Cancer
Patients support AI as radiologist backup in screening mammography
The results of a large survey from a diverse patient population revealed cautious support for artificial intelligence (AI) implementation in screening mammography, according to a new study.
While the diagnostic accuracy of AI systems has drastically improved in recent years, there is still a lack of widespread adoption and acceptance of this technology for a variety of reasons, such as concerns with data privacy, algorithmic bias or even level of knowledge of AI.
One opinion that is frequently overlooked in the conversation surrounding the growth of AI in radiology is that of the patient.
“Patient perspectives are crucial because successful AI implementation in medical imaging depends on trust and acceptance from those we aim to serve,” said study author Basak Dogan, clinical professor of radiology and director of breast imaging research at the University of Texas Southwestern Medical Center in Dallas.
“If patients are hesitant or skeptical about AI’s role in their care, this could impact screening adherence and, consequently, overall health care outcomes.”
To gain a better understanding of patient opinions and concerns regarding the use of AI in screening mammography, Dr. Dogan and colleagues developed a 29-question survey to be offered to all patients who attended their institution for a breast cancer screening mammogram. The optional survey was available for a period of seven months in 2023.
All survey questions were closed-ended and assessed the participants’ knowledge and perceptions of AI. The survey obtained demographic information in addition to clinical information, which uncovered a respondent’s history with breast cancer, such as whether they had any abnormal mammograms in the past or if they or a close family member has ever had breast cancer.
Of the 518 patients who completed the survey, most indicated support for the use of AI alongside a radiologist’s review, with 71 per cent of respondents preferring AI to be used as a second reader. This was despite concerns about loss of personal interaction with the radiologist, data privacy, lack of transparency and bias. Less than 5 per cent were comfortable with AI alone interpreting their screening mammogram.
Because of its large and diverse patient population, the survey uncovered a variety of demographic factors that influence patient perceptions. Respondents with more than a college degree or a higher self-reported knowledge of AI were two times more likely to accept AI involvement in their screening mammogram.
Of note, Hispanic and non-Hispanic Black respondents reported significantly higher concerns about AI bias and data privacy, which most likely resulted in a lower acceptance of AI among these patient groups.
“These results suggest that demographic factors play a complex role in shaping patient trust and perceptions of AI in breast imaging,” Dr. Dogan added.
Familial and personal medical history also impacted patient attitudes toward AI.
Regardless of whether an abnormality was detected by AI or a radiologist, patients who had a close relative diagnosed with breast cancer were more likely to request additional reviews. However, these patients exhibited a high degree of trust in both AI and radiologist reviews when the mammogram came back as normal.
In contrast, patients with a history of an abnormal mammogram were more likely to pursue diagnostic follow-up if AI and radiologist reviews conflicted. This was especially the case if it was AI that flagged an abnormality.
“This highlights how personal medical history influences trust in AI and radiologists differently, emphasising the need for personalised AI integration strategies in mammographic screening,” Dr. Dogan said.
The researchers noted that it is important to continue engaging with patients to understand their evolving views of AI technology in health care, as the technology continues to advance.
“Our study shows that trust in AI is highly individualised, influenced by factors such as prior medical experiences, education and racial background,” Dr. Dogan said.
“Incorporating patient perspectives into AI implementation strategies ensures that these technologies improve and not hinder patient care, fostering trust and adherence to imaging reports and recommendations.”
A combination of THC and CBD derived from cannabis was shown to kill ovarian cancer cells without harming healthy cells in laboratory studies.
The findings suggest that drugs made from these compounds could be developed to fight ovarian cancer in future, though researchers caution that much more work is needed before results can be translated into patient treatments.
The research was led by Dr Siyao Tong of Khon Kaen University.
The researcher said: “Ovarian cancer remains one of the deadliest gynaecological malignancies, characterised by late diagnosis, high recurrence rates, and limited effective treatment options.
“Our goal is to find alternative drugs that can improve efficacy and potentially reduce toxicity, ultimately bringing new hope to patients facing this challenging disease.”
Scientists tested the effects of CBD (cannabidiol, which is not psychoactive) and THC (delta-9-tetrahydrocannabinol, which is) on two ovarian cancer cell lines.
One line was sensitive to platinum-derived drugs and one was resistant.
The team found that cells from both cancer lines treated with CBD or THC formed fewer and smaller colonies.
While both compounds limited cancer cell growth, combining them produced particularly strong results.
A combination of the two was very successful at killing cancer cells.
“Notably, the inhibitory effect was most pronounced when CBD and THC were used in a 1:1 ratio,” said Tong.
Additional tests showed the compounds prevented cells from migrating, suggesting they might be able to stop ovarian cancer spreading to other parts of the body.
Both cell lines were similarly affected, indicating the compounds could work equally well for different types of ovarian cancer. The compounds also had minimal effects on healthy cells.
To explore how this worked, scientists examined cell signalling pathways. The PI3K/AKT/mTOR pathway, which regulates cell growth and survival, is overactive in ovarian cancer cells and contributes to tumour development and treatment resistance.
The CBD and THC combination appeared to restore normal regulation of the pathway.
Tong said: “Although our study is still preliminary, it lays an important foundation for future research into the potential applications of CBD and THC in ovarian cancer treatment.
“By confirming their anti-cancer activity and identifying key molecular mechanisms, our findings are expected to drive further preclinical research.
“If future studies confirm these effects, CBD-THC combination therapy may ultimately contribute to the development of new treatment strategies.”
HRT (hormone replacement therapy) may not increase breast cancer risk in women with BRCA mutations, new research suggests.
Women who inherit harmful mutations in the BRCA1 or BRCA2 genes, which help repair DNA, face elevated risks of ovarian and breast cancer.
They are often advised to have their ovaries and fallopian tubes surgically removed (bilateral salpingo-oophorectomy, removal of the ovaries and fallopian tubes) at relatively young ages to reduce ovarian cancer risk, but this brings on early menopause.
The study was led by Joanne Kotsopoulos, a scientist at the Women’s College Hospital Research and Innovation Institute and a professor at the Dalla Lana School of Public Health at the University of Toronto in Canada.
She said: “We cannot simply recommend a drastic surgery like oophorectomy for young women without offering a way for them to manage the well-established short- and long-term outcomes of surgical menopause.
“I believe we should educate patients and their health care providers on how we can safely balance the risks and benefits of MHT use to ensure longevity and improve quality of life.”
She noted there has been reluctance and misinformation regarding HRT, largely due to studies in the general population showing an association between HRT use and increased breast cancer risk.
The researchers conducted a matched prospective analysis, an observational design that pairs similar participants to mirror clinical trial conditions.
They created 676 matched pairs of women who did and did not use HRT after menopause.
Participants were matched by BRCA1 or BRCA2 status, birth year and age at menopause. The women ranged in age from 22 to 76, with an average age of 43.8.
Patients with a history of cancer, those who had received a bilateral mastectomy (removal of both breasts), and non-menopausal patients were excluded from the study.
After an average follow-up of 5.6 years, breast cancer cases were significantly lower in women who used HRT, with 87 cases in the HRT group compared with 128 cases in the non-HRT group.
Analysis by formulation showed most types of HRT were not associated with breast cancer risk.
However, two formulations were linked to decreased risk. Women who received oestrogen-only HRT were 63 per cent less likely to develop breast cancer than those who did not use HRT.
Of the 43 women who received conjugated oestrogen and bazedoxifene (a selective oestrogen receptor modulator), none developed breast cancer.
“Although based on smaller numbers, this is definitely an exciting and interesting area for future research,” Kotsopoulos said.
“Hypothetically, conjugated oestrogen and bazedoxifene could be used to mitigate breast cancer risk by avoiding progesterone, which is thought to be the breast cancer risk-associated component of MHT. Future trials will be necessary to test this hypothesis.”
There were no significant differences in results between BRCA1 and BRCA2 carriers.
“Our findings suggest that clinicians should take a personalised approach to menopause management for women with BRCA mutations who are suffering from the impact of surgical (or natural) menopause, if there are no contraindications for them,” said Kotsopoulos.
Routine mammograms could help assess cardiovascular disease risk in women, new research suggests.
The study found that both the severity of calcium in breast arteries and how it progressed on mammograms predicted future cardiovascular disease.
Researchers at Penn State College of Medicine analysed data from 10,348 women who had repeat mammograms, with an average of 4.1 years between scans.
The X-ray images can detect calcium in the breast’s arteries, a sign that blood vessels are stiffening.
As people age, calcium can build up in arteries, raising heart attack and stroke risk.
In the study, AI software assessed whether calcification was present and how severe it was.
Women with more severe calcification, and those whose calcification progressed over time, had up to two times higher risk of major events such as heart attack, stroke, heart failure and death.
Matthew Nudy is assistant professor of medicine and public health sciences at Penn State College of Medicine.
He said: “We know that women are more likely to be diagnosed at later stages of cardiovascular disease and have worse outcomes following a heart attack compared to men.
“That may be in part because the current cardiovascular risk assessment tools underestimate risk in women. We need better tools.
“In the future, assessment of breast arterial calcification may help improve our ability to predict risk and prevent cardiovascular disease.”
Vascular calcification was present in 19.4 per cent of participants at baseline.
Those who initially had no calcium but developed it on follow-up had a 41 per cent higher risk of an adverse cardiovascular event and death.
Nudy said: “This could be a way to use data that may already be available for different reason and to potentially use it to risk stratify an individual for the development of cardiovascular disease.”
-
Insight2 weeks agoCannabis compounds kill ovarian cancer without harming healthy cells, research finds
-
Opinion4 weeks agoFemtech in 2025: A year of acceleration, and what data signals for 2026
-
Insight3 weeks agoMeta removes dozens of abortion advice and queer advocacy accounts
-
News4 weeks agoRound up: First wearable detects symptoms of perimenopause, and more
-
Insight3 weeks agoSperm donor with cancer-causing gene fathered nearly 200 children across Europe
-
Mental health4 weeks agoInsomnia combined with sleep apnea associated with worse memory in older women
-
News3 weeks agoUK couples exploiting legal loophole to rank embryos based on IQ, height and health
-
Entrepreneur4 weeks agoFemtech firm launches genetic test for perimenopause