Revolutionary AI tool forecasts pancreatic cancer risk up to three years in advance
Ground-breaking research spearheaded by Harvard Medical School, in collaboration with the University of Copenhagen, VA Boston Healthcare System, Dana-Farber Cancer Institute, and the Harvard T.H. Chan School of Public Health, has developed an artificial intelligence (AI) instrument capable of identifying individuals at the greatest risk of developing pancreatic cancer up to three years before diagnosis, using solely their medical records.
The study, published in Nature Medicine on May 8, indicates that implementing AI-driven population screening could be a key strategy in detecting those at a high risk of pancreatic cancer earlier. This could, in turn, hasten the diagnosis of a condition often detected at advanced stages when treatment options are less effective, resulting in poorer outcomes. Pancreatic cancer, one of the world’s deadliest malignancies, is anticipated to increase its mortality toll.
At present, there is an absence of population-wide screening tools for pancreatic cancer. Targeted screenings are performed for individuals with certain genetic mutations or a family history that increases their risk of developing the disease. However, these screenings may overlook other cases not fitting these criteria, the researchers highlighted.
The study’s co-senior investigator, Chris Sander, a faculty member in the Department of Systems Biology at the Blavatnik Institute at HMS, underscored the significance of the AI tool. “Deciding who is at a high risk for a disease and would benefit from additional testing is one of the most challenging determinations clinicians have to make. The tests can be more invasive, more costly, and carry their own risks. An AI tool that accurately identifies those at the highest risk for pancreatic cancer and who would gain the most from additional tests could greatly enhance clinical decision-making.”
If implemented widely, this AI-driven method could expedite the detection of pancreatic cancer, lead to earlier treatment, and improve patient outcomes, possibly extending their life spans.
“AI-driven screening provides the opportunity to change the course of pancreatic cancer, a formidable disease that is exceptionally challenging to diagnose early and treat promptly,” said study co-senior investigator Søren Brunak, a professor of disease systems biology and research director at the Novo Nordisk Foundation Center for Protein Research at the University of Copenhagen.
In this novel study, the researchers trained the AI algorithm on two separate data sets, containing a total of 9 million patient records from Denmark and the United States. They instructed the AI model to identify potential signs of pancreatic cancer risk based on the data in the records.
The model could predict patients likely to develop pancreatic cancer in the future by identifying combinations of disease codes and the timing of their occurrence. Interestingly, many of the symptoms and disease codes were not directly related to or derived from the pancreas.
The researchers evaluated different versions of the AI models for their capacity to identify individuals at a heightened risk of disease development over different timescales – 6 months, one year, two years, and three years.
Overall, each iteration of the AI algorithm proved considerably more precise in predicting who would develop pancreatic cancer than current estimates of disease incidence in the general population. The researchers proposed that the model is likely as accurate in predicting disease onset as the existing genetic sequencing tests, which are generally only accessible to a small subset of patients in data sets.
Screening techniques for certain prevalent cancers, such as breast, cervix, and prostate cancer, rely on relatively straightforward and highly effective techniques, such as a mammogram, a Pap smear, and a blood test. These methods have significantly improved the outcomes for these diseases by ensuring early detection and intervention.
In contrast, pancreatic cancer poses greater challenges and costs in terms of screening and testing. Doctors predominantly focus on family history and the presence of genetic mutations. While these are crucial indicators of future risk, they often overlook many patients.
The AI tool presents a significant advantage in its potential applicability to any patient for whom health records and medical history are available, not solely those with a known family history or genetic predisposition for the disease. This is particularly important, the researchers noted, because many patients at a high risk may not be aware of their genetic predisposition or family history.
In the absence of clear indications that a person is at high risk for pancreatic cancer and without symptoms, clinicians may understandably hesitate to recommend more sophisticated and costlier testing methods such as CT scans, MRI, or endoscopic ultrasound.
When these tests are performed and suspicious lesions are detected, the patient must undergo a procedure to obtain a biopsy. Given its deep placement in the abdomen, the pancreas is difficult to reach and easy to inflame, leading to its nickname as “the angry organ.”
The researchers advocate for an AI tool that singles out those at the greatest risk for pancreatic cancer. This would ensure clinicians are testing the correct population, while also preventing others from undergoing unnecessary testing and additional procedures.
The survival rate for those diagnosed with pancreatic cancer in its early stages is about 44 percent, five years post-diagnosis. However, only 12 percent of cases are diagnosed at this stage. The survival rate decreases dramatically to 2 to 9 percent for those with tumours that have spread beyond their origin, the researchers estimated.
Chris Sander emphasised, “Despite significant advancements in surgical techniques, chemotherapy, and immunotherapy, the survival rate remains low. Therefore, besides advanced treatments, there’s a pressing need for better screening, more focused testing, and earlier diagnosis. This is where the AI-based approach serves as the initial critical step in this process.”
For the current study, the researchers created multiple versions of the AI model and trained them on the health records of 6.2 million patients from Denmark’s national health system over a 41-year span. Of these patients, 23,985 developed pancreatic cancer over time.
During the training, the algorithm identified patterns suggesting future pancreatic cancer risk based on disease trajectories. For instance, diagnoses such as gallstones, anaemia, type 2 diabetes, and other gastrointestinal-related issues pointed to a higher risk for pancreatic cancer within three years of evaluation.
Inflammation of the pancreas was a strong predictor of future pancreatic cancer within an even shorter time span of two years.
The researchers caution that none of these diagnoses on their own should be deemed indicative or causative of future pancreatic cancer. However, the pattern and sequence in which they occur over time provide clues for an AI-based surveillance model and could prompt physicians to closely monitor or test those at elevated risk.
Next, the researchers tested the best-performing algorithm on an entirely new set of patient records it had not previously seen — a U.S. Veterans Health Administration data set comprising nearly 3 million records over 21 years, including 3,864 individuals diagnosed with pancreatic cancer.
The tool’s predictive accuracy was somewhat lower on the US data set. The researchers attributed this to the shorter collection period and the different patient population profiles in the U.S. dataset compared to the Danish dataset.
When the algorithm was retrained from scratch on the U.S. dataset, its predictive accuracy improved. This, the researchers said, underscores the importance of training AI models on high quality, rich data and the necessity of access to large representative datasets of clinical records aggregated nationally and internationally.
In the absence of globally valid models, AI models should be trained on local health data to ensure their training reflects the specific characteristics of local populations.
Read More
UK’s soaring liver cancer death rate blamed on alcohol and obesity
Liver cancer deaths in the UK have seen a staggering 40% increase over the past decade, making it the fastest-growing cause of cancer-related fatalities in the country, warns the British Liver Trust. Calling attention to the alarming rise, the charity is urging immediate measures to address the “carcinogenic effects” of inexpensive alcohol and unhealthy food.
Pamela Healy, CEO of the British Liver Trust, identifies alcohol and obesity as the key drivers behind the surge in liver cancer cases and deaths. She stresses the need for government intervention to combat these issues, asserting that such action can create a healthier environment for all. Healy emphasises the urgency of addressing the accessibility and affordability of unhealthy food, often priced significantly lower than nutritious alternatives.
This call for action comes amidst delays in implementing regulations that would prohibit supermarket multi-buy deals on high-fat, high-sugar, or high-salt foods. The Association of Directors of Public Health has also urged ministers to introduce minimum unit pricing on alcohol, following Scotland’s successful implementation of a minimum price of 50p per unit in 2018.
The British Liver Trust has submitted evidence to the parliamentary health and social care committee’s inquiry into future cancer care, focusing on innovative approaches to diagnosis and treatment. In addition to advocating for earlier detection and improved access to effective therapies, the charity emphasises the importance of prevention. Liver disease, a significant risk factor for liver cancer, can be reversed through lifestyle modifications, including reduced alcohol consumption and weight loss.
The submission by the British Liver Trust emphasises the need for upstream interventions to mitigate the carcinogenic impact of an unhealthy food and beverage environment. The charity cites evidence indicating that population-wide measures regulating the affordability and accessibility of alcohol and unhealthy food are more effective in reducing disease burden and addressing health inequalities than individual behaviour change alone.
The charity calls for a comprehensive alcohol strategy that tackles promotions and affordability. It highlights the fact that alcohol is classified as a group 1 carcinogen, known to cause at least seven types of cancer. Data from Cancer Research reveals that liver cancer mortality rates per 100,000 people in the UK have risen from 6.4 in 2007-2009 to 9.3 in 2017-2019. Primary liver cancer has one of the lowest survival rates among all cancers.
The British Liver Trust emphasises the need for enhanced surveillance of high-risk groups with liver disease to enable early diagnosis and improve survival rates. Additionally, the charity advocates for increased investment in liver cancer research.
The UK government is facing mounting pressure to take more effective action to combat obesity. Danone UK and Ireland, one of the country’s major food companies, recently suggested that the government should consider taxing products high in fat, sugar, or salt to tackle the obesity crisis.
In response to the inquiry, the Department of Health and Social Care affirms its commitment to diagnosing 75% of cancers at stages 1 and 2 by 2028. The department outlines its interventions, including community health liver checks for those at high risk of cirrhosis, with a particular focus on deprived communities.
A spokesperson from the Department of Health and Social Care highlights ongoing efforts to encourage healthier food and drink choices and tackle obesity. Recognising that obesity costs the NHS approximately £6.5 billion per year and is the second leading cause of cancer, the spokesperson highlights initiatives such as calorie labelling in restaurants, cafes, and takeaways to empower individuals to make informed lifestyle choices.
The spokesperson further notes that the NHS has witnessed record numbers of cancer patients in recent years, with earlier-stage diagnoses becoming more prevalent. To support this, the government is strengthening the cancer workforce and has published the first-ever Long-Term Workforce Plan, backed by over £2.4 billion, aiming to deliver the most extensive training expansion in NHS history over the next 15 years.
Read More
New study links obesity to 18 types of cancer, including leukaemia and lymphoma
In a concerning development, a recent study has established a direct connection between excess body weight and an elevated risk of developing multiple types of cancer. While previous research had identified 13 cancers associated with overweight or obesity, this groundbreaking study expands the list to include 18 different forms of the disease. The findings highlight the urgent need for a reevaluation of the impact of overweight and obesity on cancer rates and emphasise the significance of weight management from an early age.
The study, conducted by researchers in Catalonia, Spain, examined the electronic health records of over 2.6 million individuals aged 40 or older who were initially cancer-free. Surprisingly, within a span of just nine years, more than 225,000 participants received a cancer diagnosis. The researchers meticulously analysed the data, paying close attention to individuals with a body mass index (BMI) of 25 or greater, indicative of having overweight or obesity.
Published in Nature Communications, the study’s results reveal a troubling correlation between a BMI of 25 or higher and an increased susceptibility to 18 distinct types of cancer. What is particularly noteworthy is that the risk of cancer development begins as early as 18 years old. Furthermore, individuals who were overweight during their early adulthood (between the ages of 18 and 40) faced a significantly higher risk of developing cancer. The risk further intensified for those who struggled with excess weight for extended periods and those who experienced severe obesity in their youth.
Dr. Heinz Freisling, a co-author of the study, emphasised the implications of these findings, urging a reassessment of the current estimation of the cancer burden associated with overweight and obesity. It is highly likely that the actual burden is underestimated due to these newly discovered connections.
This study adds to the growing body of evidence highlighting the long-term health risks stemming from childhood obesity, including its impact on cognitive function and brain structure. Additionally, the researchers identified several types of cancer that are now linked to excess weight, including leukaemia, non-Hodgkin lymphoma, head and neck cancers, and bladder cancer.
Previously recognised connections between excess weight and cancer include adenocarcinoma of the oesophagus, postmenopausal breast cancer, colon and rectal cancer, uterine cancer, gallbladder cancer, gastric cardia cancer, kidney cancer, liver cancer, ovarian cancer, pancreatic cancer, thyroid cancer, meningioma (a type of brain cancer), and multiple myeloma, as reported by the Centers for Disease Control and Prevention (CDC).
Dr. Panagiota Mitrou, director of research, policy, and innovation at the World Cancer Research Fund, emphasised the public health implications of this comprehensive study. The new findings establish connections between overweight/obesity and additional cancers, such as leukaemia and non-Hodgkin lymphoma. Maintaining a healthy weight throughout life, starting from early adulthood, emerges as one of the most critical preventive measures against cancer.
The study underscores the need for proactive public health measures, focusing on early prevention and weight management strategies to reduce the incidence of these cancers and promote overall well-being. By prioritising healthy weight maintenance, individuals can significantly mitigate their risk of developing various types of cancer and safeguard their long-term health.
Read More
Bariatric surgery associated with over 50% reduction in cancer risk for individuals with obesity
Bariatric surgery could considerably decrease the risk of cancers related to obesity, such as those of the breast, colon, liver, pancreas, ovaries, and thyroid, in patients with obesity.
“Bariatric surgery, which includes sleeve gastrectomy, gastric bypass, and gastric band procedures, is the principal method for significant weight loss in individuals with obesity,” stated Dr. Vibhu Chittajallu, a gastroenterology fellow at Case Western Reserve University and University Hospitals Cleveland Medical Center, during a Digestive Disease Week media briefing. He highlighted that these procedures offer benefits beyond weight loss, such as enhancements in patients’ mental and physical well-being.
Chittajallu further added, “Emerging evidence suggests that the substantial weight reduction linked with bariatric surgery may also provide a protective shield against the development of cancers associated with obesity. My team and I decided to delve deeper into this trend.”
Chittajallu and his team used TriNetX, a database involving 47 U.S. healthcare institutions and over 107 million patients, to conduct a retrospective study from 2002 to 2022. They singled out adults with a Body Mass Index (BMI) over 35 who underwent bariatric surgery, comparing them with patients with obesity who didn’t have the surgery. The study accounted for risk factors like smoking history, alcohol use, heart disease, hormone therapies, and cancer-screening tests, including 55,789 individuals in each group.
The researchers also used the International Agency for Research on Cancer to identify cancers with “sufficient” evidence of a connection to obesity. This included esophageal adenocarcinoma, multiple myeloma, and cancers of the kidney, colon, rectum, stomach, liver, gallbladder, pancreas, ovary, endometrium, breast, and thyroid.
The results revealed that after ten years, the cumulative occurrence of obesity-related cancer was 4% (n = 2,206) in the bariatric surgery group and 8.9% (n = 4,960) in the nonsurgical control group (HR = 0.482; 95% CI, 0.459-0.507).
Chittajallu pointed out that the bariatric surgery group consistently exhibited lower numbers of new cases for all types of obesity-related cancers, including those of the breast, colon, liver, pancreas, ovaries, and thyroid.
“Although more research is required to fully understand the impact of bariatric surgery on cancer risk,” Chittajallu concluded, “our findings indicate that bariatric surgery is a promising area to investigate.”
Read More
High obesity-related cancer mortality linked to easy access to fast food
Obesity has been a significant contributor to various health issues, including cancer. A recent cross-sectional study published in JAMA Oncology highlights the role of food environments in obesity-related cancer mortality. Communities with easy access to fast food were found to be 77% more likely to have high levels of obesity-related cancer mortality.
Researchers led by Dr. Malcolm Seth Bevel from the Medical College of Georgia analysed food access and cancer mortality data from over 3,000 counties in the United States. The study aimed to understand the association between food deserts (areas with limited access to grocery stores and healthy food options) and food swamps (areas with easy access to convenience stores and fast food) and obesity-related cancer mortality rates.
Using data from the U.S. Department of Agriculture Food Environment Atlas and the Centers for Disease Control and Prevention, the researchers calculated food desert and food swamp scores for each county. A higher score indicated fewer healthy food resources in the area.
The primary outcome of the study was obesity-related cancer mortality, defined as either high or low (71.8 or higher per 100,000 individuals and less than 71.8 per 100,000 individuals, respectively). The results showed that counties with high food swamp scores (easy access to fast food) were 77% more likely to have high rates of obesity-related cancer mortality.
Further analysis revealed a positive dose-response relationship between food desert scores, food swamp scores, and obesity-related cancer mortality rates. Counties with high rates of obesity-related cancer mortality also had a higher percentage of non-Hispanic Black residents, higher percentage of adults older than 65 years, higher rates of adult obesity, and higher rates of adult diabetes.
The study demonstrates the significant impact of food environments on obesity-related cancer mortality rates. Communities with easy access to fast food have a considerably higher risk of obesity-related cancer deaths. The findings emphasise the importance of promoting healthier food environments and improving access to nutritious food options in order to reduce obesity and its associated health risks, including cancer.
Read More
Bariatric surgery may reduce cancer risk in patients with obesity and type 2 diabetes
Research findings derived from a Swedish Obese Subjects (SOS) study, published in Diabetes Care, found that in people with obesity and type 2 diabetes (T2D), bariatric surgery may play a role in cancer prevention. “Durable” remission of T2D is often achieved after weight-loss surgery, further associating it with a reduced cancer risk.
The study examined long-term outcomes after bariatric surgery versus usual care in people with obesity. Researchers examined outcomes of 701 patients with obesity and T2D at baseline. A total of 393 of these patients (mean age, 48.6 years) underwent bariatric surgery while 308 patients (mean age, 50.5 years) received conventional obesity treatment. The investigators analysed cancer events, reported in the Swedish National Cancer Register, over the median follow-up of 21.3 years.
In patients treated with bariatric surgery, the incidence rate for first-time cancer during the follow-up period was 9.1 per 1,000 person-years (95% CI, 7.2–11.5). In contrast, the incidence rate for first-time cancer in patients treated with usual obesity care was 14.1 per 1,000 person-years (95% CI, 11.2–17.7). The incidence rate for first-time cancer diagnosis was significantly lower in the patients treated with bariatric surgery (adjusted hazard ratio [HR], 0.63; 95% CI, 0.44–0.89; P =.008).
Compared with the control group, bariatric surgery was associated with a significantly reduced incidence of cancer in women, (HR, 0.58; 95% CI, 0.38–0.90; P =.016). However, with bariatric surgery in men, there was no similar association (HR, 0.79; 95% CI, 0.46-1.38; P =.0413). Diabetes remission at 10 years follow-up was also associated with a reduction in cancer incidence (HR, 0.40; 95% CI, 0.22–0.74; P =.003).
The ascertainment of diabetes diagnoses was a limitation of the study, which were based on a single time point measurement and/or the use of a diabetes medication. Additionally, the majority of participants in the surgery group had received vertical banded gastroplasty or banding, which is rarely used today. High postoperative mortality following bariatric surgery was reported during the original SOS study.
“In conclusion, with increasing rates of obesity and diabetes worldwide, a greater emphasis on cancer prevention strategies is needed,” the researchers wrote. “Bariatric surgery may greatly reduce the risk of cancer among patients with obesity and diabetes. Durable diabetes remission seems imperative for cancer prevention in patients with obesity and diabetes.”
Read More