While MRI is the imaging technique of choice for assessing a range of cancers, including prostate cancer, in the UK alone, the number of radiologists is predicted to reach 40% by 2027, indicating the need for a streamlined, simplified and accurate means of cancer diagnosis, Med Tech reports.

A clinical study shows that radiologists can miss 12% of significant prostate cancer cases using MRI. The data, presented at the European Society of Urogenital Radiology (ESUR) in September 2023, shows that Pi could help reduce undetected cancers by up to 6% while reducing avoidable biopsies by up to 43%.

According to Med Tech, with the help of artificial intelligence, Pi analyzes MRIs and is fully integrated into the radiologist’s workflow, targeting key issues related to variability, radiologist timing and diagnostic accuracy in prostate cancer. Specifically, Pi is designed to be used by radiologists to evaluate and report prostate MRI studies by automatically creating 3D segmentations, volumes and risk scores. Its results can be used to save radiologists time and to support biopsy and treatment decisions.

“We desperately need to cut waiting times, detect cancer early, and provide patients and clinicians with all the information needed to for optimum treatment. With this CE mark, the results of our investment in AI and clinical research over the last four years can now be used by doctors to provide the best possible diagnosis for men with suspected prostate cancer”, explained co-founder and chief medical officer Professor Evis Sala, chair of radiology at the Università Cattolica del Sacro Cuore and director of the Advanced Radiology Centre at the Policlinico Universitario A. Gemelli, IRCCS.

Lucida Medical will demonstrate Pi at the Radiological Society of North America (RSNA) 2023 Annual Meeting.

What is Pi?
Prostate Intelligence (Pi) is an AI and machine learning based software system designed to help radiologists detect and report the presence of prostate cancer lesions from MR scans (MRI).

Technology plays a crucial role in the development of personalized medicine, and biomedical and healthcare startups are at the forefront of innovation and will change the future of medicine.

The one-size-fits-all approach is often ineffective in healthcare. Personalised medicine aims to provide a more tailored approach. This is also why a number of startups are developing health technologies that take into account patients’ unique genetic, biological and environmental factors.

Avatar Medical (France)
Avatar Medical creates real-time ED patient avatars to help clinicians and surgeons visualise medical images.The company’s VR solution helps surgeons better prepare their procedures by interacting with an ultra-fluid, photo-realistic VR representation of their patient’s medical images.

The solution is beneficial for understanding complex biological structures to help avoid mastectomies, shorten the operating time for reconstructive surgeries and inform hardware selection. Use cases include vascular, orthopedic, and head and neck surgery.

Biomesight
Biomesight is an AI-driven wellness analytics platform primarily focusing on the gut microbiome.

Over the past two decades, researchers are exploring the gut microbiota for potential gut microbe–host interactions, including the impact on metabolism, immune, and neuroendocrine responses.

The Biomesight test provides a snapshot of the gut microbiome utilizing 16S rRNA sequencing technology. This is then interpreted against recommended ranges for a subset of key bacteria (Probiotics, Commensals and Pathogens) and combined with other metrics to offer personalized recommendations for diet, prebiotic supplements and lifestyle adjustments.

Strike Pharma (Sweden)
Founded in 2020, Strike Pharma has developed proprietary Adaptable Drug Affinity Conjugate (ADAC) technology to take precision medicine to a new level. This makes it possible to create truly individualized immunotherapeutic treatments based on the genetic profile of a patient’s tumor.

Personalized genetics can increase therapeutic efficacy, and reduce dosage levels, thereby minimizing the risk of side effects.

Using a pre-trained AI model from NVIDIA, the startup Evozyne has created two proteins with significant potential in healthcare and clean energy.

A joint paper describes the process and the biological building blocks it created. One aims to cure a congenital disease, while the other is designed to consume carbon dioxide to reduce the effects of global warming.

“It’s really encouraging that even in this first round, the AI model has created synthetic proteins that are as good as naturally occurring ones. This tells us that it has properly mastered the rules of nature’s design”,

says Andrew Ferguson, co-founder of Evozyne.

A transformative model of artificial intelligence
Evozyne uses NVIDIA’s implementation of ProtT5, a transformational model that is part of NVIDIA BioNeMo, a software framework and service for creating AI models for healthcare.

“BioNeMo really gave us everything we needed to support training the model and then running tasks with the model very inexpensively – we could generate millions of sequences in just a few seconds.”

says Ferguson, a molecular engineer working at the intersection of chemistry and machine learning.

The model is the basis for Evovyne’s process, called ProT-VAE. It’s a workflow that combines BioNeMo with a variational autoencoder that acts as a filter.

The model studies the ways nature
Like a student reading a book, NVIDIA’s transformational model reads amino acid sequences across millions of proteins. Using the same techniques that neural networks use to understand text, it learns how nature assembles these powerful building blocks of biology.

The model then predicts how to assemble new proteins suitable for the functions Evozyne wants to address.

According to some research, there are more than a half-million people with disabilities who never leave their homes. That is causing them debilitating isolation which exacerbates physical and emotional issues. The lack of reliable and safe transportation is often one of the reasons for whether a person gets the regular medical care they need or not. This adds up to an enormous societal cost in human suffering and healthcare costs.

There are more than 60 million adult Americans who live with a disability. Too many struggles to get to their doctors, to get to work and training, and to fully participate in their community.

Community service providers who provide programming for adults with disabilities fill the gaps left by public paratransit, family and friend networks. There are lots of urban centres that have a variety of agencies that provide transportation services along with training and social programs.

As technology is developing and social problems become more serious, there are technologies that are helping and changing people’s lives. Such tech is the new tailored software-as-a-service (SaaS) which is designed to support transportation that can result in better, less costly services. It will not only reduce costs but will also create a system that is more easily accessible to users and managed by staff.

Many of us know that technology is slowly replacing most of the traditional ways of managing a certain problem. That’s why adding a software solution can be one with an array of benefits, even though it can be intimidating financial consideration for a funds-strapped organization. If nowadays we rely on all these traditional methods for coordinating transportation such as hand-written schedules and phone calls, we can be sure that human mistakes will be really expensive, too. So, by adopting a digital solution, we can ensure that we will achieve efficiency and accuracy, beneficial to everyone who provides or uses these transportation programs.

When it comes to the patient’s safety and privacy issues, we need to know that they are at the forefront of technological solutions for care. In particular, scheduling systems for patient populations must be focused on providing safe and timely transport for the individual. There are solutions that are in a HIPAA-compliant, cloud-hosted platform. They can be integrated with providers’ existing infrastructure, in which providers can change, track and coordinate schedules.

There is no doubt that people with disabilities deserve to be heard when we talk about their care and mobility. Using a software solution that is geared specifically to serve a diverse population with different abilities gives users autonomy and freedom to manage their own schedules.

Are there other features that are ideal for a modern scheduling system?

Well, of course. It includes options for tailored individual transport preferences, trackable on- and off-boarding managed schedule changes and the ability to devise optimal routing under real-time circumstances.

Another solution that is created with providing compassionate care that is top of mind will also feature driver check-ins at pick-up, arrival, and drop-off back home. This will provide assurance both to the staff and the families who feel safe and comfortable when knowing that patients are secure and in good hands.

Tej Anand, a professor at The University of Texas at Austin’s McCombs School of Business, said that the U.S. has the most complicated health system in the world, with high administrative and patient costs, and that there’s a lack of incentive to keep people healthy.

Betty Jo Rocchio, senior vice president and system chief nursing officer at Mercy, agreed, adding that patients struggle to navigate the system.

Wilson To, the head of worldwide healthcare, life sciences and genomic at Amazon Web Services, raised the issue of unstructured data. He said:

“We see a lot of unstructured data that’s out there. To what degree are they looking for new solutions to put some structure into that, to make it more usable or find ways of removing these data silos that exist within these organizations in order to make it more interoperable, for example?”

Payers have the most data that goes unshared across the spectrum, Rocchio said, and stakeholders aren’t working together on a standardized data set. She said:

“It’s not helping us across the continuum of care, but it’s siloing us on purpose. We’re getting exactly what we designed.”

The fragmented data ecosystems within healthcare have produced what Anand called “the three Rs of efficiency.”

Why Interoperability Is Important to Healthcare Delivery

“Data is so important to the workflow of medicine,” said Dr. Mujeeb Basit, associate chief medical informatics officer and assistant professor at the UT Southwestern Medical Center in Dallas. “We’ve spent so much time creating complex solutions to solve downstream data problems, when in reality, we should be spending our time fixing the upstream data access.”

He highlighted the difficulties of creating quality metrics for every department in his organization and said improvements in institutionwide foundational systems are needed.

Healthcare organizations must design strategies to increase data liquidity and elevate meaningful information sharing among stakeholders seamlessly inside and outside of hospital walls, Basit added.

During a separate spotlight keynote session, Cerner President Donald Trigg spoke on the strategy behind excellent care delivery inside and outside the hospital.

Dynamic forces of change, accelerated by the COVID-19 pandemic, are rapidly reorganizing the healthcare industry and models of care delivery, Trigg said, so that leaders are focused on not only solving today’s challenges those of the next five years and beyond.

Moving Toward Equity in Healthcare

Blue Cross Blue Shield Association President and CEO Kim Keck outlined the importance of data sharing to addressing health inequities. She said:

“We can create lasting change. As an industry, we should commit to sharing insights that provide transparency to the prevalence and magnitude of health disparities.”

Data collection for information on race, ethnicity and language needs to be improved and standardized across the board, she added. Building trust among patients and committing to patient data privacy will also be an ongoing effort.

The scientists were light on details about how they acquired the Moderna sample. “For this work, RNAs were obtained as discards from the small portions of vaccine doses that remained in vials after immunization; such portions would have been required to be otherwise discarded and were analyzed under FDA authorization for research use,” they said.

According to Stanford scientists Andrew Fire and Massa Shoura, this isn’t technically “reverse-engineering” a vaccine. “We didn’t reverse engineer the vaccine. We posted the putative sequence of two synthetic RNA molecules that have become sufficiently prevalent in the general environment of medicine and human biology in 2021,” they told Motherboard in an email. “As the vaccine has been rolling out, these sequences have begun to show up in many different investigational and diagnostic studies. Knowing these sequences and having the ability to differentiate them from other RNAs in analyzing future biomedical data sets is of great utility.”

“This project did not waste vaccine material or reduce in any way the number of vaccine doses available to the public,” they told Motherboard. “None of the residual ‘dregs’ that we used for this work came from vaccines that could have been otherwise administered. Think of the thin layer of milk coating a carton that had been fully used and emptied yesterday and sitting on the kitchen counter—if we sequenced that, we’d get a full picture of the cow genome even though the small quantity of milk would be of no use.”

The scientists told Motherboard they felt that their peers working at Moderna/NIH and BioNTech/Pfizer had done the world a great service and that releasing the RNA sequences will help continue to benefit humanity. “While anyone interested could data-mine and filter these sequences out later, there is a substantial economy of scale and educational value in having the sequences available ASAP and in not having to guess where they have come from,” they said.