Smart Triage, an AI-powered autonomous patient triage system developed by health technology company Rapid Health, was implemented at The Groves Medical Centre in October 2023. The system has transformed patient access, enabling equitable and safe care based on clinical need rather than on a first-come-first-served basis.

An independent real-world evaluation, funded by Health Innovation Kent Surrey Sussex, one of 15 health innovation networks across England, and conducted by Unity Insights, has measured the impact of autonomous patient triage between October 2023 and February 2024. The evaluation assessed the system’s acceptability, implementation, effectiveness, and impact on health inequalities.

Key findings of the evaluation include:

• Patient waiting times reduced by 73%, from 11 to 3 days, for pre-bookable appointments
• The practice had 47% fewer phone calls at peak hours, with a 58% reduction in the maximum number of calls, all but eliminating the “8am rush”
• Same-day appointment requests fell from over 62% to 19%, significantly expanding the capacity for pre-bookable appointments
• 70% fewer patients needed a repeat appointment, having received the right care on their first visit
• 85% of appointments booked via the new system were delivered face-to-face, a 60% increase compared to the pre-implementation period
• Only 18% of all patient requests were initiated over the phone after the system was implemented versus 88% prior to it being implemented
• 91% of appointments were automatically allocated without staff or clinical intervention.

These changes have culminated in a better overall experience for patients at The Groves Medical Centre. GPs now spend 50% more time with each patient by moving from 10 to 15-minute appointments.

Dr Andrea Fensom, GP Partner at Groves Medical Centre, remarked: “Smart Triage has completely changed how we work. It has not only optimised our resources but increased patient access. Feedback shows that patients find it easy to use our online tool and it’s convenient for them, giving them multiple options for appointments where safe to do so and booking them with the most appropriate clinician for their problem. We are all very proud of these results”

Increase in Appointment Availability

Additionally, the practice has achieved an 8% increase in the number of appointments delivered per working day without hiring additional staff. Patients now have a wider selection of appointment slots to choose from, with an average of 61 slots available per patient appointment request. This has resulted in a 14% reduction in patient no-shows, despite the practice already maintaining low DNA (did not attend) rates.

Jake Kennerson, Group Manager at Groves Medical Centre, added, “The positive outcomes we’ve seen in such a short period are a testament to the effectiveness of this innovative system. There’s been a significant decrease in the number of patients requiring same-day appointments and wait times have been drastically reduced. All of this change was achieved during the peak winter months and without any additional staff. If others were to adopt a similar approach, it could lead to transformative results for patients and the NHS as a whole.

AI Delivers Autonomous Triage Process

In contrast to traditional online consultation and triage tools that only collect information, Smart Triage fully automates the patient navigation process from the initial contact with their GP practice. Whether requesting care online, by phone, or in person, patients are guided through a series of questions based on their concerns. The system then assesses their symptoms and directs the patient to the most suitable care, even enabling immediate self-booking into the right appointments. This streamlined process empowers patients to access care at their convenience while relieving the practice from direct involvement in each request. This is the first time a study has proven an autonomous clinical system is safe and effective in doing this process end to end.

Expressing his pride in the system’s success, Carmelo Insalaco, CEO of Rapid Health, said, “We’re really proud to see the extraordinary impact of autonomous patient triage at The Groves Medical Centre. These results reflect what we consistently observe with our customers across the country – the remarkable potential for Smart Triage to dramatically enhance patient access and choice, while solving the persistent challenges of lengthy waiting lists and disruptive morning bottlenecks. We look forward to further collaboration and expansion across the wider NHS to benefit more patients and healthcare providers”.

By implementing the autonomous patient triage software, GP practices and Primary Care Networks (PCNs) can improve patient access, reduce workload, unlock capacity and manage patient demand more effectively. With better access for patients online, call volumes are reduced and peaks in demand can be smoothed out, eventually eliminating the ‘8am rush’. This ultimately enhances and automates the Modern General Practice Access Model which was introduced by NHS England last year.

The post NHS Study Reveals 73% Reduction in Waiting Times Achieved through Pioneering Autonomous AI Triage System at GP Practice appeared first on .

So: what are these opportunities, and where are we seeing AI make the biggest difference?

Automating administration

The most common use of AI in healthcare is to outsource time-consuming, repetitive administrative tasks that divert valuable resources away from patient care. Speed is often of the highest priority with this in mind, using technologies like generative AI and Robotic Process Automation (RPA) to accelerate processes.

Generative AI can entirely automate the creation of documents and reports, reducing the time pressure on administrative staff. RPA takes this one step further, using those reports as reference points to automatically schedule appointments and billing, as well as distributing that data to other key staff. Critical information is readily available when needed, improving overall operational efficiency – and without putting the workforce under any more strain.

As data-driven systems are entirely beholden to the data they’re using, this sort of integration can also significantly reduce human error. There’s very little room for the system to misinterpret the cold, hard data so crucial for patient care and compliance – avoiding the mistakes that can lead to serious consequences.

Beyond that, the use of advanced analytics can facilitate better data management. The classic applications of AI in a business setting still apply; it can analyse and identify patterns in datasets too large and/or too complex for humans to discern. This enables medical professionals to make data-driven decisions that can improve patient outcomes and optimise resource allocation. For example, predictive analytics can help in forecasting admission rates, enabling hospitals to better manage their staffing and resources.

Addressing medical practitioner burnout

COVID-19 brought much needed attention to the issue of medical professional exhaustion while also exacerbating it, with healthcare workers facing unprecedented levels of stress and fatigue. A recent study from the University of Bath has found that almost half of NHS staff are showing symptoms of burnout.

The logistical burden that AI can take on makes it an important tool for workers in this environment – not just in terms of collating data, but also in how we interact with it. For example, natural language processing (NLP) algorithms can transcribe and summarise consultations, freeing up clinicians to focus more on patient interaction rather than paperwork.

NLP can then, in the right environment, pull any of that data for a user at the drop of a hat. It can do so in response to direct questions in normal language, rather than making users wrestle with archaic hardware and ancient user interfaces to get what they need.

It’s important to also recognise that we very much live and work in the era of flexible working – and healthcare technologies should reflect that. The ability to access key patient information away from a particular practice is hugely important in reducing the need for travel and promoting a healthier work-life balance.

That accessibility positions AI to assist in clinical decision support, providing practitioners with real-time insights and recommendations based on the latest research and patient data. This not only improves the accuracy of diagnoses and treatment plans, but also reduces the cognitive load on clinicians.

Ultimately, having access to up-to-date information and automated recommendations empowers medical experts to make faster, better-informed decisions – which both lead to better treatment outcomes and reduced stress.

AI in health practice

A prime example of AI’s impact in healthcare can be seen in radiology. Recently, healthcare technology provider deepc has made significant strides in using AI to support stroke detection, chest x-ray triage, cell identification, and PET quantification – as just a few examples that empower clinicians and radiologist to better ascertain disease in patients.

These AI algorithms provide non-overlapping data in combination of the clinical review of the patient’s images. They allow for quicker reporting times and the identification of anomalies in radiology and pathology images that might have otherwise taken much longer to detect with the human eye, which  is incredibly important for treating conditions where early diagnosis is very strongly tied to improved patient outcomes.

For example, a patient is scheduled for an outpatient CT scan, and the AI detects a stroke. Utilising the critical results that come from the AI health systems, the imaging management layers (VNA, PACS, enterprise viewers) can notify other HIM systems to raise the urgency of this routine exam to the top of the priority list.

These same systems can go beyond that to standardise the interpretation of images. AI health algorithms provide a consistent and objective analysis of imaging data, reducing the variability and ensuring that all patients receive the same high standard of care. While a radiologist will still interpret the exams the AI can quickly point them to significant findings that may be crucial to the diagnosis and reducing their dictation times per report.

The use of AI in combination with a reading radiologist ensures that small details aren’t overlooked due to fatigue, and also helps in protecting radiologists from their own bias. This standardisation is particularly beneficial in large healthcare systems, where multiple radiologists may be interpreting images from different locations and with differing perspectives.

The expansion of AI in health

All of these integrations are firmly grounded in the reality of day-to-day treatment – but the potential applications of AI extend far beyond administrative automation and industry standards. AI is making significant strides in various other areas, including predictive analytics, and personalised medicine. It offers medical professionals a chance to deliver more targeted and effective treatments, improving outcomes and overall care quality.

Predictive analytics can help identify patients at risk of developing chronic conditions, enabling early intervention and preventive care. AI algorithms have the performance levels and the data required to properly assess electronic health records (EHRs) for any correlation with the risk factors associated with conditions such as diabetes, cardiovascular diseases, and mental health disorders. Proactively addressing these risks will have much more chance of successful prevention, while also reducing the strain on the practice itself.

In personalised medicine, we’ll see the advent of more precise and individualised treatment plans. By analysing genetic, environmental, and lifestyle data, we’ll be able to help tailor treatments to each patient’s unique characteristics. This approach not only enhances the effectiveness of treatments but also minimises adverse effects, leading to better experiences and outcomes.

Looking ahead

AI technologies are constantly evolving, and it is crucial for health practitioners to stay ahead of the curve. We’re already seeing the groundwork for ambitious projects being laid.

In the UK alone, the new Labour government has announced a new AI Act as part of its King’s Speech; just a couple of months ago, the Medicines and Healthcare products Regulatory Agency (MHRA) has recently launched AI Airlock, its new regulatory sandbox for AI as a Medical Device. AI is only set to become faster, more intelligent, and more capable – with more tools for its development and regulation.

That’s not to overlook the huge impact that AI has already had upon healthcare. By automating administrative tasks, supporting clinician well-being, and enhancing diagnostic accuracy, the sector is transforming for the better. Innovations is paving the way for a more efficient, effective, and compassionate medical system.

As we look to the future, the integration of AI in the health industry will continue to expand, offering new opportunities to enhance patient care and operational efficiency. By embracing these technologies, medical professionals can not only improve their current practices, but also prepare for the challenges and opportunities that lie ahead.

By Alexander Ryan, Director EMEA Healthcare Business Development, Hyland

The post The Transformative Power of AI in Healthcare: Enhancing Efficiency, Combating Burnout, and Improving Diagnostics appeared first on .

You’ve spoken about putting our doctors and nurses at the center of healthcare technology, where they deserve to be. What does that mean, and why is it important?

Physician burnout is the worst it’s ever been, and a significant contributor to that is the heavy administrative burden put on clinicians. They are using software and technology that isn’t designed for them. The solutions are not intuitively designed, are disruptive to clinician workflows and require numerous clicks and scrolls. It’s far too time-consuming and mentally exhausting. Physicians are leaving medicine at alarming rates. We need to design solutions that work for them and make tasks easier to complete, rather than more difficult.

How is voice-enabled technology key to solving the issue of physician burnout?

Voice is the next generation of user interaction, the next big revolution in user interface since mobile. If physicians can simply speak naturally to complete tedious, time-consuming tasks — such as clinical documentation or finding information from the EHR — it frees up time and mental energy so they can focus on patient care and have more balance in their lives, in turn helping to reduce physician burnout.

One of the physicians we work with in Lynchburg, Va., Dr. Elizabeth Goff, has struggled with work-life balance. She considered going part-time — or quitting medicine entirely. There just wasn’t enough of her to go around as a busy mom and doctor. She’s featured in a recent mini-documentary, “From Burnout to Balance.” Dr. Goff talks about being “so weighed down and didn’t realize it” until the burden was alleviated. Now, she’s back to loving what she does and giving the best of herself to her patients and family. We’re very proud that Suki Assistant enabled Dr. Goff to maintain her practice full-time. That’s an important outcome considering the clinician staffing shortages the industry is reckoning with today.

Health systems are facing tremendous financial pressures. How can they afford to invest in new solutions at a time when they are projected to not make any profit this year and to lose money next year?

Suki can be a meaningful solution that helps health systems tackle their most pressing financial issues. Physicians save significant time on administrative tasks, and as a result, can spend more time on patient care. Our data shows that doctors who use Suki increase their encounter volumes between 20-29%, which translates to approximately $58K – $84K of incremental annual revenue per physician. That is a tremendous benefit in a time when many health systems are expected to lose money.

Another contributor to financial pressures is attrition. Doctors are a critical resource for our collective health, and we must keep as many of them actively practicing medicine as possible. Systems that invest in solutions that make their lives easier, and help prevent physician burnout, will be best positioned to retain and attract more physicians. For healthcare organizations reckoning with the dual, interrelated challenges of retention and negative margins, Suki can help move the needle on both in a significant way.

What’s the difference between ambient and technology-driven solutions?

Today, “ambient” solutions rely heavily on humans in the background transcribing encounters and completing other tasks. As a result, these solutions are relatively expensive (thousands of dollars per user per month), have a significant turnaround time, and the quality varies depending on the person working on the task. In contrast, technology-driven solutions are more affordable, tasks are completed in real-time, and the quality actually improves with use as machine learning models get tuned to each user’s individual preferences.

Since January 2022, Suki has seen a 7X increase in users and an expansion of support to physicians across 30+ specialties. Suki is the only pure technology-based voice assistant for healthcare. The acceleration of our adoption underscores the real need for an affordable tech-based solution.

We’ve entered a new era in AI where it will be very clear which solutions use tech and which still rely on people. We’ll also see an accelerated pace of innovation in which tech-based solutions will tackle challenging problems in increasingly automated ways. We have an exciting product roadmap at Suki that I am excited to share more details about soon.

You’ve said that voice is poised to become the primary user interface for all tech, with voice becoming the “new mobile.” What do you mean by that?

Voice is on the cusp of changing how we interact with all technology. Just as smartphones revolutionized how we communicate and obtain information, voice will do the same for how we work and live. You can already start to see it with consumer voice assistants such as Siri or Alexa. You talk to those assistants, and they help you with tasks like checking the weather or adjusting your thermostat. Eventually, voice will become the main way we interact with all technology from writing emails to researching information to shopping.

Suki has delivered some exciting innovations in the past 12 months, adding multiple features that give clinicians more freedom and flexibility. From “show me” commands that enable providers to easily retrieve patient information — such as medications or allergies — from the EHR to the ability to use their mobile device as a microphone to talk to their computers, Suki’s goal is to make the completion of administrative work as frictionless as possible. That way, clinicians can focus on patient care.

Looking to the future, we understand one of your biggest fears in healthcare is slowness. When you say speed does not mean quality has to suffer, what do you mean by that, and why is it important?

When it comes to technology, healthcare “slowness” can have negative impacts from many vantage points. For instance, quality innovation is key to forward momentum, but the wrong development process can result in products that don’t deliver meaningful value. A thoughtful product development process that includes user feedback will maintain speed without sacrificing quality. When such a process is in place, it is easy to develop valuable features quickly. One key is understanding user workflows, obtaining their feedback on what’s been developed and adjusting accordingly. It may seem obvious, but time and again, companies fail to pressure test their new capabilities in the field and end up in pitfalls.

The slowness of the healthcare buying process is another significant challenge and prolongs adoption of technologies that can transform workflows and care delivery. Healthcare organizations can take months or years to vet and select new solutions providers. This long sales cycle carries risks for healthcare organizations, and it delays efforts to advance innovation.

Organizations sacrifice the gains that a solution could provide when they take an extended amount of time to select a solution. Meanwhile, some solutions providers — especially startups — may not be able to survive these long assessment periods. That puts innovation at risk for the entire industry.

About the author

Punit Singh Soni is the Founder & CEO of Suki and a seasoned product leader who has been part of high-growth teams at Google, Motorola, Flipkart and Cadence Design Systems. He holds an MBA from The Wharton School and an MS in Electrical Engineering from University of Wyoming.

The post Fighting Physician Burnout through Voice-Enabled Technology appeared first on .

AI is well-established in some sectors of the health care industry as well. Pharmaceutical researchers are using it to discover new drugs with greater speed and efficiency than before. Hospital systems are using it to study their patients’ journey from the point of admission to the point of release, with the goal of making the process more efficient and satisfying.

But one of the most important health care specialties of all – cardiology – is just beginning to recognize the benefits that AI can bring to its field. As we know, heart disease is the leading cause of death in the United States. By 2035, more than 130 million adults, or 45% of the U.S. population, are projected to have some form of cardiovascular diseases (CVD). In 2035 total costs of CVD are expected to reach $1.1 trillion. Direct medical costs are projected to reach $748.7 billion. Indirect costs are estimated to reach $368 billion.

Cardiology has adopted various imaging technologies over recent decades, and the use of imaging technologies is linked to improved patient outcomes. But the millions of images being captured every day are still being analyzed manually, placing heavier and heavier workloads on clinicians, increasing the risk of diagnostic errors, disagreements among experts, and eventual human burnout. Cardiologists at the top of their profession agree that they need more ways to provide better care and improve outcomes. It is time to recognize the emergence of additional technologies like AI and move this vital medical field even more forward.

By combining cardiac imaging analysis with artificial intelligence, we can tap the insights of multiple experts, improve the quality of analysis, shorten the time spent waiting for diagnoses, and lower costs in our health care system. AI will not replace humans, of course, but it can provide an immediately available second opinion and help researchers and clinicians make even better decisions. AI is a consistent, quantifiable, readily available tool that will better equip us in the lifesaving work of cardiology.

Let’s look at how this could work

Researchers seeking to improve the use of stents in opening clogged coronary arteries can look at a series of images collected through Intravascular Optical Coherence Tomography, or IVOCT, and input their analysis into AI-enabled software. The more images they analyze, the more they can teach the software what to look for when stents fail to expand properly, when they fail to completely cover diseased segments of an artery, or when dissections at the stents’ edges go untreated. Armed with this hard data, the researchers can recommend ways to improve products, procedures, or both.

Or imagine a clinician performing an echocardiogram on a patient and seeing a potential problem with the patient’s ejection fraction (EF), a measure of the volume of blood the heart is pushing into the body. It would take hours for the clinician to manually trace the hundreds of image frames needed to accurately quantify the patient’s EF, evaluate the heart strain, and make a diagnosis. Instead, clinicians today quickly “eyeball” the images, leaving a diagnosis dependent on the physician’s experience, alertness, and access to second opinions. AI-enabled software, having learned from the insights of many experts diagnosing many similar cases, can automatically interpret the images, save the clinicians precious time, and give them and their patients added confidence in the diagnosis and course of treatment.

Artificial Intelligence and Cardiac Imaging

These types of AI advances in cardiology are not far off in the distant future.

Dyad Medical Inc., a Boston-based medical technology startup, has developed the Libby  software platform to use artificial intelligence to help interpret three- and four-dimensional medical images in intravascular OCT and additional other primary modalities for cardiac imaging.  A global community of clinicians have shared their expertise to train Dyad’s artificial-intelligence model, effectively offering thousands of second opinions. The U.S. Food and Drug Administration recently cleared Dyad’s Libby platform for viewing and quantifying intravascular OCT images. The FDA clearance is an important milestone that will give researchers, imaging centers and hospital systems another tool to automate their ability to see inside blood vessels.

In training its artificial intelligence software to help interpret cardiac images, Dyad also has accumulated what it believes is the largest repository of cardiac imaging data held by a private company, allowing its software to learn from the insights of many experts analyzing this large trove of data.

Other advantages of the Libby platform include that it is cloud-based, so users can access results from anywhere, at any time of day or night, and on any device. The platform also integrates into a hospital’s existing information technology, so any new applications can be added easily to the platform and the existing systems and workflows.

FDA clearance in hand, a leading research hospital will soon begin using the platform to research ways to improve clinical conclusions based on intravascular OCT. By the end of 2022, we expect to see the platform and the intravascular modality in use in hospital settings. We cannot predict when the FDA will act on the use of Libby for other modalities, but the company is currently submitting for FDA clearance the platforms for multiple future modality support.

In the ideal future, every practitioner around the world will consult Dyad technology every time they interpret any medical images. This will continue to train Dyad’s AI-enabled software to become an even more accurate, more efficient, and more valuable tool for everyone involved in the diagnosis of heart disease globally.

About the author

Ronny Shalev holds a Ph.D. in electrical engineering and computer science from Case Western Reserve University and is CEO and founder of Dyad Medical Inc.

The post It’s Time to Combine Artificial Intelligence with Cardiac Imaging appeared first on .

SENSIGHT is the first data analytics platform to provide industrial scale access to anonymised and de-identified real world data insights globally across multiple therapy areas combined with built in simple to use research algorithms.

The platform provides clinicians, research academics and life science professionals with an instant AI research capability to analyse health insights across a curated common data environment, underpinned and protected by a rigorous information governance and security framework. No direct patient data is, or ever will be, shared on SENSIGHT.  The platform instead rapidly interrogates Sensyne’s deep diverse datasets and delivers intelligent analytics and data-driven insights, not the data itself. Subscribers will be screened to ensure legitimate interest, with only those in accredited companies and organisations being accepted.

Researchers can communicate and collaborate with each other on the platform – creating a virtual scientific research network that connects professionals across the healthcare and life sciences industries creating a community with common interests in particular research fields or areas of unmet medical need.

Lord (Paul) Drayson PhD FREng, Chief Executive Officer of Sensyne, said, “Sensyne Health was founded to bring the power of clinical AI and health data analytics to improve patient outcomes, reduce healthcare costs and accelerate the discovery and development of new medicines. For several years we have worked within an ethical, transparent, and fair framework that ensures patient data privacy and security and shares the commercial return from our work with healthcare providers such as the NHS and health systems in the US. SENSIGHT now enables us to exponentially scale that vision and creates a new channel for our other products and services. The transformative power of Sensyne’s ethical AI is now available to the smallest and largest healthcare and life sciences organisations and its design enables the creation of a global community of researchers all working towards a common aim: better health for all.”

SENSIGHT has launched with access to a 2 million anonymised and de-identified patient data set which is expected to grow rapidly to 10 million patients by the end of December 2021. The data is available from Sensyne’s unique research partnerships with leading NHS and international healthcare providers.

This data is available free to Sensyne’s partners, while commercial users will be charged £25,000 per person per year.

SENSIGHT for Synthetic Patient Cohorts

A specific feature of SENSIGHT at launch is the ability to offer medical researchers unique functionality to analyse the feasibility of running synthetic control arms on specific patient data sets using Sensyne’s proprietary analytics tools. Synthetic control arms create virtual patient groups based on real patient data to serve as the control group in a clinical trial.

The platform enables the ability to create, validate and explore curated patient cohorts, initially in the areas of heart failure, stroke, and haematological cancer with a further six disease areas following by the end of December 2021 and future plans for SENSIGHT eventually covering most disease areas.

The post Sensyne Launches Real-world Patient Data Analytics Platform, SENSIGHT appeared first on .

The ongoing effects of the pandemic are placing huge pressures on healthcare delivery at a time when there is a growing need to deliver value-based care. This coupled with growing patient populations with chronic conditions and/or co-morbidities, staff and skills shortages, and increased strains on resources, are all resulting in healthcare providers increasingly looking towards AI technologies to fill the gaps in patient care. The opportunity is significant, outlooks for the sector expect the global AI healthcare market to grow from USD $4.9 billion in 2020 and reach USD $45.2 billion by 2026.

Technologies that can automate workflows and processes, and artificial intelligence solutions designed to assist diagnostic processes and help streamline treatment and care provision have become a crucial element of any care system. Seeing AI and ML as a strategic division within the delivery of patient care are now, more than ever, fundamental to successful healthcare provision.

Artificial intelligence simplifies the lives of patients, doctors and hospital administrators by performing tasks that are typically done by humans, but in less time and at a fraction of the cost. The applications are extensive, and already AI is being applied across a huge range of healthcare applications, from increasing the accuracy of detecting and diagnosing cancer, to tailoring treatment plans to meet the specific needs of individual patients.

The Impact of AI on Patient Care

The impact of AI on patient care was the topic of discussion for members of our HealthTech Networking Club at our recent monthly HealthTech RapidConf events.

Looking to the future optimistically, there are countless possibilities for the support of AI. Currently, machines are only as good as we understand biology to be.  Therefore, the focus should be on enabling clinicians to do a better job and as a result improve care.

This concept was supported by panellist, Dr. Lynda Chin, who states that, “patient care is not an engineering problem, computers don’t treat patients”.

Many factors influence decision making, and generally, in medicine, not all information is complete therefore approaching it as an engineering problem, or a technical problem, is not as straightforward. In medicine, it is about bending rules, and human judgment and intuition are important.

Dr. Joanna Elmore adds that an area where AI can be very powerful and helpful in medicine is when there is variability. She uses a personal story of cancer screening which resulted in 3 different diagnoses. In healthcare, variability is a significant issue and delivering a consistent standard of care is problematic. For example, one pathologist could interpret a case of invasive melanoma in one way, but when presented with a similar case a year later, would they interpret that in the exact same way? Generally, the answer is no, and less than half the time they’ll offer a different diagnosis. AI on the other hand will consistently provide the same diagnosis, every time. It will be more reproducible!

Also, during the session, Dr. Anthony Chang tackled the negative presumptions about AI stemming from the incorrect forecast of AI replacing doctors as inaccurate. There is a need for conversational translation between data scientists and medical doctors. Clinicians can use AI to learn more about themselves and connect the dots by working backward to make breakthroughs in diagnoses.

This is a sentiment echoed by Dr. Chin. AI will make the jobs of cardiologists and radiologists more meaningful and productive by reducing the burden placed upon them. For example, a task such as reading an EKG study, could ideally be tasked to an AI application. The ability for the technology to apply an extensive library of learned experience to the reading, means that it is well provisioned to identify, and flag, abnormalities quickly and more accurately. The time saved by automating such tasks, means that physicians are empowered to use their time in more effective ways and ultimately provide a much higher overall standard of care.

How AI can Improve Patient Care

There is an emphasis on AI levelling the playing field for patient care which will improve overall outcomes. AI should help physicians make data-driven decisions, with decision support.

Dr. Chang highlights where machine learning has been applied to covid testing to improve processing rates. In one recent study, AI was able to detect Covid 26% faster than lateral flow tests.

He also cautions that we must focus on adopting AI for the long-term with a vision of improving things for the next generation of clinicians, while still supporting this generation of clinicians. One aspect of this is to use machine learning to address current biases which exist within healthcare data. In the future, the requirement to deliver equitable care can be made easier by AI and ML.

According to Balint Bene, CEO of specialist HealthTech accelerator Bene : Studio, AI should be used in ways that enhance the patient experience, improve physician time management and leverage tools to gain efficiencies – let doctors be doctors!

Want to be involved in future discussions of our HealthTech Networking club?

The invite-only networking club connects leading HealthTech companies, investors, healthcare providers and other key experts/players in the Healthtech industry providing private networking opportunities.

The networking club is free to join simply apply for an invite here.

The post Understanding the role of AI in Patient Care appeared first on .

The stakes of AI ethics are especially high in the healthcare sector. Medical professionals, who are bound by codes of ethics and federal regulations, must exercise due diligence when processing data. Otherwise, they could risk causing harm if patient medical data is not carefully applied.

Better understanding of potential AI pitfalls and new standards for its ethical use in healthcare are helping professionals theorize the best way to use it. These new guidelines can help practitioners leverage the technology in a way that minimizes potential risk.

The Ethical Challenges of AI and Big Data in Healthcare

Medical researchers and healthcare providers face two major challenges related to AI: the replication of bias in algorithms and the ethical use of patient medical data in training.

Bias is one of the most significant challenges AI researchers face. Without the proper precautions, well-trained algorithms can reproduce bias that already exists in the world. For example, algorithms trained on gender-imbalanced chest X-ray data tend to be worse at identifying the signs of disease in the underrepresented sex. A skin cancer-detecting algorithm that relies primarily on data from light-skinned individuals may be ineffective at detecting anomalies in those with deeper pigment.

Healthcare algorithms are becoming increasingly popular due to the real-world benefits they can offer. AI-powered CT scan analysis can tell radiologists which scans to look at next based on the likelihood it contains evidence of diseased tissue. This helps slash wait times and improve radiologists’ analysis accuracy.

Preventive algorithms like these can reduce the overall cost of healthcare while improving the quality of a provider’s medical services. This is especially important as expenses continue to rise and it becomes increasingly common for fully funded employers to pay premiums that grow steadily every year.

As they become more commonplace, algorithms may be likely to encode bias from existing datasets into healthcare tools that appear objective. More diverse information and improved cleaning processes can help researchers manage these tendencies. If statistics are inclusive, they’re less likely to reproduce already existing healthcare biases. Effective cleaning and testing processes can help researchers catch biased datasets or algorithmic discrimination.

The data that enables these AI algorithms can also create challenges for researchers. Privacy and data protection expert Emerald de Leeuw has argued that companies will need to be ethical with their data to survive.

Informed consent and the effective de-identification of patient data will likely be necessary if researchers want to ethically gather and analyze this information.

Potential Regulations and Standards for Ethical Artificial Intelligence

Specific ethical and regulatory frameworks can help researchers translate these goals into real-world practice. For example, some researchers have argued that medical professionals who use AI should also become artificial intelligence experts. Knowledge of important AI drawbacks — the black-box algorithm problem, algorithmic bias and automation discrimination — can help practitioners understand when they should use their own judgment to second-guess results.

Others have suggested that informed consent around AI should extend beyond the collection of data. They think patients should be informed of the use of AI team members before being subject to a healthcare algorithm or intelligent medical equipment like an AI-enabled surgical robot.

At the same time, major organizations are beginning to create formal guidelines that may help researchers develop ethical artificial intelligence in healthcare. In January 2021, the World Health Organization published a report on AI in healthcare that included six guiding principles for designing and implementing medical artificial intelligence.

These principles, which include “protecting human autonomy,” “promoting human well-being and safety and the public interest,” and “ensuring inclusiveness and equity,” could help provide a rough foundation for more specific future guidelines for ethical healthcare AI.

New Ethical Guidelines May Structure the Use of Healthcare AI

Healthcare AI algorithms offer potential for medical providers and researchers. However, ethical challenges may make these algorithms much riskier in practice. Without the proper precautions, algorithms could encode existing biases into apparently objective tools or allow practitioners to leverage patients’ medical data without their explicit consent.

Researchers and AI experts are beginning to lay the groundwork for future ethical guidelines. They will help practitioners effectively apply AI in healthcare while minimizing the risk for harm it can cause.

They may also help practitioners better understand the potential challenges that the use of AI tools may pose — and how to communicate those risks to patients. That way, artificial intelligence in healthcare will better benefit everyone involved.

The post Ethical Artificial Intelligence: Regulations and Standards in Healthcare appeared first on .

This agreement represents an important first step in Sensyne’s mission of building an international resource for medical research using real world evidence.  The St. Luke’s dataset covers 2.5 million de-identifed unique patients, from a patient population of approximately one million people across 12 hospitals and over 300 outpatient locations.

Consistent with Sensyne’s approach with all its relationships with health systems, this research will be undertaken to the highest standards of information governance and data security and in accordance with The Health Insurance Portability and Accountability Act (HIPAA), the U.S. data protection legislation that protects sensitive patient information. All data supplied to Sensyne for research will be de-identified by St. Luke’s beforehand, will remain in the U.S., and the provision of the data will operate under an agreed set of data processing procedures.

“We are proud of the results we have achieved to-date in partnership with the U.K.’s National Health Service and we are excited to apply our pioneering partnership model in the United States with a respected leader like St. Luke’s. Healthcare data saves lives, and our aim is to build the world’s best resource for the ethical use of anonymised and de-identified patient data for medical research. This new partnership represents an important step towards that goal.” Comments Lord (Paul) Drayson, PhD, CEO of Sensyne Health.

Founded in 1872, St Luke’s University Health Network is a fully integrated, regional, non-profit network of more than 16,000 employees providing services at 12 hospital sites and 300 outpatient sites. Dedicated to advancing medical education, St. Luke’s is the preeminent teaching hospital in central-eastern Pennsylvania.  In partnership with Temple University, St. Luke’s established the Lehigh Valley’s first and only regional medical school campus. St. Luke’s flagship University Hospital has earned the 100 Top Major Teaching Hospital designation from IBM Watson Health nine times and seven years in a row, including in 2021 when it was identified as the number one ‘Teaching Hospital in the Country’.

St. Luke’s joins 11 National Health Service (NHS) Trusts in the U.K., covering more than 13% of the U.K. population, which have partnered with Sensyne sharing anonymised clinical datasets to enable the discovery of new treatments, increase disease understanding, and advance clinical trial design.

Under the terms of the agreement, St. Luke’s will receive shares in Sensyne Health plc as well as a royalty on revenues that are generated by Sensyne from the research undertaken under this agreement.

Chad Brisendine, VP and Chief Information Officer of St. Luke’s said:  “At St. Luke’s, we are committed to caring not just for the health and physical safety of our patients, but also for the safety and privacy of their information.  In an information and data-driven world, we are always looking for ways to lead our industry towards more effective and nuanced approaches to data protection and privacy for patients. Sensyne’s ethical model represents the kind of approach we need to embrace to advance our clinical and financial goals while meeting our patients’ expectations of us as trusted stewards of their healthcare information.”

The post Sensyne Health Signs First U.S. Strategic Research Agreement with St. Luke’s University Health Network appeared first on .