Category: IT in Healthcare

Categories : Expert Opinion IT in HealthcareTags :

Digital Tools Can Transform Africa’s Healthcare Outcomes – And Save the Continent Billions

On By ModernMedia
AI image created with Gencraft

By Thom Renwick, General Manager, Roche Pharma South Africa

Early screening and treatment. Much higher survival rates. And savings in the billions of dollars. From AI-powered medicine development to teleconsultations, technology can boost Africans’ health and livelihoods while growing economic and social impact across the continent.

Access to quality healthcare is fundamental to leading a fruitful, economically active life. Yet, breast cancer is still the number one cancer killer of women in Africa – in most cases, while they’re still in their prime. Tragically, most are diagnosed too late for curative treatment.

Across the continent, non-communicable diseases – such as treatable breast cancer – cause hundreds of thousands of preventable deaths every year[1], devastating families and hampering economic growth.

Global projections indicate a worrying 38% rise in incidence of breast cancer and a 68% increase in deaths by 2050 without urgent intervention, with the least developed countries being the most affected, according to a new white paper[2] by independent German economic think tank the WifOR Institute.

The Value of Investing in Innovative Medicines report outlines the economic burden from not treating the aggressive HER2-positive type of breast cancer over five years in seven African countries – South Africa, Kenya, Nigeria, Algeria, Tunisia, Côte d’Ivoire and Morocco. The findings are staggering, indicating a $10.3-billion loss in productivity from 2017 to 2023.[3]

The data also shows that, in Africa, 89% of the economic burden of HER2-positive breast cancer – representing 15% to 20% of all breast cancer cases around the world – falls on women of working age.[4]

It goes beyond economics. Mothers hold households together and when they die that has huge ramifications for entire families and communities.

In sub-Saharan Africa, every 100 deaths among women under 50 leave around 210 children without their mothers[5], resulting in unstable, vulnerable households and long-term developmental challenges.

These figures are a wake-up call, but in challenge lies scope for innovation. I believe we can – and must – turn the burden into opportunity.

Closing the gap through health-tech partnerships

Every woman diagnosed and treated early is not only more likely to survive but also able to remain active in her family and community[6], contributing to shared prosperity.

Through healthcare and technology partnerships, we can leapfrog traditional healthcare models and turn the tide towards survival.

Excitingly, this process has already started. Governments are increasingly setting strategies and allocating funding for digital health. Start-ups and companies are driving the uptake of digital health tools that could revolutionise care delivery.

Artificial intelligence stands out as the breakthrough technology. Pharmaceutical and biotech companies such as Roche are already using AI throughout their value chains, both in the early stage of drug development and also to correctly interpret the enormous amounts of data generated to deliver effective health solutions.

In most sub-Saharan countries, more than 20% of the population lives more than two hours from essential health services.[7] Tech’s role in Africa’s future is about much more than connectivity or commerce. It’s about lives and well-being – AI, apps, telemedicine and other digital solutions can close the gap to bring care closer to people.

But without individuals and organisations working together, innovation can’t come to life.

And since the journey for a patient experiencing a health crisis such as breast cancer involves many stakeholders, we must urgently identify opportunities for partners to come together and spur real action.

This week, Roche sponsored the 28th annual Africa Tech Festival’s first-ever health track. Policymakers, innovators, professionals and experts met to thrash out actionable solutions to the continent’s biggest health challenges.

This was part of an ambitious broader strategy to transform healthcare in Africa – investment in early intervention strategies can generate returns that far outstrip their cost.

Research by McKinsey & Company shows that the African digital health space is already seeing unprecedented growth, with $123-million in investment secured by 55 start-ups in 2021.[8]

The consultancy’s analysis showed that digital health tools – such as virtual platforms for consultations; electronic health records; mobile apps to help patients self-manage their diseases; and patient e-booking platforms – could help South Africa, Kenya and Nigeria capture efficiencies of up to 15% in total healthcare expenditure by 2030.[9]

Widespread adoption could free up an astounding $1.9-billion to $11-billion in South Africa alone.[10]

Speaking with one voice for a better future

Innovation has been the backbone of progress across any major public health disease – whether it’s HIV, cancer or ophthalmology. It takes a combination of passionate people and expert innovation to make a difference.

One existing solution and real-life example of African innovation and partnership is EMPOWER, a groundbreaking digital health platform developed to improve coordinated breast and cervical cancer care in Kenya.[11]

The initiative has grown from a single clinic in 2019 to a 76-site national platform and is integrated into Kenya’s National Cancer Registry.[12]

Empower ensures that the entire patient journey, from screening to treatment and follow-up, is digitally powered.

The current average five-year survival rate for breast cancer across Africa is roughly five out of 10 patients that are diagnosed (48%).[13] My vision is that this will increase to 80% within the next 5 years.

Realising this audacious goal will take commitment from stakeholders to drive action for the tens of thousands of African women who desperately need it.

There is no reason why someone in a Western society should have a better health outcome than here in Africa. The health of our people is the wealth of our nations. We must speak with one voice and act now.

––––––––––

Thom Renwick is general manager of Roche South Africa and the sub-region. He began his journey with the company in 2012 on its United Kingdom graduate programme, following his studies at King’s College London, Cranfield School of Management and the University of Oxford.

During his career at Roche, he has worked in global product strategy in Basel, Switzerland, as head of ophthalmology in the UK and as chief of staff for Pharma International. He won the PharmaTimes New Marketer of the Year Award in 2015 and was featured in the publication’s Smart People series in 2021.

[1] World Health Organisation African region. https://www.afro.who.int/health-topics/noncommunicable-diseases. Accessed: Nov. 12, 2025. [Online]. Available: https://www.afro.who.int/health-topics/noncommunicable-diseases.

[2] WifOR Institute, ‘The Value of Investing in Innovative Medicines: Socioeconomic Burden of HER2+ Breast Cancer and Annual Social Impact of Roche’s Treatments for the Disease in Africa’. Accessed: Nov. 7, 2025 [Online]. Available: https://africa.roche.com/stories/what-s-it-worth-the-value-of-innovation

[3] WifOR Institute, ‘The Value of Investing in Innovative Medicines: Socioeconomic Burden of HER2+ Breast Cancer and Annual Social Impact of Roche’s Treatments for the Disease in Africa’. Accessed: Nov. 7, 2025 [Online]. Available: https://africa.roche.com/stories/what-s-it-worth-the-value-of-innovation

[4] WifOR Institute, ‘The Value of Investing in Innovative Medicines: Socioeconomic Burden of HER2+ Breast Cancer and Annual Social Impact of Roche’s Treatments for the Disease in Africa’. Accessed: Nov. 7, 2025 [Online]. Available: https://africa.roche.com/stories/what-s-it-worth-the-value-of-innovation

[5] WifOR Institute, ‘The Value of Investing in Innovative Medicines: Socioeconomic Burden of HER2+ Breast Cancer and Annual Social Impact of Roche’s Treatments for the Disease in Africa’. Accessed: Nov. 7, 2025 [Online]. Available: https://africa.roche.com/stories/what-s-it-worth-the-value-of-innovation

[6] WifOR Institute, ‘The Value of Investing in Innovative Medicines: Socioeconomic Burden of HER2+ Breast Cancer and Annual Social Impact of Roche’s Treatments for the Disease in Africa’. Accessed: Nov. 7, 2025 [Online]. Available: https://africa.roche.com/stories/what-s-it-worth-the-value-of-innovation

[7] Mckinsey, ‘How digital tools could boost efficiency in African health systems.’ Accessed: Nov. 7, 2025 [Online]. Available: https://www.mckinsey.com/industries/healthcare/our-insights/how-digital-tools-could-boost-efficiency-in-african-health-systems

[8] Mckinsey, ‘How digital tools could boost efficiency in African health systems.’ Accessed: Nov. 7, 2025 [Online]. Available: https://www.mckinsey.com/industries/healthcare/our-insights/how-digital-tools-could-boost-efficiency-in-african-health-systems

[9] Mckinsey, ‘How digital tools could boost efficiency in African health systems’. Accessed: Nov. 7, 2025 [Online]. Available: https://www.mckinsey.com/industries/healthcare/our-insights/how-digital-tools-could-boost-efficiency-in-african-health-systems

[10] Mckinsey, ‘How digital tools could boost efficiency in African health systems’. Accessed: Nov. 7, 2025 [Online]. Available: https://www.mckinsey.com/industries/healthcare/our-insights/how-digital-tools-could-boost-efficiency-in-african-health-systems

[11] Roche Africa, ‘From vision to national platform: EMPOWER scales through Kenya’s National Cancer Institute’. Accessed: Nov. 7, 2025 [Online]. Available: https://africa.roche.com/stories/empower-scales-through-kenya-national-cancer-institute

[12] Roche Africa, ‘From vision to national platform: EMPOWER scales through Kenya’s National Cancer Institute’. Accessed: Nov. 7, 2025 [Online]. Available: https://africa.roche.com/stories/empower-scales-through-kenya-national-cancer-institute

[13] A. Padu-Pebrah, et al., ‘Five-Year Survival Outcomes for Breast Cancer Patients Across Continental Africa: A Contemporary Review of Literature with Meta Analysis’, eLife. Accessed: Nov. 7, 2025 [Online]. Available: https://elifesciences.org/reviewed-preprints/105488#mainMenu

Categories : Cardiovascular Disease IT in HealthcareTags :

Study Highlights the Limits of AI in Heart Care

On By ModernMedia
Human heart. Credit: Scientific Animations CC4.0

There are limits in applying AI to images of the heart, a new study from the Smidt Heart Institute at Cedars-Sinai reveals. The findings were published in the Journal of the American Society of Echocardiography.

Investigators trained multiple artificial intelligence models to read images from echocardiograms, a type of ultrasound test that evaluates the structure and function of the heart. Their goal was to determine whether AI could use these images to calculate measurements like inflammation and scarring that are normally obtained through another, more costly test called cardiac magnetic resonance imaging (CMRI). By examining findings from 1453 patients who had undergone both tests, they found the AI models could not accomplish this task.

“As compared to echocardiograms, cardiac MRI machines are expensive and not available for many patients, especially those in rural areas, so we had hoped that AI could reduce the need for it,” said Alan Kwan, MD, assistant professor in the Department of Cardiology in the Smidt Heart Institute at Cedars-Sinai and co-senior author of the study. “Our results showed the limited powers of AI in this area.”

Source: Cedars-Sinai Medical Center

Categories : Ethics and Law IT in HealthcareTags :

POPIA Compliance for Health Data: Navigating Special Personal Information Requirements in Healthcare

On By ModernMedia

By Wendy Tembedza, Partner at Webber Wentzel


Health data is one of the most valuable assets in modern healthcare, and the Protection of Personal Information Act, 2013 (POPIA) places strict requirements on its use.

Stakeholders in the healthcare sector understand the value of data in ensuring appropriate treatment for patients. With the proliferation of technologies such as artificial intelligence, which enable healthcare practitioners to derive valuable insights from the data they hold, the importance of managing data in a manner that ensures compliance with data protection laws must remain front of mind in all data processing activities.

This obligation is particularly acute given the volumes of data that evolving technologies allow healthcare institutions to collect and utilise. Importantly, when these larger datasets include special personal information, the obligation to process such information lawfully becomes even more significant. This is because POPIA regulates the processing of special personal information (which includes health and sex life information) more closely than it does other forms of personal information.

The implications of POPIA’s strict regulation of processing health and sex life information means that, where a responsible party is considering collecting such data, an assessment must be made before collection to ensure that the intended processing activities will be lawful under POPIA. Conducting such an assessment prior to collection is integral to establishing a lawful basis for processing from the outset, as all handling of health and sex life information must remain lawful throughout the processing lifecycle, from collection and use to deletion and destruction.

POPIA establishes, as a starting point, a prohibition on processing health and sex life information unless a justification exists. One general exception is where the data subject has granted consent for such processing. It is important to note that consent is specifically defined under POPIA as an informed, voluntary expression of will. Importantly, consent must be specific and cannot be overly generalised. Any reliance on consent must therefore meet these definitional requirements. Ensuring compliance with these requirements is increasingly pertinent where data is used for purposes that differ from the reason for which it was initially collected.

POPIA provides additional exemptions for processing special personal information. For health information, POPIA permits processing by medical professionals, healthcare institutions or facilities, or social services, where such role players are providing healthcare services. POPIA also provides an exemption that applies to insurance companies, medical schemes, medical scheme administrators, and managed healthcare organisations in certain circumstances.

While POPIA creates these categories of exemptions, it is important to note that even where a role player falls within an exemption, this does not eliminate the obligation on a responsible party to comply with POPIA’s eight conditions for lawful processing. Any responsible party relying on an exemption must still ensure that processing activities are ultimately lawful and consistent with the standards of care contemplated under POPIA.

The use of automated means to make decisions about data subjects using their health and sex life information must also be carried out lawfully and in compliance with POPIA. A data subject cannot be subject to a decision that has legal consequences for them, or that otherwise affects them to a substantial degree, where such a decision is based solely on automated decision-making using their personal information, except in limited instances.

Notably, POPIA specifically identifies health as an example of a decision that could have legal consequences or otherwise affect a data subject substantially. This highlights the importance of assessing all data processing activities, especially in sectors like healthcare, where there is growing reliance on technology to make diagnostic or treatment-related decisions.

The Information Regulator has recognised the importance of properly regulating the processing of health and sex life information in recently published Draft Regulations relating to the processing of such data by certain responsible parties. The Information Regulator notes that the primary purpose of these Draft Regulations is to assist responsible parties in implementing POPIA correctly and to provide better transparency to data subjects regarding their information.

The scope of application of the Draft Regulations includes insurance companies, medical schemes, medical scheme administrators, managed healthcare organisations and pension funds.

The Information Regulator’s move to regulate the processing of health and sex life information more closely underscores the importance of ensuring that all such processing activities are undertaken with an increased measure of care. Organisations must therefore assess their processing activities routinely to ensure ongoing compliance with POPIA. This is particularly important as healthcare-related technologies continue to advance, creating new and innovative ways to use data in patient treatment.

Healthcare stakeholders must ensure that use of such technologies comply with POPIA’s requirements and meet the standards established under the Act.

Categories : IT in HealthcareTags :

Doctors Who Use AI Viewed Negatively by Their Peers, Study Shows

On By ModernMedia

Johns Hopkins researchers find that despite pressure on clinicians to be early adopters of AI, many face scepticism from peers for using it

Photo by Andres Siimon on Unsplash

Doctors who use artificial intelligence at work risk having their colleagues deem them less competent for it, according to a recent Johns Hopkins University study.

While generative AI holds significant promise for advancing health care, a new study finds its use in medical decision-making impacts how physicians are perceived by their colleagues. The research shows that doctors who primarily rely on generative AI for decision-making face considerable scepticism from fellow clinicians, who correlate their use of AI with a lack of clinical skill and overall competence, resulting in a diminished perceived quality of patient care.

The research included a diverse group of clinicians from a major hospital system, involving attending physicians, residents, fellows, and advanced practice providers. Results of the study were published in Nature Digital Medicine.

Stigma stunts better care

The findings may indicate a social barrier to AI adoption in health care settings, which could slow advances that might improve patient care.

“AI is already unmistakably part of medicine,” says Tinglong Dai, professor of business at the Johns Hopkins Carey Business School and co-corresponding author of the study. “What surprised us is that doctors who use it in making medical decisions can be perceived by their peers as less capable. That kind of stigma, not the technology itself, may be an obstacle to better care.”

The study, conducted by researchers at Johns Hopkins University, involved a randomised experiment where 276 practicing clinicians evaluated different scenarios: a physician using no AI, one using AI as a primary decision-making tool, and another using it for verification. The research found that as physicians were more dependent on AI, they faced an increasing “competence penalty,” meaning they were viewed more sceptically by their peers than those physicians who did not rely on AI.

“In the age of AI, human psychology remains the ultimate variable,” says Haiyang Yang, first author of the study and academic program director of the Masters of Science in Management program at the Carey Business School. “The way people perceive AI use can matter just as much as, or even more than, the performance of the technology itself.”

Skipping AI equalled more respect

According to the study, peer perception suffers for doctors who rely on AI. Framing generative AI as a “second opinion” or a verification tool partially improved negative perceptions from peers, but it did not fully eliminate them. Not using GenAI, however, resulted in the most favourable peer perceptions.

The findings align with theories that suggest perceived dependence on an external source like AI can be seen as a weakness by clinicians.

Ironically, while GenAI’s visible use can undermine a physician’s perceived clinical expertise among peers, the study also found that clinicians still recognise AI as a beneficial tool for enhancing precision in clinical assessment. The research showed that clinicians still generally acknowledge the value of GenAI for improving the accuracy of clinical assessments, and they view institutionally customized GenAI as even more useful.

The collaborative nature of the study led to thoughtful suggestions for GenAI implementation in health care settings, which are crucial to balance innovation with maintaining professional trust and physician reputation, the researchers note.

“Physicians place a high value on clinical expertise, and as AI becomes part of the future of medicine, it’s important to recognise its potential to complement – not replace – clinical judgment, ultimately strengthening decision making and improving patient care,” said Risa Wolf, co-corresponding author of the research and associate professor of pediatric endocrinology at Johns Hopkins School of Medicine with a joint appointment at the Carey Business School.

Source: Johns Hopkins University

Categories : Cancer IT in HealthcareTags :

Altron HealthTech Set to Pilot South Africa’s First Oncology Companion App

On By ModernMedia

ThriveLink to connect patients, doctors, caregivers, and medical schemes in a seamless digital platform

The last thing someone dealing with a life-threatening disease wants is the pain of endless administrative paperwork and confusion that arises when aspects of their care are not easily coordinated. Altron HealthTech is set to pilot a solution designed to minimise these burdens by integrating various aspects of care management into one solution.   

The company announced today that it will soon begin piloting ThriveLink, South Africa’s first platform to connect patients, doctors, caregivers, and medical schemes in one integrated digital space. The oncology companion app is designed to help cancer patients flourish during a trying time by providing seamless care coordination, access to key information and educational content and removal of administrative obstacles. 

“We’ve built this tool with the ultimate goal of making life easier for cancer patients to be empowered throughout managing their treatment journey,” says Altron HealthTech MD Leslie Moodley. “They’ll receive appointment tracking, medication reminders, and secure communication with their care team – all customised for their unique treatment plan in one digital space – so they can focus on what matters most: their health and wellbeing.” 

Addressing a growing crisis

The development team was inspired to create ThriveLink after frontline agents logged an alarming increase in cancer diagnoses. Cancer cases in South Africa are projected to nearly double from 62 000 in 2019 to 121 000 nationally by 2030 based on data compiled by the SA Journal of Oncology, driven by an aging population and increased lifestyle risks. 

“We have insight into anonymised and aggregated data, and were shocked at the increase in cancer volumes,” says Moodley. “We realised there was value in developing a tool that could span the entire healthcare value chain and all the various touchpoints, to solve for a very real issue. This insight sparked a critical question: how can we make it easier for oncologists, our key stakeholders, to focus on what matters most – patient care? 

ThriveLink brings together data from specialists, medical aids, pharmacies, and other relevant sources to coordinate care to connect healthcare providers. Beyond appointment tracking and medication reminders, the app offers educational content, emotional support tools, and secure communication channels. 

“The solution enables these data points to collaborate in a technical sense to coordinate care,” explains Moodley. “Our response was to build a technology-driven platform that not only streamlines authorisations and treatment protocols but also enables real-time interoperability. This empowers oncologists to coordinate care more efficiently, track treatment pathways, and adapt plans based on patient-specific outcomes. Patients won’t have to worry about burdensome details and will get reminded when it’s time to take their medication or schedule a follow-up.” 

Built on medical expertise and security

The app serves as the vital link in a complex ecosystem, ensuring secure information flow, informed decision-making, and trust at every stage.  

Altron HealthTech consulted widely with oncologists, patients, and other medical professionals before beginning development. A base application was rolled out to specialists about a year ago, and feedback from that pilot informed the expanded platform now ready for patient testing. 

The app has been built on secure, cloud-based software-as-a-service architecture in compliance with the Protection of Personal Information Act and all relevant regulatory requirements. Patients must provide informed consent before signing up. 

Beyond supporting patients directly, ThriveLink is designed to help control healthcare costs. Cancer is among the most expensive therapeutic burdens, with the Cancer Alliance having predicted that this disease will cost the public sector an additional R50 billion between 2020 and 2030. 

“By streamlining processes and integrating claims, authorisations, and clinical data, we remove duplication and costs from the system,” says Moodley. “This can indirectly help keep medical aid premiums down, benefiting all medical scheme patients.” 

Altron HealthTech is in early-stage discussions with medical aid schemes interested in integrating the app into their mobile solutions. 

Categories : IT in Healthcare Obstetrics & GynaecologyTags :

Virtual Antenatal Care Linked to Poorer Pregnancy Outcomes

On By ModernMedia
Source: Pixabay CC0

Women who receive more virtual antenatal care during their second or third trimesters could experience poorer pregnancy outcomes, including higher risks of preterm birth, Caesarean sections and neonatal intensive care unit admissions, a new study suggests.

Increased virtual antenatal care in later pregnancy was also found to be associated with lower rates of early skin-to-skin contact with the newborn and fewer instances of breastfeeding as the first feed.

Led by King’s College London and published in the American Journal of Obstetrics & Gynecology, the study looked at associations between virtual antenatal care and pregnancy outcomes in more than 34 000 pregnancies from a diverse, South London population, from periods before and during the COVID-19 pandemic.

Women were split into four groups, according to the proportion of virtual antenatal care appointments received during their pregnancy – low and stable virtual antenatal care throughout pregnancy, high first trimester virtual antenatal care, high second trimester virtual antenatal care, and high third trimester virtual antenatal care.

Pregnancy and birth outcome data were obtained from hospital records via the Early Life Cross-Linkage in Research, Born in South London (eLIXIR-BiSL) platform, funded by the UKRI Medical Research Council (MRC).

Analyses of the data revealed that, compared with those who received a low and stable proportion of virtual antenatal care throughout their pregnancy:

  • Women who received a high proportion of virtual antenatal care in their second trimester experienced more premature births (before 37 weeks), labour inductions, breech presentation, and bleeding after birth; and
  • Women who received a high proportion of virtual antenatal care in their third trimester had more premature births (before 37 weeks), elective or emergency Caesarean sections, and neonatal intensive care unit admissions; as well as lower rates of third- or fourth-degree vaginal tears, early skin-to-skin contact with the newborn and fewer instances of breastfeeding as the first feed.

During the COVID-19 pandemic, the use of virtual antenatal care increased, to limit face-to-face contact and prevent spread of the SARS-CoV-2 virus. While research has looked at the experiences of women and healthcare providers receiving and delivering virtual care, fewer studies have focused on the impact of virtual antenatal care on pregnancy outcomes.

Our work adds an important perspective to the growing evidence base on virtual antenatal care, suggesting that the timing of its use during pregnancy may influence pregnancy outcomes.

Dr Katie Dalrymple, Lecturer at King’s and first author of the study

The findings build on an earlier study by the team, which found that virtual maternity care during the COVID-19 pandemic was linked to higher NHS costs – with each 1% increase in virtual antenatal care associated with a £7 increase in maternity costs to the NHS.

In addition to the cost implications of virtual care, the findings from the new study suggest that virtual antenatal care could come with increased risks to mother and baby. The authors conclude that careful consideration may be needed to minimise these risks before using virtual antenatal care in future health system shocks or to replace face-to-face care.

Our study findings suggest the need for careful integration of virtual care in maternity services, to minimise potential risks.

Professor Laura Magee, Professor of Women’s Health at King’s and co-senior author of the paper

Source: King’s College London

Categories : IT in Healthcare NeurologyTags :

Human Instruction with AI Guidance Gives the Best Results in Neurosurgical Training

On By ModernMedia

Study has implications beyond medical education, suggesting other fields could benefit from AI-enhanced training

Artificial intelligence (AI) is becoming a powerful new tool in training and education, including in the field of neurosurgery. Yet a new study suggests that AI tutoring provides better results when paired with human instruction.

Researchers at the Neurosurgical Simulation and Artificial Intelligence Learning Centre at The Neuro (Montreal Neurological Institute-Hospital) of McGill University are studying how AI and virtual reality (VR) can improve the training and performance of brain surgeons. They simulate brain surgeries using VR, monitor students’ performance using AI and provide continuous verbal feedback on how students can improve performance and prevent errors. Previous research has shown that an intelligent tutoring system powered by AI developed at the Centre outperformed expert human teachers, but these instructors were not provided with trainee AI performance data.

In their most recent study, published in JAMA Surgery, the researchers recruited 87 medical students from four Quebec medical schools and divided them into three groups: one trained with AI-only verbal feedback, one with expert instructor feedback, and one with expert feedback informed by real-time AI performance data. The team recorded the students’ performance, including how well and how quickly their surgical skills improved while undergoing the different types of training.

They found that students receiving AI-augmented, personalised feedback from a human instructor outperformed both other groups in surgical performance and skill transfer. This group also demonstrated significantly better risk management for bleeding and tissue injury – two critical measures of surgical expertise. The study suggests that while intelligent tutoring systems can provide standardised, data-driven assessments, the integration of human expertise enhances engagement and ensures that feedback is contextualised and adaptive.

“Our findings underscore the importance of human input in AI-driven surgical education,” said lead study author Bianca Giglio. “When expert instructors used AI performance data to deliver tailored, real-time feedback, trainees learned faster and transferred their skills more effectively.”

While this study was specific to neurosurgical training, its findings could carry over to other professions where students must acquire highly technical and complex skills in high-pressure environments.

“AI is not replacing educators – it’s empowering them,” added senior author Dr Rolando Del Maestro, a neurosurgeon and current Director of the Centre. “By merging AI’s analytical power with the critical guidance of experienced instructors, we are moving closer to creating the ‘Intelligent Operating Room’ of the future capable of assessing and training learners while minimising errors during human surgical procedures.”

Source: McGill University

Categories : Expert Opinion IT in HealthcareTags :

Doctors’ Human Touch Still Needed in the AI Healthcare Revolution

On By ModernMedia

AI-based medicine will revolutionise care including for Alzheimer’s and diabetes, predicts a technology expert, but it must be accessible to all patients

AI image created with Gencraft

Healing with Artificial Intelligence, written by technology expert Daniele Caligiore, uses the latest science research to highlight key innovations assisted by AI such as diagnostic imaging and surgical robots.

From exoskeletons that help spinal injury patients walk to algorithms that can predict the onset of dementia years in advance, Caligiore explores what he describes as a ‘revolution’ that will change healthcare forever.

Economically, the market for AI in healthcare is experiencing rapid growth, with forecasts predicting an increase in value from around USD 11 billion in 2021 to nearly USD 188 billion by 2030, reflecting an annual growth rate of 37%. AI is already being used in some countries, for example to search through genetic data for disease markers, or to assist with scheduling and other administrative tasks – and this trend is set to continue.

However, the author caveats his predictions of progress by warning these technologies may widen existing inequality. Caligiore suggests that AI-based medicine must be available to all people, regardless of where they live or how much they earn, and that people from low-income nations must not be excluded from cutting-edge care which wealthier nations can access.

Other challenges posed by the advancement of AI in healthcare includes who takes responsibility for treatment decisions, especially when a procedure goes wrong. This is a particular challenge given widespread concerns around explainable AI, as many advanced AI systems operate as black boxes, making decisions through complex processes that even their creators cannot fully understand or explain.

Caligiore says AI should support doctors and patients, not replace doctors who, says the author, have a ‘unique ability to offer empathy, understanding, and emotional support’.

“AI should be viewed as a tool, not a colleague, and it should always be seen as a support, never a replacement,” writes Caligiore.

“It is important to find the right balance in using AI tools, both for doctors and patients. Patients can use AI to learn more about their health, such as what diseases may be associated with their symptoms or what lifestyle changes may help prevent illness. However, this does not mean AI should replace doctors.”

Despite his warnings, Caligiore is largely optimistic about the impact of AI in healthcare: “Like a microscope detecting damaged cells or a map highlighting brain activity during specific tasks, AI can uncover valuable insights that might go unnoticed, aiding in more accurate and personalized diagnoses and treatments,” he says.

In any case, Caligiore predicts the healthcare landscape will look ‘dramatically different’ in a few years, with technology acting as a ‘magnifying glass for medicine’ to enable doctors to observe the human body with greater precision and detail.

Examples of where AI will make profound impacts in healthcare include, regenerative medicine, where gene and stem cell therapies repair damaged cells and organs. Spinal cord injury patients are among those who could benefit.

AI may also provide personalised therapies, suggesting treatments tailored to specific individuals often based on their unique genetic profile. Studies are being conducted into targeting different tremor types in Parkinson’s and breast cancer subtypes

The convergence of regenerative medicine, genetically modified organisms (GMOs), and AI is the next frontier in medicine, Caligiore suggests. Genetically modified organisms (GMOs), living organisms whose genetic material has been altered through genetic engineering techniques, have already paved the way for personalised gene therapies.

Blending real and virtual worlds may also prove useful to healthcare, for example the ‘metaverse’ – group therapy where patients participate with an avatar, or ‘digital twins’ – AI simulations of a patient’s body and brain on a computer so doctors can identify underlying causes of disease and simulate the effects of various therapies for specific patients to help doctors make more informed decisions.

These advances and others will reshape the doctor-patient relationship, according to Healing with Artificial Intelligence, but the author suggests the key is for patients and clinicians to keep a critical mindset about AI.

Caligiore warns that role of physicians will evolve as AI becomes more integrated into healthcare but the need for human interactions will remain ‘central to patient care’.

“While healthcare professionals must develop technical skills to use AI tools, they should also nurture and enhance qualities that AI cannot replicate – such as soft skills and emotional intelligence. These human traits are essential for introducing an emotional component into work environments,” he explains.

Source: Taylor & Francis Group

Categories : IT in HealthcareTags :

New Research Finds Surprises in ChatGPT’s Diagnosis of Medical Symptoms

On By ModernMedia

The popular large language model performs better than expected but still has some knowledge gaps – and hallucinations

When people worry that they’re getting sick, they are increasingly turning to generative artificial intelligence like ChatGPT for a diagnosis. But how accurate are the answers that AI gives out?

Research recently published in the journal iScience puts ChatGPT and its large language models to the test, with a few surprising conclusions.

Ahmed Abdeen Hamed – a research fellow for the Thomas J. Watson College of Engineering and Applied Science’s School of Systems Science and Industrial Engineering at Binghamton University – led the study, with collaborators from AGH University of Krakow, Poland; Howard University; and the University of Vermont.

As part of Professor Luis M. Rocha’s Complex Adaptive Systems and Computational Intelligence Lab, Hamed developed a machine-learning algorithm last year that he calls xFakeSci. It can detect up to 94% of bogus scientific papers — nearly twice as successfully as more common data-mining techniques. He sees this new research as the next step to verify the biomedical generative capabilities of large language models.

“People talk to ChatGPT all the time these days, and they say: ‘I have these symptoms. Do I have cancer? Do I have cardiac arrest? Should I be getting treatment?’” Hamed said. “It can be a very dangerous business, so we wanted to see what would happen if we asked these questions, what sort of answers we got and how these answers could be verified from the biomedical literature.”

The researchers tested ChatGPT for disease terms and three types of associations: drug names, genetics and symptoms. The AI showed high accuracy in identifying disease terms (88–97%), drug names (90–91%) and genetic information (88–98%). Hamed admitted he thought it would be “at most 25% accuracy.”

“The exciting result was ChatGPT said cancer is a disease, hypertension is a disease, fever is a symptom, Remdesivir is a drug and BRCA is a gene related to breast cancer,” he said. “Incredible, absolutely incredible!”

Symptom identification, however, scored lower (49–61%), and the reason may be how the large language models are trained. Doctors and researchers use biomedical ontologies to define and organise terms and relationships for consistent data representation and knowledge-sharing, but users enter more informal descriptions.

“ChatGPT uses more of a friendly and social language, because it’s supposed to be communicating with average people. In medical literature, people use proper names,” Hamed said. “The LLM is apparently trying to simplify the definition of these symptoms, because there is a lot of traffic asking such questions, so it started to minimize the formalities of medical language to appeal to those users.”

One puzzling result stood out. The National Institutes of Health maintains a database called GenBank, which gives an accession number to every identified DNA sequence. It’s usually a combination of letters and numbers. For example, the designation for the Breast Cancer 1 gene (BRCA1) is NM_007294.4.

When asked for these numbers as part of the genetic information testing, ChatGPT just made them up – a phenomenon known as “hallucinating.” Hamed sees this as a major failing amid so many other positive results.

“Maybe there is an opportunity here that we can start introducing these biomedical ontologies to the LLMs to provide much higher accuracy, get rid of all the hallucinations and make these tools into something amazing,” he said.

Hamed’s interest in LLMs began in 2023, when he discovered ChatGPT and heard about the issues regarding fact-checking. His goal is to expose the flaws so data scientists can adjust the models as needed and make them better.

“If I am analysing knowledge, I want to make sure that I remove anything that may seem fishy before I build my theories and make something that is not accurate,” he said.

Source: Binghamton University

Categories : IT in Healthcare Lab Tests and ImagingTags :

New AI–based Test Detects Early Signs of Osteoporosis from X-ray Images

On By ModernMedia
Photo by Cottonbro on Pexels

Investigators have developed an artificial intelligence-assisted diagnostic system that can estimate bone mineral density in both the lumbar spine and the femur of the upper leg, based on X-ray images. The advance is described in a study published in the Journal of Orthopaedic Research.

A total of 1454 X-ray images were analysed using the scientists’ system. Performance rates for the lumbar and femur of patients with bone density loss, or osteopenia, were 86.4% and 84.1%, respectively, in terms of sensitivity. The respective specificities were 80.4% and 76.3%. (Sensitivity reflected the ability of the test to correctly identify people with osteopenia, whereas specificity reflected its ability to correctly identify those without osteopenia). The test also had high sensitivity and specificity for categorising patients with and without osteoporosis.

“Bone mineral density measurement is essential for screening and diagnosing osteoporosis, but limited access to diagnostic equipment means that millions of people worldwide may remain undiagnosed,” said corresponding author Toru Moro, MD, PhD, of the University of Tokyo. “This AI system has the potential to transform routine clinical X-rays into a powerful tool for opportunistic screening, enabling earlier, broader, and more efficient detection of osteoporosis.”

Source: Wiley