AI, your new GP?

10

October

2025

No ratings yet.

AI in the mainstream has become synonymous with LLMs, giving students an easy way out of assignments or a tool to generate content. But is there a way in which AI has a tangible benefit? European scientists may have an answer.

A team at the European Molecular Biology Laboratory (EMBL) in Cambridge and the German Cancer Research Center introduced a new AI model for healthcare called Delphi-2M, which can predict more than 1,000 conditions a person might face in the future. Its creators hope that it could predict conditions like Alzheimer’s disease or cancer, which affects millions of people each year.

Authors have taken inspiration from large language models, such as Gemini, which are trained on enormous amounts of text scraped from the internet. These models learn to select the word most likely to come next in any given sentence. Similarly, Delphi-2M AI model analyses data from 400,000 anonymous participants to predict healthcare conditions.

The difference from typical LLMs lies in its ability to account for the time between conditions and the patients’ life events. Creating this feature didn’t come without problems, as early version sometimes predicted diagnoses for people who had already died.

The model was subsequently tested on data from 1.9m Danes, yielding varying results. Events that follow from a specific condition, like diabetes, had more accurate predictions, while more random external factors, like a virus, were harder to predict.

It may take up to ten years before we will see healthcare Gen AI used in daily healthcare checkups. Nonetheless, the model has proven valuable for research, as clustering conditions allows exploration of relationship between diseases. AI is already present in hospitals, mostly assisting with analysing healthcare data. A well-known example, serving over 300,000 patients annually, is Powerful Medical, start-up that interprets electrocardiograms enabling early diagnosis of cardiovascular conditions.

However, there are downsides. A series of recent studies reported that AI models across the healthcare sector led to biased results for women and ethnic minorities. The problem lies in the datasets used for training, content from the internet, which existing societal biases reflected in the LLMs responses. Researchers from MIT have suggested that one way to reduce bias in AI is to filter which data should be used for training.

References:

Heikkilä, M. (2025, September 19). AI medical tools downplay symptoms in women and ethnic minorities. Subscribe to read. https://www.ft.com/content/128ee880-acdb-42fb-8bc0-ea9b71ca11a8

Guardian News and Media. (2025, September 17). New AI tool can predict a person’s risk of more than 1,000 diseases, say experts. The Guardian. https://www.theguardian.com/science/2025/sep/17/new-ai-tool-can-predict-a-persons-risk-of-more-than-1000-diseases-say-experts

A new AI model can forecast a person’s risk of diseases across their life. (n.d.). https://www.economist.com/science-and-technology/2025/09/17/a-new-ai-model-can-forecast-a-persons-risk-of-diseases-across-their-life

Please rate this

Philips and the Rise of Digital Twins: From Smart Systems to Smarter Lives

18

September

2025

No ratings yet.

You probably think of cars, airplanes, jet engines, or heavy machinery when you hear the term ‘digital twin.’ Conversely, Philips likely evokes images of hospital monitoring, TVs, or shavers. Nonetheless, Philips, a world leader in healthcare technology, is changing the story of the digital twin by taking it from the factory floor to the hospital setting and, eventually, to the human body.

From Buildings to Bodies
Digital twins, virtual models of physical systems, have long been used to optimize industrial operations (Emmert-Streib, 2023). Now, Philips is applying these principles to healthcare, starting with infrastructure.

In a recent hospital demonstration (Philips Healthcare, 2023), a care unit was digitally replicated and simulated to track patient flow, staff shifts, and room capacity. By adjusting parameters like staff availability and care demand, the model revealed impacts on key performance indicators such as discharge times. As such, data derived from these models provides administrators with powerful insights to optimize hospital operations.

Predictive Machines and Personalized Organs
Philips isn’t stopping at buildings. Their MRI systems now use digital twin models to track performance, forecast failures, and guide maintenance. Combining live sensor data with historical information, these simulations predict machine states, moving healthcare from reactive to predictive servicing (Philips, 2018a). In clinical settings where downtime delays diagnoses, foresight like this can be lifesaving.

The company has also ventured into modeling the human heart. In 2015, it introduced HeartModel, which generates personalized 3D heart simulations using ultrasound data (Philips, 2018b). By tailoring these anatomical models to individual physiology, clinicians can better evaluate cardiac function and plan treatments. Yet challenges remain. No two hearts are identical, and building universally accurate models is complex (Philips Nederland, 2022). Therefore, instead of replicating the entire human body, Philips now focuses on modular ‘building blocks’ that already add clinical value, such as single-organ models in cardiovascular care (Philips Nederland, 2022).

Beyond Twins
Digital twins are just one part of Philips’ broader vision. The company is also exploring technologies like virtual reality (VR) and augmented reality (AR). VR, for instance, would enable simulations of lifelike medical scenarios, allowing clinicians and students to practice complex procedures in safe, controlled environments. AR holds promise in surgery: imagine overlaying patient-specific 3D models onto the body, enabling surgeons to ‘see through’ the skin and anticipate anatomy before operating (Philips, 2018b).

Why this matters now
These innovations arrive at a critical moment, as healthcare systems are under immense pressure. According to the Future Health Index 2025, over 30% of patients experience worsening conditions due to delays, and 1 in 4 are hospitalized before seeing a specialist (Philips, 2025b). AI-powered digital twins could help ease these burdens by streamlining diagnoses, predicting complications, and personalizing care.

However, adoption isn’t straightforward. While 82% of healthcare professionals believe AI tools can save lives, only 59% of patients share that trust (Philips, 2025a). Concerns over accuracy, ethics, and data security remain barriers, highlighting that building public confidence is as important as advancing the technology itself.

A New Kind of Value
Philips’ transformation is not just technological, it’s strategic. Mapped onto the Business Model Canvas, Philips’ trajectory is clear. Key resources now extend beyond hardware to include AI, cloud platforms, and patient data. Customers increasingly consist of hospitals, clinicians, and health systems, and revenue streams increasingly revolve around ‘insight-as-a-service’ (McKinsey & Company, 2023), marking a shift from product-driven to data-driven ecosystems (Weill & Woerner, 2015).

The Future
So, digital twins are more than a breakthrough, they represent a shift towards predictive, personalized care that could redefine the future of healthcare. Ultimately, their impact depends not just on innovation, but on society’s willingness to embrace it.

As long as these tools remain complements to existing workflows, they have my trust. What about you, do you trust these developments?

References
Emmert-Streib, F. (2023). What is the role of AI for digital twins? AI, 4(3), 721–728. https://doi.org/10.3390/ai4030038

McKinsey & Company. (2023). How healthcare systems can become digital-health leaders. McKinsey & Company. https://www.mckinsey.com/industries/healthcare/our-insights/how-healthcare-systems-can-become-digital-health-leaders

Philips. (2018a, August 30). The rise of the digital twin: How healthcare can benefit. Philips Global. https://www.philips.com/a-w/about/news/archive/blogs/innovation-matters/20180830-the-rise-of-the-digital-twin-how-healthcare-can-benefit.html

Philips. (2018b, November 12). How a virtual heart could save your real one. Philips Global. https://www.philips.com/a-w/about/news/archive/blogs/innovation-matters/20181112-how-a-virtual-heart-could-save-your-real-one.html

Philips Nederland. (2022, May 19). Met een digitale tweeling kunnen we voorspellen hoe een patiënt reageert. Philips Nederland. https://www.philips.nl/a-w/about/news/archive/standard/about/news/articles/2022/20220519-met-een-digitale-tweeling-kunnen-we-voorspellen-hoe-een-patient-reageert.html

Philips. (2025a). Future Health Index 2025: Building trust in healthcare AI. Philips Global. https://www.philips.com/a-w/about/news/future-health-index/reports/2025/building-trust-in-healthcare-ai

Philips. (2025b, May 14). Philips Future Health Index 2025: AI poised to transform global healthcare, urging leaders to act now. Philips Global. https://www.philips.com/a-w/about/news/archive/standard/news/press/2025/philips-future-health-index-2025-ai-poised-to-transform-global-healthcare-urging-leaders-to-act-now.html

Philips Healthcare. (2023, February 16). Optimal care system design using Digital twin [Video]. YouTube. https://www.youtube.com/watch?v=2Bf6VfDVtmU

Weill, P., & Woerner, S. L. (2015). Thriving in an increasingly digital ecosystem. MIT Sloan Management Review, 56(4), 27–34. https://sloanreview.mit.edu/article/thriving-in-an-increasingly-digital-ecosystem/

Please rate this

3D printing in healthcare

7

October

2022

No ratings yet.

Nowadays, customization and personalization are becoming more standard practices in many areas, whether it is in retail or in technology. A technology that enables this in many different facets is 3D printing. 3D printing is an upcoming technology that can be used for multiple purposes. Currently, for businesses, it is enabling them to easily create prototypes of their final product. This is called “rapid prototyping” (Hoffman, 2020). The 3D printer allows them to quickly adjust the product and implement potential changes.

In several industries such as healthcare, art and automotive industry 3D printing can be used and an increasing number of ways of applying this technique are found. Especially in healthcare 3D printing can have multiple benefits such as customisation and personalisation, increased cost efficiency, enhanced productivity and democratization and collaboration. For surgeries that involve implants or prosthetics, 3D printing will allow for easier customisation as the prototype can be made at a higher speed and adjustments that are needed can be implemented faster, which thus makes the customisation easier. Also, the speed at which these customised parts are made is much higher compared to the current traditional methods. As these surgeries and therefore the customised parts are relatively low volume, the cost of 3D printing is minimal (Ventola, 2014).  

As mentioned above one current use is the personalisation of implants and prosthetics. There are several more and potentially more complicated applications in the healthcare industry. One application of 3D printing is the bio-printing of tissues and organs. Tissue or organ failure is currently treated by organ transplants, but there is a chronic shortage of human organs. Even if a transplant has taken place, it is still unsure how the body reacts to this new organ and if it will not be rejected. Bio-printing with cells from the patient’s body could eliminate this risk of rejection.

In conclusion, bio-printing is a promising technology that could increase the speed of customisation in healthcare as well as a potential solution to the organ shortage.

Bibliography

Hoffman, T. (2020, July 1). 3D Printing: What You Need to Know. Retrieved from pcmag.com: https://www.pcmag.com/news/3d-printing-what-you-need-to-know#:~:text=Designers%20use%203D%20printers%20to,and%20novelty%20items%2C%20and%20toys

Ventola, C. L. (2014). Medical Applications for 3D Printing: Current and Projected Uses. P&T, 704-711.

Please rate this

Proteus: the end of the smart pill? 

4

October

2022

5/5 (1)

Andy Thompson, CEO of Proteus Digital Health, came up with an idea that brings AI and the healthcare together. He invented the world’s first pill with microchip that tracks your health. The tiny microchip has to be taken together with the medicine and is able to gather data about the effectivity and safety of the related medicine. The microchip is coupled to a smart system where the consumer can see their personal data and get reminders when to take the drug. The sensors in the microchip detect effects of the medicine as high adherence or negative side-effects. As a consequence, a huge amount of costs and even deaths can be reduced. The World Health Organization (WHO) estimated that in developed countries, 50% of patients that are chronically ill experiences non-adherence of medicines. For instance, in the US this amount is approximated around 25%-50% and causes around 125.000 deaths annually.

Moreover, healthcare providers that have permission to gain insight into the data, can work with more efficacy. The doctors are better able to prescribe treatments and prevent unnecessary bad health outcomes. As depicted in the picture below, the microchip is inserted into a capsule of the drug and will eventually transfer the data to a wearable sensor patch (Kleinsmith, 2022).

This innovation seemed very promising at first. However, Proteus filed for bankruptcy one year after its invention. The CEO remains positive and is convinced that its product will flourish in the future (Kleinsmith, 2022). My thoughts on this are also positive and it makes me think why it did not become popular as it can improve the health industry to a great extent.
So, I am curious, have you ever heard of this and what are your thoughts of it?
Sources

Kleinsmith, N. a. P. S., 2022. Proteus Digital Health: Healthcare for Everyone, Everywhere, Rotterdam: s.n.

Please rate this

AI4Covid: Effective AI covid-tests using only cough sounds

3

October

2022

No ratings yet.

In the fight against the coronavirus, early and accurate diagnosis is vital. To this day most common tests still rely on antibodies, therefore results are often only conclusive after several days and not reliable enough.

Researchers in the field of automated cough classification have been working on another strategy: They adapted a supervised machine-learning algorithm that detects slight differences in coughs and can diagnose or rule out respiratory infections accordingly. 

This tool is supposed to automatically identify cough sounds and define them pursuant to certain parameters. AI makes it possible to compare patterns with other coughs and diagnose instantaneously. Cough sounds are especially informative because the sounds correlate with tissue structure in the respiratory organs, in addition to providing insight to the behavior of surrounding organs and structures.

The most challenging aspect of the studies is to find the most significant features, on which grounds to train the machine-learning system. The Massachusetts Institute of Technology has based their program on the four attributes: Muscular degradation, vocal cord strength, sentiment as well as respiratory and lung performance (Saplakoglu, 2020). For their program thousands of volunteers uploaded forced coughs and filled out information on their health status, symptoms and covid infection. While a large group of cases were then used to train the machine-learning system, another was used to function as a test group. Although results were very encouraging, transferring this success out of the laboratory provided a challenge, since cough sound not only vary on respiratory function, but many other parameters, such as mother-tongue and gender. Therefore investigation continued and showed that time-frequency representation of a cough successfully aided in achieving higher quality results. So far the best model is Random Forest with an accuracy of 90% (Tena, Clarià and Solsona, 2022).

These cough related covid tests have the potential to contain the pandemic in a more efficient way, as they would – if installed as an app on phones – not need high cost data evaluation in labs and would therefore be more easily accessible and affordable. Also AI can spot covid infections sooner than rapid covid tests can and would therefore be a strong advantage to the prevention of high spreading.

References

Saplakoglu, Y. (2020). Newsela [online] newsela.com. Available at: https://newsela.com/read/ai-detect-covid19-cough/id/2001015957/%C2%A0/https://newsela.com/read/ai-detect-covid19-cough/id/2001015957/%C2%A0/ [Accessed 2 Oct. 2022].
Tena, A., Clarià, F. and Solsona, F. (2022). Automated detection of COVID-19 cough. Biomedical Signal Processing and Control, [online] 71, p.103175. doi:10.1016/j.bspc.2021.103175. Available at: https://www.sciencedirect.com/science/article/pii/S1746809421007722  [Accessed 1 Oct. 2022].
Detecting COVID-19 through cough sounds. (n.d.). www.nature.com. [online] Available at: https://www.nature.com/articles/d42473-022-00294-9 [Accessed 2 Oct. 2022].

Please rate this

Horse Racing: Reduction of Death Cases using Modern Technology

30

September

2022

5/5 (2)

Although for years Horse Racing has been popular for its thrill and the opportunity to place bets, it has been increasingly targeted with criticism by the public for its numerous fatal injuries – not only concerning horses, but also jockeys. In order to cast off this unfavorable reputation, the British Horse Racing Authority (BHA) has established means to reduce mid race injuries, such as obligatory pre-race examinations. 

With the general amelioration of medical technology, those health check-ups strongly increased in significance. Especially the refinement of the MRI has fostered an early detection of illnesses or injuries, like small ruptures of muscle tissue or tendons. Over the last five years, this is estimated to have averted about 30% of fatal equine injuries (EBR, 2022). 

Next to MRIs, ultrasound and thermal imaging cameras that are used to monitor a horse’s temperature post race, other technologies have been developed specifically for this sport. 

The University of Bath has designed an equine fitness tracker referred to as EquiVi (the Guardian, 2019). This device includes three sensors, which are placed on the horse’s body during practice or a race. The sensors are able to continuously measure important vital signs, such as blood pressure, temperature and respiratory rate, and transfer this data simultaneously via a wireless connection to a digital device. This enables coaches, owners and veterinarians to track the horse’s welfare during extreme physical exertion and adapt its training and racing schedule accordingly. In addition, the relation of the visible performance and cardiovascular activity can be examined, which is again very conclusive about the horse’s true level of fitness. Lead researcher Dr. Ben Metcalfe stresses the benefits of such an non-intrusive monitoring device as the horse is not exposed to any damaging influences (www.bath.ac.uk, 2019).

The risk reduction for fatal equine injuries automatically minimises health threats for the jockey. Still, accidents can and do occur, which led the BHA to ask the University of Bath for another research project. Through remodeling countless falls of jockeys accessible in the digital race archive, they are working to better understand and treat common injuries such as concussions and injuries involving the spinal cord. 

These different approaches to not only prevent mid-race injuries, but also maximise a positive treatment outcome, are only possible through the newest technological innovations. Therefore nowadays, modern technology even contributes to the safety and with it the continued existence of one of the oldest and most traditional sports.

References:
the Guardian. (2019). Equine fitness trackers could save lives of racehorses. [online] Available at: https://www.theguardian.com/sport/2019/mar/30/racehorses-to-be-fitted-with-life-savingfitness-sensors [Accessed 29 Sep. 2022].
Incze, G. (2022). How Horse Racing Has Embraced Technological Innovations. [online] European Gaming Industry News. Available at: https://europeangaming.eu/portal/latest-news/2022/03/02/110251/how-horse-racing-has-embraced-technological-innovations/ [Accessed 29 Sep. 2022].
EBR, E. (2022). How Technology Has Changed Horse Racing. [online] The European Business Review. Available at: https://www.europeanbusinessreview.com/how-technology-has-changed-horse-racing/ [Accessed 29 Sep. 2022].
www.bath.ac.uk. (2019). Boost to horse welfare and performance thanks to new monitoring device. [online] Available at: https://www.bath.ac.uk/announcements/boost-to-horse-welfare-and-performance-thanks-to-new-monitoring-device/ [Accessed 29 Sep. 2022].

Please rate this

Google’s DeepMind facing data privacy lawsuit

5

October

2021

4/5 (1)

From data to app to lawsuit

2015: Alphabet Inc.’s British artificial intelligence subsidiary DeepMind obtains private health records of 1.6 million patients from the Royal Free London NHS Foundation Trust. 

This data was to be used to develop the ‘Streams’ app which aims to alert, detect, and diagnose kidney injuries. The app was being developed for use by doctors to detect acute kidney injury. This app was already being used by the Royal free with great praise.

From DeepMinds point of view, they are making use of valuable data in order to progress healthcare and save lives. From Royal Free’s point of view, they are enabling this by sharing this data and then using the app created by this to treat patients. However, for some citizens, this seems like a breach of data privacy.

The British law firm Mishcon de Reya has filed a class-action lawsuit against DeepMind to represent Andrew Prismall and the other 1.6 million patients whose data was shared. 

Who is at fault?

Something I find quite interesting about this case is that DeepMind is accused of being at fault rather than the Royal Free, who shared the data in the first place. Although the Streams app was developed by DeepMind, the app was a collaboration between DeepMind and Royal Free and could not have succeeded without both of their inputs.

I believe that both players are to blame in this situation and that DeepMind can not be put at fault alone. Who do you believe is at fault in this situation?

How can we prevent this in the future?

For such situations, a healthcare system with strong regulations regarding data privacy, and healthcare providers who abide by such regulations, would largely diminish the threat of major tech firms such as Alphabet. However, too many regulations can inhibit innovation in some situations. Finding a balance between innovation and safety is a challenge that many industries and regulators struggle with worldwide.

I believe that it is no easy task to find such a balance. There is a growing number of factors influencing a push for both regulation and free innovation as digital information becomes one of the most important assets for innovative development. Experts on data privacy and innovation must come together to form regulations that can foster safe innovation.

What do you think should be done to foster safe innovation in the information era?

References:

https://www.bbc.com/news/technology-40483202

https://www.bbc.com/news/technology-58761324

https://www.cnbc.com/2021/10/01/google-deepmind-face-lawsuit-over-data-deal-with-britains-nhs.html

https://deepmind.com/

Please rate this

Big Tech in Healthcare

16

September

2021

5/5 (1)

Hightech giants – such as Google, Amazon and Apple – are on the fast line when it comes to incorporating healthcare into their business. The past months have shown how seriously the big technology companies are already involved in the healthcare market. It becomes clear that from telemedicine to health trackers, to clinical studies, a whole range of market trends are addressed. Each player pursues its own strategy, which is based on its own digital, tech or platform competence: 

Apple continues to strengthen its leading position in the wearables market and adds an ever-increasing number of features every few months. The focus is always on gathering and evaluating user health data. Apple and its devices (iPhone, Apple Watch, etc.) are already deeply embedded in customers’ daily lives, which should not be overlooked. Apple makes use of this proximity to bring clinical research to its consumers’ wrists. According to the latest news, Apple even plans the move to blood-pressure measures and a wrist thermometer in the Apple Watch to help with fertility planning. Furthermore, Apple users will soon be able to share personal health data (e.g. vital, movement and sleep data) with others via the app, e.g. their relatives, their fitness trainer and ideally with the doctor. Consequently, Apple continues its journey into the “closed” ecosystem where Apple users and devices are connected with one another efficiently and in a value-oriented manner. 

With its fundamental skill of data analysis, Google, as the most important point of contact for patients, is continuously developing new services and therefore data sources. With the acquisition of Fitbit in 2019, Google likewise joined the wearables industry. Along with the pharmaceutical company Boehringer Ingelheim, Google works on discovering new application possibilities of super-fast quantum computers for drug development. Furthermore, Google’s Health App incorporated a new function for assessing skin, hair, and nail issues. A sophisticated system analyzes three photos taken by the camera. Several questions are then added to the analysis. Consequently, a list of probable explanations for the symptom is generated. As Google has the most data power they apply this information to create customer-centric goods, which is critical to their success. The software is not intended to replace medical advice from a dermatologist, but it is apparent that it should and will move in this direction.

Amazon is expanding its range of medical services with Alexa, in addition to expanding the variety of its “Amazon Care” health platform and its presence in the online pharmacy market by adding prescription drugs to its “Amazon Pharmacy” range. Furthermore, Amazon dares to step into the highly competitive wearables market with its “halo” bracelet. What makes “halo” so intriguing is that, in addition to tracking vital health parameters like activity level, heart rate, and sleep, it can also analyze the mood/emotional condition of its carrier based on the tone of his or her voice. This sets them apart from the competition and provides Amazon with highly sensitive data which gives them an even more detailed understanding of their customers. For Amazon, the focus is always on the proximity to customers and their needs, or the customer experience.

However, all this hype of the big tech companies in healthcare can only succeed in the long term if patients and healthcare professionals also accept and incorporate their initiatives. Currently, corporations such as Apple are actively pursuing participation from both health researchers and hospitals. A prevalent fear of healthcare professionals is that patients may utilize new technology to self-diagnose, and medical devices would induce worrying results without having an expert opinion. However, if this is actually the case still must be proven. For now, doctors should focus on integrating rather than disregarding new technologies and be more receptive to new innovations brought to the table by both big tech and various entrepreneurs.

References:

https://www.mobihealthnews.com/news/apple-reportedly-looking-expand-smartwatch-health-features-blood-pressure-and-fertility

https://www.apple.com/de/newsroom/2021/06/apple-advances-personal-health-by-introducing-secure-sharing-and-new-insights/

https://www.businessinsider.com/2-14-2021-big-tech-in-healthcare-report?international=true&r=US&IR=T

https://www.theverge.com/2021/5/18/22440754/google-health-ai-skin-condition-model-dermatology

https://healthcaresuccess.com/blog/tag/big-tech-in-healthcare

Please rate this

AI in Healthcare: “The AI will see you now”

13

September

2021

No ratings yet.

In recent years, AI has been integrated in various disciplines with great success (i.e., Supply chain, Recruitment and Video Game Industry). However, one discipline remains heavily apprehensive of AI, and this is the healthcare industry. According to Challen et al (2019), AI and machine learning bots in other industries are able to identify errors and quickly correct themselves before any harm is done. Unfortunately, this is not transferable to the healthcare industry as when it comes to the patient’s health, there is literally no room for trial and error.

Despite the apprehensiveness of the healthcare sector, the use of AI is slowly adopted and can be seen providing simple aid that otherwise requires an additional personnel. Creating chatbots for mental health assistance, monitoring patients’ health and predicting cardiac arrest and/or seizures are some ways AI supports physicians in less high-risk tasks. With the developing technologies in the field of AI, AIs are also able to diagnose patients based on electronic health records, patient history, and pathology images (analysis of blood, urine and tissue samples).

The adoption of AI is slowly progressing due to its ability to alleviate physician burnout, a genuine concern in the field of healthcare. Physician Weekly (2018) states that at least 42% of practitioners experience burnout due to lack of support/personnel, short patient visits, complicated patients and overwhelming workload. Consequently, this affects their performance in providing quality patient care as well as the patient’s safety. Hence, what if the next step for AI in healthcare is to aid physicians with walk-in patients diagnosis and treatment? 

A study by Longoni, Bonezzi & Morewedge (2019) has deduced that despite AI predictive analysis can identify potential ailments faster than human doctors as well as having a higher accuracy rate, patients are reluctant and derive negative utility towards an automated healthcare provider. The argument for these findings are linked to Uniqueness Neglect, a concern that AI are unable to account for each patient’s unique circumstances which makes them hesitant to trust an AI diagnosis. An AI may be able to predict accurately what treatment a patient needs, however, a human practitioner may be able to weigh the pros and cons more specifically, also taking into account the well-being of the patient. 

From a technological point of view, the adoption of AI in the healthcare industry may alleviate physician burnout, aid in less risky decisions such as analytics and image processing, as well as maximizing physician efficiency. However, when it comes to treatment, AI does not have the ability to take over the role of human physicians…… yet.


Please rate this

Quality Data is Quality Care

8

October

2020

No ratings yet. Big Data has changed the way we manage and analyse data in any industry. The healthcare industry is a promising area where data analytics can be applied as it not only reduces costs, it can prevent diseases, predict epidemic outbreaks and improve overall life quality. The future of healthcare will therefore be driven by data analytics and digital transformation. In this blog post I will address why big data in healthcare is important and in what ways it can be applied.

Big data refers to vast quantities of information created by the digitization of everything that gets analysed by specific technologies. Data collection is critical in the healthcare industry. Doctors need to understand as much as possible about patients, as early as possible. Treating diseases at early stages is simpler and less expensive (Lebied, 2018). For years, health data collection has been very costly and time consuming. With today’s innovative technologies, it becomes easier to collect data and translate it to useful insights for better care. This not only reduces costs; it also makes a patient’s health situation more predictable (Lebied, 2018). This in turn enables insurance companies to tailor their packages based on this information.

Healthcare analytics can provide support in asking critical questions such as ‘What is the probability that this patient will recover within 6 months?’ or ‘How likely is this patient to suffer from complications if we perform this surgery’? Driven by the rise of Internet of Things (IoT) and Artificial Intelligence (AI) such as machine learning and robotics, we now have algorithms that can help us answer these questions (Philips, 2020). According to a 2019 survey, 60% of health executives recognize the benefits of healthcare analytics, and 42% of them have seen improved patient satisfaction (Kent, 2019). Below we see how healthcare organizations are using predictive analytics (Dé, 2019).

BlogpostIS

So in what ways do healthcare organizations apply analytics? Here are 3 examples of innovative technologies driven by healthcare analytics.

  1. Electronic Health Records (EHRs)

An EHR is a digital record of a patient’s demographics, medical history, allergies and more. These records are shared via secured systems and are available for providers from the public and private sector (Lebied, 2018). Leading healthcare organizations have integrated next generation analytics platforms into their EHR, such as algorithms and machine learning. This enables predictive, analytics- powered patient risk assessment. EHR can, for example, generate warnings and reminders when a patient should get a new test or when a patient is not following prescriptions.

  1. Precision Medicine

Precision Medicine (PM) is the most common application of machine learning in healthcare. It predicts what treatment protocols are likely to succeed on a patient, based on various attributes and the treatment context (Davenport & Kalakota, 2019). PM requires a training dataset for which the outcome variable is known, which is called supervised learning. Philips, the global leader in healthcare, for example applies PM to the field of oncology. PM will enable treatments to be tailored to genetic changes in each individual’s cancer (Philips, 2020). Cancer patients currently may receive a combination of treatments, while with PM, information about genetics can help doctors decide which treatment is best for each individual patient (Davenport & Kalakota, 2019).

  1. Real-Time Alerting

The traditional way of analysing medical data is facilitated through software that is only used in hospitals (Lebied, 2018). However, as in-house treatments are expensive, doctors want patients to stay away from hospitals as much as possible. To track patient data anytime and anywhere, real-time alerting is applied to wearables. These wearables collect the patient’s data continuously and send this data to the cloud (Knapp, 2018). An example is a blood pressure tracker, which alarms doctors when a patient’s blood pressure is too low or too high, so that appropriate action can be taken. This not only reduces in-house treatment costs; it also makes sure doctors can treat a patient as early as possible. What is more, it allows health executives to access the cloud with collected data to compare data in socioeconomic context and translate the data to useful insights (Lebied, 2018).

Evidently, the opportunities arising from healthcare analytics are very promising. Yet, as predictive analytics can be, their impact eventually depends on their knowledgeable use by health executives. The development of applications empowered by data analytics relies on the expert input. Another important note is that the issue of data privacy arises from the data driven nature of healthcare analytics. What will happen when data is shared seamlessly between different stakeholders? Should patients have control over what data is shared and with whom? The debate of how data can be shared without breaching patients’ trust is still ongoing.

 

References

Davenport, T., & Kalakota, R. (2019). The potential for artificial intelligence in healthcare. Future healthcare journal6(2), 94–98. https://doi.org/10.7861/futurehosp.6-2-94.

Dé, A., (2019). Why Healthcare Analytics Will Deliver More Results In 2019. [online] Biplatform.nl. Available at: <https://biplatform.nl/1826849/why-healthcare-analytics-will-deliver-more-results-in.html> [Accessed 7 October 2020].

Kent, J., (2019). 60% Of Healthcare Execs Say They Use Predictive Analytics. [online] HealthITAnalytics. Available at: <https://healthitanalytics.com/news/60-of-healthcare-execs-say-they-use-predictive-analytics> [Accessed 5 October 2020].

Knapp, J., (2018). Real-Time Healthcare Analytics: Monitor, Predict, Nudge, Act | Vocera. [online] Vocera.com. Available at: <https://www.vocera.com/blog/real-time-healthcare-analytics-monitor-predict-nudge-act> [Accessed 7 October 2020].

Lebied, M., (2018). 12 Examples Of Big Data In Healthcare That Can Save People. [online] BI Blog | Data Visualization & Analytics Blog | Available at: <https://www.datapine.com/blog/big-data-examples-in-healthcare/> [Accessed 5 October 2020].

Philips. (2020). Predictive Analytics In Healthcare: Three Real-World Examples. [online] Available at: <https://www.philips.com/a-w/about/news/archive/features/20200604-predictive-analytics-in-healthcare-three-real-world-examples.html> [Accessed 6 October 2020].

 

Please rate this