AI is reshaping medicine now with personalized cancer treatments

Researchers are now turning to artificial intelligence to customize cancer therapies and find fresh purposes for old medicines. Other computer systems can scan microscopic images or spot tiny biological signals that humans might overlook entirely. Some of these tools have already helped patients, while others sit in clinical trials or research labs. We must stay careful about telling the difference between exciting science and treatments you can actually receive today.

Still, what scientists are accomplishing would have seemed impossible just a few years ago. Here is where AI is reshaping medicine right now and what you need to know before trusting it with your health. Join our upcoming CyberGuy LIVE class called Get Better Healthcare With AI. In this free live online event, Kurt "CyberGuy" Knutsson will show five practical ways AI can help you take a more active role in your healthcare journey.

You will learn how to organize your own health history and remember important appointment details without stress. The session covers how to understand complicated medical information, research prescriptions safely, and prepare smart questions for your next doctor's visit. No technical experience is needed at all. Register for free now at CyberGuyLive.com.

One of the biggest recent developments comes from Moderna and Merck. On Aug. 19, these companies announced positive topline results from a Phase 3 melanoma trial. The study tested intismeran autogene, also known as V940 or mRNA-4157, alongside Keytruda. The trial enrolled 1,137 people with high-risk melanoma that surgeons had completely removed previously.

The combination met its primary endpoint for recurrence-free survival successfully. It also met a key secondary endpoint measuring distant metastasis-free survival as well. Merck and Moderna stated this was the first positive Phase 3 readout for an individualized neoantigen therapy ever. It was also the first positive Phase 3 result for an mRNA-based cancer therapy overall.

The basic idea behind this sounds complicated, yet it is fascinating to watch unfold. Researchers start with a sample of a patient's tumor tissue directly. They analyze its unique mutations and use an algorithm to select targets that may help the immune system recognize the cancer cells. The resulting individualized therapy can encode up to 34 neoantigens in total.

Moderna has also said the V940 program uses integrated AI algorithms during the development process itself. The company then creates an mRNA treatment based on the selected targets they found earlier. You may have seen this approach called a personalized cancer vaccine before now. Moderna and Merck currently describe intismeran as an individualized neoantigen therapy officially.

The goal is to train the immune system to recognize characteristics unique to that patient's specific cancer type. There is plenty of reason for excitement regarding these findings, but there is also an important limitation to note carefully. Merck and Moderna have announced only topline results from the Phase 3 trial so far in this case.

The companies plan to present the full findings at an international medical meeting soon. They will share them with regulators after that presentation occurs. The study continues to track overall survival rates for enrolled patients right now. Earlier results offer additional context regarding efficacy levels. In a smaller Phase 2b study with longer follow-up, intismeran plus Keytruda reduced the risk of recurrence or death by 49% compared with Keytruda alone.

It also reduced the risk of distant metastasis or death by 59% in that earlier data set. Those earlier results came from a much smaller patient group than the current study shows. That makes the larger Phase 3 trial an important step forward for everyone involved. Still, intismeran remains investigational at this time strictly speaking.

The FDA has not approved intismeran as a melanoma treatment yet today. Developing a new medicine can take years of work and patience. Another group of researchers is asking a different question entirely right now. What if a useful treatment already exists for your condition? Dr. David Fajgenbaum co-founded the nonprofit Every Cure to pursue that possibility actively.

About 18,000 recognized diseases exist around the globe according to Every Cure's 2025 annual report. Only roughly 4,000 have FDA-approved medications available today. That leaves an enormous number of conditions with very limited treatment options.

Every Cure uses AI to scan biomedical knowledge and look for connections between existing medicines and other diseases they might potentially treat. The organization says its system can generate tens of millions of predictions in less than a day. Researchers then examine the most promising possibilities.

The federal Advanced Research Projects Agency for Health, or ARPA-H, is backing this approach through a project called MATRIX. MATRIX uses machine learning and artificial intelligence to predict which FDA-approved drugs could potentially treat other diseases. Researchers then validate promising candidates through laboratory or clinical work. AI does not prove that a drug will work for another illness. Instead, it can help researchers decide where to look next. That could dramatically narrow an otherwise enormous search.

Fajgenbaum has seen firsthand what finding a new use for an existing drug can mean. Kaila Mabus developed multicentric Castleman disease at 13 and became severely ill despite chemotherapy. In 2020, her doctors tried ruxolitinib, a drug already used for certain blood disorders but not FDA-approved for Castleman disease. She began improving within months and was declared in remission in January 2021. AI did not identify her treatment, but her case shows why Every Cure wants to use AI to uncover promising drug-disease connections much faster and on a far larger scale.

At Columbia University Fertility Center, artificial intelligence has taken on a very different challenge. Researchers developed the Sperm Tracking and Recovery system, known as STAR. It combines high-speed imaging with an AI detection model and microfluidics.

STAR was designed for patients with azoospermia or cryptozoospermia, conditions where sperm may appear absent or exist in extremely small numbers. The system examines a semen sample far more thoroughly than a person could reasonably do by hand. STAR can capture and process about 1.1 million images every hour. Its AI model examines frames for possible sperm cells.

When the system confirms one, a microfluidic mechanism isolates the cell. Doctors may then use the recovered sperm for fertility treatment or freeze it for later use. In one validation sample, embryologists searched for two days without finding sperm. STAR found 44 sperm in about an hour. That is exactly the type of repetitive search where AI can shine. A human eye can get tired. A computer can keep examining frame after frame.

STAR has already helped produce a baby. This technology has moved beyond a research demonstration. Columbia says STAR achieved its first reported pregnancy in March 2025. The couple involved had spent nearly two decades trying to conceive. STAR found and recovered sperm that conventional examination of the same sample had missed. The pregnancy later resulted in a healthy delivery.

That does not mean STAR will work for everyone. Columbia currently reports that sperm are found in about 28% of patients who previously received an azoospermia diagnosis. The center says about 20% of mature eggs fertilize with STAR-recovered sperm. Around 18% of those fertilized eggs develop into good-quality embryos for transfer or freezing.

Those rates are lower than typical IVF or ICSI. The patients using STAR often face especially difficult fertility problems, which helps explain the difference. Even so, the technology shows how finding one tiny biological clue can completely change the options available to a patient.

Researchers at the University of Hong Kong are exploring another possibility.

Their new AI-based tool, known as CardiOmicScore, sifts through molecular clues hidden inside blood samples to spot trouble before it starts. The team built this system using massive datasets from the UK Biobank, which allowed them to examine nearly 3,000 circulating proteins and over a hundred metabolites alongside genomic records. By applying deep learning techniques, they estimated future risk for six specific cardiovascular conditions including coronary artery disease, stroke, heart failure, atrial fibrillation, peripheral artery disease, and venous thromboembolism. When layered on top of standard clinical information, this approach sharpened risk predictions significantly. In some cases, the system could flag elevated danger levels as much as 15 years before symptoms even appeared.

Imagine what that foresight could eventually mean for patient care. Doctors might receive a warning while there is still ample time to intervene rather than discovering disease only after symptoms develop. However, it is important to remember that CardiOmicScore remains a research development right now. You cannot walk into your doctor's office today and request it as a routine screening test because the technology has not yet crossed over into standard practice.

Scientists at UCLA are pursuing another path toward personalized cancer treatment by creating tiny laboratory-grown replicas of patient tumors called organoids. Researchers expose these biological models to different drugs and monitor the results closely under controlled conditions. Their platform combines 3D bioprinting with advanced imaging and artificial intelligence to handle the vast amount of data generated as organoids respond to therapy. The system can track thousands of individual organoids simultaneously, allowing researchers to examine how different parts of a tumor react to various medications. This capability becomes valuable because cancer behaves differently from one patient to another, and even cells within the same person's tumor might respond in unique ways. Eventually, this technology could help identify therapies that better fit an individual patient's specific cancer profile, though UCLA continues to develop and validate the platform for now.

The possibilities for AI in medicine extend far beyond blood samples and microscopes into something as personal as your own voice. Researchers are studying what computers can learn from the way we speak, with a Perspective published Sept. 4 in npj Digital Medicine examining voice biomarkers for ALS and Parkinson's disease. Neurodegenerative diseases cause measurable changes in speech patterns that AI could potentially analyze to help monitor disease progression over time. For ALS specifically, authors see particular potential in tracking changes that affect both speech and swallowing abilities. However, this field remains early in its development stages.

At the time of publication, no speech or voice-derived endpoint for ALS or Parkinson's disease had received qualification from the FDA or European Medicines Agency yet. One ALS speech analytics platform has received FDA Breakthrough Device designation which can help speed regulatory review but does not amount to full FDA marketing authorization. Researchers see real potential here despite these hurdles because clinical proof still has more catching up to do before widespread adoption becomes a reality.

You may encounter AI in your healthcare without ever opening an AI chatbot or realizing it is happening at all. A laboratory could use it while analyzing a tumor, and a fertility clinic might use it to search for something the human eye missed during examination. Researchers can also use AI behind the scenes to find treatments worth investigating further before they reach patients. The key question for you remains how much evidence supports the specific technology being used in your care today. A university research project sits at a very different stage from a medical device that has gone through clinical testing and regulatory review, so understanding those distinctions matters. You should also understand how much human oversight remains involved before fully trusting any automated system with your health decisions.

Artificial intelligence can assist doctors in processing vast amounts of data and spotting patterns humans might miss. Yet your healthcare decisions must always rest on qualified medical judgment tailored to your specific situation. Asking a few targeted questions becomes essential when AI enters your care team. You deserve to know exactly how these tools affect you.

First, ask what the AI actually does. Does it analyze information for a doctor? Or does it flag something for additional review? The phrase "AI-powered" covers a wide range of technology. Ask for a simple explanation instead.

Second, find out who reviews the result. A human specialist or laboratory professional must check the findings before anyone makes a decision. Human review becomes especially important when a result could affect treatment or diagnosis.

Third, check the technology's regulatory status. Ask whether the FDA has cleared or approved the device when authorization applies. Also find out what type of research supports it. Early research can show promise while still leaving important questions unanswered.

Fourth, ask what happens to your health data. Medical AI may rely on sensitive information. Ask how your provider stores that data and who can access it. You can also ask whether your information may be used to improve or train an AI system. For more details on transparency around artificial intelligence in healthcare, see the CyberGuy guide on patient disclosure. This article provides general information and does not replace advice from your healthcare professional.

What I find so interesting is how AI helps doctors and researchers see things incredibly difficult to locate otherwise. A single system can search over a million microscope images in an hour looking for just one sperm cell. Another sifts through huge amounts of medical research to find a possible new use for an existing drug. Researchers are even developing cancer treatments around unique mutations inside one patient's tumor. That is pretty remarkable.

But we must be careful not to let excitement move faster than the science. The melanoma Phase 3 results look encouraging, yet we still need to see complete data. Several other technologies in this article remain experimental or available only in limited settings. For me, that is where things get really interesting. AI may help doctors find answers faster and uncover possibilities they might otherwise miss.

What I want to see next is how often those discoveries translate into treatments that actually make people healthier and improve their lives. If AI uncovered a treatment your doctor had never considered, how much evidence would you need before feeling comfortable trying it? Let us know by writing to us at CyberGuy.com.

Sign up for my FREE CyberGuy Report. Get the best tech tips, urgent security alerts and exclusive deals delivered straight to your inbox. For simple ways to spot scams early and stay protected, visit CyberGuy.com – trusted by millions who watch CyberGuy on TV daily. Plus, you'll get instant access to my Ultimate Scam Survival Guide free when you join.