Low-dose CT chest scans could help detect pneumonia in at-risk patients while exposing them to only small amounts of radiation, a new study has found. The research, published in Radiology: Cardiothoracic Imaging, shows that ultra-low-dose scans can effectively detect pneumonia in patients with compromised immune systems, enabling doctors to treat the infection before it becomes life-threatening. According to the researchers, these scans expose patients to just 2% of the radiation dose used in a standard CT scan.

"This study paves the way for safer, AI-driven imaging that reduces radiation exposure while preserving diagnostic accuracy,” lead researcher Dr Maximiliano Klug, a radiologist with the Sheba Medical Center in Ramat Gan, Israel, said in a news release. He added that CT scans are the gold standard for detecting pneumonia but there are concerns regarding the risk posed by repeated exposure to radiation. There is a solution- ultra-low-dose CT scan. However, the problem is that these scans can be grainy and hard to read, researchers said.

Study Gives Solution To This

To overcome that, Klug's team developed an AI program that could help "de-noise" low-dose scans, making them sharper and easier to read. Between September 2020 and December 2022, 54 patients with compromised immune systems who had fevers underwent a pair of chest CT scans -- a normal dose scan and an ultra-low-dose scan. The AI program cleaned up the low-dose scan, and then both sets of images were given to a pair of radiologists for assessment. Radiologists had 100% accuracy in detecting pneumonia and other lung problems with the AI-cleaned low-dose scans, but 91% to 98% accuracy in examining the scans that hadn’t been improved through AI, results show.

"This pilot study identified infection with a fraction of the radiation dose," Klug said. "This approach could drive larger studies and ultimately reshape clinical guidelines, making denoised ultra-low dose CT the new standard for young immunocompromised patients.

How Can You Detect Pneumonia?

Pneumonia is a lung infection that causes the air sacs in the lungs to fill with fluid or pus and can be caused by bacteria, viruses, or fungi. The symptoms can range from milk to severe, which includes:

Coughing with or without cough

Fever

Chills

Trouble breathing

Chest pain, especially when breathing deeply or coughing

Sweating or chills

Rapid heart rate

Loss of appetite

Bluish skin, lips, and nails

Confusion.

How to detect Pneumonia in coughing newborns and toddlers?

Pneumonia can severely affect newborns and young children as their lungs are comparatively more sensitive. As per Dr Goyal, young children can cough for various reasons including seasonal infections and tonsillitis, which is very common in this age group. But if they look visibly irritable and have poor sleep patterns, then parents must reach out to an expert. "I am not saying that parents must visit a hospital but any local paediatrician would be able to detect pneumonia in your kid.

Artificial intelligence has steadily been becoming a bigger part of the healthcare sector. One of the biggest examples is ChatGPT.

Open AI recently begun rolling out Health in ChatGPT to eligible users in the United States, allowing people to securely connect medical records, Apple Health data, and other supported health sources directly to ChatGPT.

The feature aims to help users in understanding their lab reports better, document their medical history, prepare for doctor visits, and gauge complex medical information.

While it promises convenience and personalised health insights, it has also sparked concerns about privacy, data security, and how much trust people should place in AI for healthcare decisions.

What Is ChatGPT Health?

It is currently available on the web and iOS for eligible Free, Go, Plus, and Pro users in the US, with the rollout happening gradually. 

Once connected, users can ask questions such as:

• What has changed between my latest and previous blood tests?

• Can you explain my cholesterol report in simple language?

• How are my sleep and exercise affecting my overall health?

• What questions should I ask my doctor during my next appointment?

Instead of uploading reports every time, ChatGPT can use connected health information, with the user’s permission, to provide more personalized explanations. 

Also read: AIIMS Doctor Issues Warning After Patient Follows ChatGPT Advice, Suffers Internal Bleeding

OpenAI Emphasises Privacy

According to the company, “Health is designed to support; not replace, medical care and is not intended for final diagnosis or treatment. For urgent symptoms or emergencies, seek immediate professional help.” 

The company also states, “Conversations in Health are not used to train our foundation models.” 

Users can disconnect connected accounts whenever they choose. OpenAI says synced data from disconnected sources is deleted from its systems within 30 days, although information already included in conversation history remains unless users delete those chats. 

Pros And Cons Of ChatGPT Health

How Can It Help?

Makes Medical Reports Easier To Comprehend

Medical records often contain technical terminology that patients struggle to interpret.

AI can translate complicated reports into simpler language that laymen can understand.

Saves Time Before Doctor Visits

Patients can review previous reports, organise symptoms, and prepare questions before appointments, making doctor visits more productive.

Maintains Medical History

People often have information spread across hospital portals, physical files, wearable devices, and fitness apps.

ChatGPT can combine these sources to identify patterns over time, like changes in sleep, physical activity, or important bio markers. 

Supports Better Health Tracking

Rather than searching through multiple reports manually, users can quickly compare test results or check long-term changes with simple prompts.

Also read: Man Falls Ill After Seeking ChatGPT Advice on Cutting Salt

Potential Downsides

Despite the advantages, experts caution against relying too heavily on AI for healthcare.

Privacy Concerns

Although OpenAI has introduced additional security measures, users are still sharing extremely sensitive personal health information with an AI platform.

Some AI privacy experts argue that any cloud-based storage of medical information is risky.

AI Can Still Make Mistakes

ChatGPT can explain information but may misunderstand context, overlook rare conditions, or generate inaccurate answers.

OpenAI clearly states that the feature must not replace professional medical advice, diagnosis, or treatment. 

Risk of Delaying Medical Care

The launch comes amid renewed scrutiny over AI-generated medical advice.

A recently filed lawsuit alleges that a user delayed seeking emergency treatment after relying on ChatGPT’s health guidance.

While the allegations are still part of ongoing legal proceedings, the case has intensified discussions about the limitations of AI in healthcare. 

Should You Give AI Access To Your Medical Records?

If your goal is to better understand your lab reports, organise medical information, or prepare for doctor consultations, ChatGPT Health could become a useful health assistant.

However, if you are expecting AI to diagnose illnesses, decide treatments, or replace healthcare professionals, experts say that would be a mistake.

Healthcare decisions often depend on physical examinations, medical history, imaging, and clinical judgment, areas where AI cannot replace qualified doctors.

The human brain may begin undergoing important immune changes much earlier than previously thought. A recent study found that these changes could help explain why the risk of dementia increases with age.

Researchers found that the hippocampus, the brain region responsible for learning and memory, experiences a major shift in its immune cells during the 40s and 50s.

The findings suggest that this change could lead to chronic inflammation associated with Alzheimer's disease and other forms of dementia in the future .

What Did The Study Find?

The study, conducted by scientists from the University of California San Diego, the New York Genome Center, and the University of California Irvine, analysed postmortem hippocampal tissue from 40 neurologically healthy adults aged between 20 and 95 years.

Researchers examined more than 1.2 million brain cells, discovering that around midlife, the brain's immune environment changes dramatically.

One of the biggest findings involved microglia, the brain's resident immune cells. While these cells normally protect the brain by clearing debris, fighting infections, and supporting neurons, researchers observed that they gradually shift into a more inflammatory state during middle age.

This altered immune environment resembles patterns commonly seen in neurodegenerative diseases like dementia.

Also read: World Brain Day: Climate Change Is Not Just Harming The Planet, It Could Also Be Affecting Your Brain

Link Between Ageing & Dementia

Scientists have long known that aging is the strongest risk factor for dementia. However, exactly how normal aging causes diseases like Alzheimer's has remained vague.

The new findings suggest that the process may begin decades before symptoms like memory loss appear.

Instead of viewing aging as a slow, continuous process, the study indicates that the brain may pass through a distinct biological transition during midlife.

Once this immune environment changes, it may make the brain more vulnerable to inflammation and cognitive decline.

Richard J. Hodes, MD, Director of the National Institute on Aging (NIA), said, "Aging is the single largest risk factor for dementia, but our understanding of how it drives disease is still incomplete. This previously hidden microglial shift, now uncovered by innovations in technology and thinking, may be an important clue to help us complete the puzzle."

The researchers also believe these immune changes may not simply be a consequence of aging but could actively influence how the brain ages.

Also read: Can One Partner's Dementia Raise the Other's Risk? New Study Suggests An Interesting Link

Could This Contribute In Dementia Treatments & Management?

Although the findings do not mean that everyone in their 40s or 50s will develop dementia, they provide researchers with a potential window for clinical intervention.

If scientists can identify or modify these immune changes before significant brain damage occurs, future therapies may be able to delay or even prevent neurodegenerative diseases.

Experts continue to recommend:

• Keeping blood pressure, blood sugar, and cholesterol under control.
• Exercising regularly.
• Getting adequate sleep.
• Eating a balanced, brain-healthy diet.
• Staying mentally and socially active.
• Managing hearing loss and avoiding smoking.

These lifestyle measures are already known to reduce several risk factors associated with dementia, and the new findings suggest they may be particularly important during the brain's midlife transition.

A six-year-old girl in China died after receiving an experimental gene-editing treatment for a rare neurodevelopmental disorder. The incident sparked scrutiny on ethics and safety of cutting-edge gene therapies, particularly when they involve children and individualized treatments.

The case, uncovered through a joint investigation by Science and Retraction Watch, sparked international concern as the child's death was never disclosed publicly, despite related preclinical research later being published in Nature.

What Happened?

According to the investigation, the six-year-old girl, identified by the pseudonym "Mei," had Snijders Blok-Campeau syndrome, a rare genetic condition. It caused symptoms like mild intellectual disability and developmental delays.

Her parents reportedly paid more than $800,000 to support development of a personalized ("n=1") gene-editing therapy designed specifically for their daughter's mutation.

In March 2025, she received a spinal infusion containing trillions of adeno-associated viruses (AAVs) carrying a CRISPR-based gene editor intended to correct the faulty gene in brain cells. Within days, she developed a severe immune reaction and died approximately one week after treatment.

An internal hospital review concluded that the most likely cause of death was an overwhelming immune response triggered by the viral delivery system rather than the gene-editing mechanism itself.

The controversy extends well beyond the patient's death. According to Science investigation:

• The child's death was not publicly disclosed.
• The child's treatment was omitted from a later Nature publication describing related preclinical work.
• Animal studies had reportedly shown warning signs, including severe liver and kidney toxicity at high doses.
• The girl's parents may not have been fully informed about the potential side effects of the therapy.

Following the investigation, local Chinese health authorities reportedly fined the hospital involved for faulty execution of the clinical research. Several experts have called for an independent review of the published research and greater transparency around experimental human gene-editing trials.

Also read: Ebola Outbreak in DR Congo Nears 3,000 Cases, 1,300 Deaths as UN Warns Virus Is 'Spreading Like Wildfire'

Bioethicists and gene therapy researchers say the case underscores the need for complete transparency whenever experimental therapies are tested on humans.

Hank Greely, director of the Center for Law and the Biosciences at Stanford University, told Science that the trial "shouldn't have gone to trial".

Pediatrician Marcelo Bellusci, who participates in gene therapy trials, told El País, "In this type of trial there can be serious side effects, but families are always informed about them. This team skipped the current rules."

About Gene-Editing Therapies

Gene-editing technologies such as CRISPR offer the possibility of correcting genetic mutations caused by diseases instead of simply treating symptoms. Several CRISPR-based therapies have shown remarkable success in inherited blood disorders, including sickle cell disease.

However, experts stress that therapies targeting the brain remain considerably more complex because they often require large viral doses and carry greater risks of immune complications.

As more individualized gene-editing therapies move toward human testing, experts argue that every serious adverse event must be reported promptly to regulators, journals, clinicians, and patients to ensure future treatments become both safer and more trustworthy.