aren’t designed to be chart hits, but production music that can be purchased cost-efficiently for YouTubers, Short Films and other backing-tracks.   Despite the fact that this remains the most common use of AI in music, some artists are looking to push this even further. Musician Taryn Southern, for example, has created an EP based purely on AI compositions generated using Amper Score. The platform generated a beat, melody and basic structure before Southern then rearranged and added lyrics too. Could this form of collaboration become the future of mainstream music? Rage Against the Machine Learning As with any change, AI’s interruption of the music industry is not without controversy, and there are those who believe that the human contribution is what makes music what it is.  Indeed, there are still several limitations to what AI can achieve creatively. Despite a neural network’s success with creating original compositions, another’s ability to write lyrics was somewhat lacklustre. Despite being trained on a combination of lyrics (for structure), and literature (for vocabulary), its output was largely nonsense and included lines such as “I got monk that wear you good”.   Perhaps, like Southern’s compositions, AI is best used as an accompanying tool. London-based start-up AI Music offer technology that ‘shape-shifts’ songs to adapt to the context in which they’re played. This could be anything from tempo changes to match a listener’s speed to remastering tracks to appeal to different moods and situations. IBM’s Watson Beat, on the other hand, creates compositions that naturally fit to the visuals of a video. In this context, as within many other industries, AI looks set to support our existing skillsets rather than replace jobs.  Whether you’re looking to create collaborative technologies or revolutionise an industry, we may have a role for you. Take a look at our latest opportunities or get in touch with one of our specialist consultants to find out more.

recently viewed jobs