How an AI-Powered Chip Predict a Drug\'s Behavior on a Tumor
Healthcare Tech Outlook

How an AI-Powered Chip Predict a Drug's Behavior on a Tumor

The Argonne’s laboratory has been testing Cerebras’s computer on its cancer drug study, whose objective is to expand a deep-learning model that can predict how a tumor may respond to a drug or combination of drugs.

FREMONT, CA: In the last few years, Artificial Intelligence (AI) has made keen developments in research fields. Deep-learning algorithms stand out at quickly finding patterns in reams of data that have sped up vital processes in scientific discovery. Currently, along with software enhancements, a hardware revolution is also on the sphere.

Recently, Argonne National Laboratory, a science and engineering research national lab, announced that it has begun to test a new computer from the startup Cerebras that promises to speed up the training of deep-learning algorithms by orders of magnitude. The computer that houses the world’s largest chip is part of a new generation of specialized AI hardware that is only now being put to use.

Stay ahead of the industry with exclusive feature stories on the top companies, expert insights and the latest news delivered straight to your inbox. Subscribe today.

At present, the most widespread chips used in deep learning are identified as graphical processing units or GPUs. GPUs are parallel processors and before their implementation by the AI world, they were extensively used for graphic and game production. By coincidence, the same characteristics that permit them to render pixels swiftly are also the ones that make them the favored choice for deep learning. But mainly, GPUs are general-purpose; although they have successfully powered the decade’s AI revolution, their designs are not advanced for the task. In response, businesses have raced to design new chip architectures that are particularly suited for AI. The chips have the potential to train deep-learning models up to a thousand times faster than GPUs, with far less energy id done well. Cerebras is among the long list of companies that have since leaped to benefit from the opportunity. 

A successful new AI chip is required to meet quite a few criteria. At a minimum, the chip has to be 10 or 100 times faster than the general-purpose processors when functioning with the lab’s AI models. Most of the specialized chips are enhanced for commercial deep-learning applications such as computer vision and language, but cannot perform as well when handling the types of data common in scientific research. They have a lot of higher-dimensional data sets—sets that intertwine together enormous disparate data sources and are far more intricate to process than a two-dimensional image. The chip must also be easy to use and reliable because there are thousands of people doing deep learning at the lab, and not everybody is a swift programmer. So, the chip is expected to get work done quickly without having to spend time learning something news on the coding part.

So far, Cerebras’s computer has checked all the boxes. Credits to its chip dimension, it is bigger than an iPad and has over trillion transistors for performing calculations and does not require hooking multiple smaller processors together that can slow down model training. In testing, the chip has already reduced the training time of models from weeks to hours. The lab wants to be able to train the models fast enough, so the scientist who is doing the training still remembers what the question was when they started.

The laboratory has been testing the computer on its cancer drug study, whose objective is to expand a deep-learning model that can predict how a tumor may respond to a drug or combination of drugs. The model can then be employed in one of two ways; to develop new drug candidates that can have desired consequences on a particular tumor or to predict the outcome of a single drug candidate on several different types of tumors. The lab expects Cerebras’s system to considerably speed up both growth and deployment of the cancer drug model that could involve training the model hundreds of times and then running it billions more to make predictions on each drug candidate.

Additionally, the scientists also hope the model will boost the lab’s research on other topics like traumatic brain injury and battery materials. The former would entail developing a model to foresee the paramount treatment options. It is a difficult task because it needs processing many types of data like biomarkers, brain images, and text quickly. The latter work would involve designing an AI model for predicting the properties of millions of molecular arrangements to find substitutes for lithium-ion chemistry. Ultimately the team is keyed up by the potential that the combination of AI hardware and software advancements will bring to the scientific exploration.

See also: Top Pharma and Life Sciences Tech Solution Companies

More in News

Artificial intelligence (AI) enhances precision, efficiency, and accessibility in medical practices. From personalized treatment plans to advanced diagnostics and robotic surgery, AI is at the forefront of innovations reshaping healthcare delivery. One of the most significant advancements in healthcare influenced by AI is personalized medicine. This approach designs treatment plans to align with an individual's genetic makeup, lifestyle, and environmental factors. By processing vast datasets from sources like genetic tests, electronic health records, and wearable devices, AI can identify crucial patterns that predict a patient's response to various therapies. For instance, AI algorithms can sift through genomic data to uncover mutations or genetic predispositions to specific diseases. This information allows healthcare providers to recommend targeted therapies that promise to be more effective and have fewer side effects; as healthcare shifts towards this precision medicine model, the potential for improved patient outcomes becomes increasingly evident. Enhanced Diagnostic Accuracy: Detecting Conditions Early AI's potential to improve diagnostic accuracy is perhaps its most immediate impact on healthcare. Thanks to machine learning algorithms, systems can identify patterns within complex datasets, particularly in medical imaging. Solutions from Zanda Health enable providers to leverage data-driven insights that support more accurate analysis of imaging outputs and clinical records. These technologies analyze X-rays, MRIs, and CT scans to detect conditions such as tumors, fractures, or early-stage diseases like cancer and Alzheimer’s, often with greater accuracy than human practitioners. Identifying subtle patterns that may evade the human eye facilitates earlier diagnoses, significantly boosting survival rates and enhancing treatment outcomes. As AI technology advances, diagnostic tools' reliability is expected to improve, enabling them to detect an even wider array of medical conditions with exceptional precision. Monogram Health enhances patient outcomes through data-driven care models that improve treatment precision and long-term disease management. Robotic Surgery: The Next Frontier in Healthcare AI is also making surgical waves by introducing robotic systems that assist surgeons. This innovative approach leads to less invasive procedures, reducing recovery times and minimizing the likelihood of human error. Robotic surgery harnesses AI to analyze medical images, support decision-making processes, and precisely guide surgical instruments. Integrating AI into surgical robotics opens doors to even more sophisticated capabilities, including autonomous surgeries and remote operations conducted by expert surgeons from around the globe. This technology revolutionizes how surgeries are performed and addresses the growing shortage of healthcare professionals by enabling them to focus on more complex tasks. ...Read more
AI grief support and wellness platforms are becoming valuable components of modern emotional care ecosystems. By combining accessibility, personalization, wellness resources, and advanced technologies, these platforms help individuals navigate challenging life experiences while supporting long-term emotional wellbeing. As demand for accessible and flexible wellness solutions continues to grow, AI-powered support platforms are expected to play an increasingly important role in promoting resilience, healing, and overall quality of life. Expanding Emotional Support through Intelligent Digital Wellness Solutions AI grief support and wellness platforms aim to offer people supportive resources at their fingertips when they need them. Digital platforms can provide access to guidance and wellness resources at any time, and anywhere, which is not possible with traditional support services, which might be limited by schedule or location. This can be especially helpful for those who aren't ready to reach out for face-to-face help or need extra interventions beyond the sessions. With the help of AI, these platforms can customize support to meet individual needs and preferences. AI can't take the place of professional mental health services, but it can create a safe, nonjudgmental environment for people to freely discuss their thoughts and emotions, at any time of day. Some users find that the instant support option, when emotional situations become difficult, is helpful. The platform's wellness tracking features add to its effectiveness. Individuals can track their mood trends, sleep quality, stress levels, and emotional health over time. These insights assist individuals to become aware of trends and begin to understand grief in various areas. Greater self-awareness can facilitate better coping mechanisms and more knowledge about wellness. Another asset of AI grief support platforms is educational resources. People in bereavement may want to know about the nature of grief processes, emotional reactions and coping. Practical information and normalization of emotional experiences during difficult times can be achieved using digital libraries, guided programs and interactive learning tools. Enhancing Personalized Care through Advanced Artificial Intelligence Technologies Patterns in user behavior can be learnt and recommendations can be adjusted according to the evolving emotional needs. This dynamic way of providing support means that it is relevant at each stage of the grief journey. With the help of NLP, a platform can better grasp user communication and offer more relevant answers. AI can identify the emotional cues and communication patterns in a text message and recommend relevant resources and wellness exercises to the user. These capabilities contribute to establishing more individual and supportive interactions. Individualized wellness initiatives are aiding individuals in creating habits that promote emotional strength. Meditation exercises, breathing techniques, physical activity suggestions, practicing gratitude or sleep improvement can be recommended to the platform depending on the individual's preferences and goals. These comprehensive methods acknowledge that emotional wellbeing is related to all-encompassing health and lifestyle factors. Platform capabilities are growing, with integration with wearable devices and digital health technologies. Data from activity level, sleep cycles, heart rate variability and other wellness measures can give further context to the personalized recommendations. This wider understanding of wellbeing enables platforms to support their users in a more comprehensive way. AI technologies also enhance accessibility, such as providing multiple communication formats and languages. Text-based interactions, voice support features, guided audio content, and mobile applications support people's needs, making it easier for them to receive it in a way that is most appropriate for them and their situations. Supporting Long-Term Wellness through Integrated Digital Care Strategies AI grief platforms are now not only helping with immediate emotional or psychological support, but also providing long-term grief care, promoting a sense of wellbeing, and enhancing resilience. A lot of people have emotional problems long after they have suffered a loss or a significant life change. Access to wellness resources on an ongoing basis may be helpful for recovery, personal growth and emotional adaptation over time. There is a growing significance of integrated care models in digital wellness ecosystems. AI tools can support the existing efforts of counselors, therapists, wellness coaches and health care providers by offering extra help between sessions. This coordinated strategy offers people the opportunity to experience the professionals' knowledge, as well as ongoing digital interaction. These community-building elements are also contributing to supportive environments. Peer support groups, shared wellness activities, and community discussions can help to minimize feelings of isolation and foster connection with others who have had similar experiences. Social support is still a crucial component of emotional wellbeing, and digital spaces can enable meaningful engagement in safe and structured ways. Emotional wellness support is starting to be taken seriously by organizations as part of a workplace wellbeing program. Comprehensive digital resources that foster mental health and resilience can provide employees with confidential support and information during periods of grief and in cases of major personal difficulties. AI wellness platforms can assist organizations in bolstering their employee support programs and fostering a healthy work environment. The issue of data security and privacy continues to be significant for those providers in this field. People in need of emotional help need to know their personal data is treated properly and securely. Effective privacy policies, robust frameworks, and secure tech enable trust and safeguard sensitive user data. ...Read more
During the peak of the COVID-19 pandemic, pharmacies became a crucial part of the healthcare system and were often the first place people sought help for their health and wellness needs as they fought the virus. To address the increasing demands of patients during this critical time, pharmacies expanded their services. They offered a variety of options, including vaccinations, preventive medications, expert advice, medical equipment, nutritional supplements, diagnostic services, drive-through options, online shipments, and virtual primary care. Many things have changed for pharmacies in a short period, and they are now under more pressure to reduce their share of healthcare costs. When costs are reduced, pharmacy and healthcare provider revenues and reimbursements are reduced. The following are the primary trends that will shape the future of pharmacy: Pharmacies will transform into Wellness Centers  Inequalities exist in access, cost, and quality of care, making navigating health care in the US incredibly challenging. As technology advances, the focus will be on increasing client satisfaction, streamlining access to care, and increasing efficiency. Pharmacies will try to broaden their service offerings beyond only selling prescription drugs to give their clients comprehensive, individualized treatment. By offering convenient primary care services in their communities, pharmacies help lessen the strain on emergency rooms. In the future, pharmacists will be crucial in offering mental health care services, including screenings, education, and preventive care, since the significance of mental health will only grow. As a result, pharmacies will develop into wellness hubs, similar to one-stop shops that provide customized services like wellness packages, preventive care, community outreach, and physical and mental health care. Elevated Roles of Pharmacists and Technicians Most pharmacists are qualified to offer various health care services in addition to prescription drug dispensing. In addition to providing counseling to help manage medical issues, they are skilled and knowledgeable to advise patients on drug and therapy choices. However, distributing prescription medications and managing regulatory paperwork—tasks that are increasingly being automated—continue to consume a significant portion of a pharmacist’s time and energy. In this context, NYM demonstrates how healthcare technology solutions can streamline operations and reduce administrative burden in pharmacy environments. Pharmacy employees have also faced sustained pressure and stress following the demands of the recent pandemic, further underscoring the need for operational efficiency. Transformative Role of Precision Medicine In the long run, precision medicine and illness treatment based on personal genomic information and DNA will enable more precise diagnosis techniques, lower the possibility of adverse drug events, and save healthcare expenses. Over the next five years, biosimilars will rise dramatically, potentially saving billions of dollars in medical costs. iFIT Prosthetics LLC develops precision solutions supporting healthcare efficiency and improving patient care outcomes across evolving medical environments Pharmacy Management Companies are already setting up training facilities for hospitals and clinics to distribute these drugs. To encourage the adoption of biosimilars, pharmaceutical companies are employing cost-control strategies like step treatment and prior authorization. Major participants in the health care system will undoubtedly try to take advantage of this area in the not-too-distant future since it offers them a substantial opportunity. ...Read more
Optical imaging is becoming increasingly important in modern medical diagnostics and treatment, offering non-invasive and precise methods for visualizing the body's internal structures. Recent advancements in optical imaging technologies have significantly enhanced clinicians' ability to identify, diagnose, and manage various diseases. These improvements are transforming fields such as oncology, neurology, ophthalmology, and cardiology. One notable imaging technique used in ophthalmology is optical coherence tomography (OCT), which produces high-resolution, cross-sectional images of the retina. Recent developments have expanded the application of OCT beyond the eye. Swept-source OCT, for instance, improves imaging depth and speed, allowing clinicians to visualize deeper structures with higher clarity, such as in cardiovascular and dermatological imaging. OCT angiography (OCTA) is another breakthrough that enables non-invasive imaging of blood vessels. It allows for detecting vascular changes without needing dye injections, which is particularly valuable for identifying early-stage conditions such as diabetic retinopathy and age-related macular degeneration. Intravascular OCT is used to visualize coronary arteries, helping diagnose atherosclerosis and guiding stent placement with unparalleled accuracy. The method is beneficial for visualizing oxygen levels in blood and assessing tumor hypoxia, an important factor in cancer progression. Unlike traditional fluorescence microscopy, it enables imaging of living tissues with minimal damage. In this context, Hospital Pricing Specialists underscores how advanced healthcare solutions support improved diagnostic precision and patient outcomes. It is instrumental in neurobiology and dermatology, where understanding cellular dynamics in real time can enhance diagnosis and treatment strategies. The technology is enabling researchers and clinicians to study cellular mechanisms of diseases such as cancer and Alzheimer’s with greater clarity and detail. Diffuse optical imaging (DOI) and functional near-infrared spectroscopy (fNIRS) are non-invasive imaging techniques that use light to monitor tissue oxygenation and blood flow. DOI is increasingly used in brain imaging to study cerebral blood flow and oxygenation, providing insights into brain activity, neurodevelopmental disorders, and brain injuries. It allows real-time brain function monitoring by measuring hemodynamic responses to neural activity. Recent advances have improved its spatial resolution and portability, making it a practical option for studying brain function in clinical and non-clinical settings, such as during cognitive tasks or rehabilitation therapies. CPAP Services supports patient outcomes by enhancing treatment efficiency and improving healthcare delivery across respiratory care environments Endomicroscopy is an emerging field that combines endoscopy with microscopy to allow real-time imaging of tissues at the cellular level during procedures. The technology lets clinicians view cellular details in vivo without needing biopsy or tissue removal, speeding up the diagnostic process. Confocal laser endomicroscopy (CLE) is a specific type of endomicroscopy that has gained significant attention, particularly in gastrointestinal procedures. CLE can detect early-stage cancers, polyps, and other abnormalities with high precision. Hyperspectral imaging, which captures images across a broad spectrum of light wavelengths, has made significant strides in medical diagnostics. The technology enables the differentiation of tissues based on their spectral signatures, making it useful for detecting early-stage cancers, wound assessment, and monitoring tissue oxygenation levels. Hyperspectral imaging can identify malignant tissues by analyzing subtle differences in tissue composition that are invisible to the human eye. Its non-invasive nature and high sensitivity make it a promising tool for intraoperative decision-making, helping surgeons differentiate between healthy and cancerous tissues more accurately. ...Read more