The three risk assessment tools now in use fall far
\nshort. Using the latest deep learning techniques, investigators are developing
\nmore personalized ways to locate women at high risk.<\/h4>\n![](\"https:\/\/blogger.googleusercontent.com\/img\/b\/R29vZ2xl\/AVvXsEi6xpvtuvpBR9Szs_Pu9gNV4MB-cMs2iBpASnJQ801ME2PrFQweW8m_dQVroNzKjRheJ2keb7orwqVCFOpktXbhckU1-hB8HMIRGnCwbV6938T0E_ftA3gMQGip8roPeVjKY-eAgmbiX16s\/w400-h220\/shutterstock_1207894222+%25283%2529.jpg\")
<\/a><\/div>\nJohn Halamka, M.D., president, Mayo Clinic Platform, and Paul
\nCerrato, senior research analyst and communications specialist, Mayo Clinic
\nPlatform, wrote this article.<\/span><\/i><\/p>\nThe promise of personalized medicine will eventually allow
\nclinicians to offer individual patients more precise advice on prevention,
\nearly detection and treatment. Of course, the operative word is <\/span>eventually. <\/i>A
\ncloser examination of the screening tools available to detect breast cancer
\ndemonstrates that we still have a way to go before we can fulfill that promise.
\nBut with the help of better technology, we are getting closer to that
\nrealization.<\/span><\/p>\nDisease screening is about risk assessment. Researchers collect
\ndata on thousands of patients who develop breast cancer, for instance, and
\ndiscover that the age range, family history and menstruation history of those
\nwho develop the disease differs significantly from those who remain free of it.
\nThat in turn allows policy makers to create a screening protocol that suggests
\nwomen of a certain age who have experienced early menarche or late menopause
\nare more likely to develop the malignancy. That risk assessment is consistent
\nwith the fact that more reproductive years means more exposure to the hormones
\nthat contribute to breast cancer. Similarly, there\u2019s evidence to show that
\nwomen with first degree relatives with the cancer and those with a history of
\novarian cancer or HRT use are at greater risk.<\/span><\/p>\nStatistics like this are the basis for several breast cancer
\nrisk scoring systems, including the Gail score, the IBIS score, and BCSC
\ntool.\u00a0 The <\/span>National
\nCancer Institute<\/span><\/a>, which
\nuses the Gail model, explains: \u201cThe Breast Cancer Risk Assessment Tool allows
\nhealth professionals to estimate a woman’s risk of developing invasive breast
\ncancer over the next 5 years and up to age 90 (lifetime risk). The tool uses a
\nwoman\u2019s personal medical and reproductive history and the history of breast
\ncancer among her first-degree relatives (mother, sisters, daughters) to
\nestimate absolute breast cancer risk\u2014her chance or probability of developing
\ninvasive breast cancer in a defined age interval.\u201d While the screening tool
\nsaves lives, it can also be misleading. If, for example, it finds that a woman
\nhas a 1% likelihood of developing breast cancer, what that really means is a
\nlarge population of women with those specific risk factors has a one in 100
\nrisk of developing the disease. There is no way of knowing what the threat is
\nfor any one patient in that group. Similar problems exist for the International
\nBreast Cancer Intervention Study <\/span>(IBIS) score<\/span><\/a>, based on the
\nTyrer-Cuzick Model, and the <\/span>Breast Cancer Surveillance Consortium<\/span><\/a> (BCSC) Risk Calculator. These
\n3 assessment tools can give patients a false sense of security if they don\u2019t
\ndive into the details. BCSC, for instance, cannot be applied to women younger
\nthat 35 or older than 74, nor does it accurately measure risk for anyone who
\nhas previously had ductal carcinoma in situ (DCIS), or had breast augmentation.
\nSimilarly, the NCI tool doesn\u2019t accurately estimate risk in women with BRCA1 or
\nBRCA1 mutation, as well as certain other subgroups.<\/span><\/p>\nDuring a conversation with Tufia Haddad, M.D,, a Mayo Clinic
\nmedical oncologist with specialty interest in precision medicine in breast
\ncancer and artificial intelligence, she discussed the research she and her
\ncolleagues are doing to improve the risk assessment process and identify more
\nhigh-risk women. Dr. Haddad pointed out that there are numerous obstacles that
\nprevent women from obtaining the best possible risk assessment. Too many women
\ndo not have a primary care practitioner who might use a risk tool. And those
\nthat do have a PCP are more likely to have an evaluation based on the Breast
\nCancer Risk Assessment tool (the Gail model). \u201cWe prefer the Tyrer-Cuzick model
\nin part because it incorporates more personal information for each individual
\npatient including a detailed family history, a woman\u2019s breast density from her
\nmammogram, as well as her history of atypia or other high risk benign breast
\ndisease,\u201d says Dr. Haddad. Unfortunately, the Tyrer-Cuzick method requires many
\nmore data elements to assess breast cancer risk, which discourages busy
\nclinicians from using it.<\/span><\/p>\n
![](\"https:\/\/blogger.googleusercontent.com\/img\/b\/R29vZ2xl\/AVvXsEi6xpvtuvpBR9Szs_Pu9gNV4MB-cMs2iBpASnJQ801ME2PrFQweW8m_dQVroNzKjRheJ2keb7orwqVCFOpktXbhckU1-hB8HMIRGnCwbV6938T0E_ftA3gMQGip8roPeVjKY-eAgmbiX16s\/s714\/shutterstock_1207894222+%25283%2529.jpg\")
<\/a><\/div>\nJohn Halamka, M.D., president, Mayo Clinic Platform, and Paul The promise of personalized medicine will eventually allow Disease screening is about risk assessment. Researchers collect Statistics like this are the basis for several breast cancer During a conversation with Tufia Haddad, M.D,, a Mayo Clinic
\nCerrato, senior research analyst and communications specialist, Mayo Clinic
\nPlatform, wrote this article.<\/span><\/i><\/p>\n
\nclinicians to offer individual patients more precise advice on prevention,
\nearly detection and treatment. Of course, the operative word is <\/span>eventually. <\/i>A
\ncloser examination of the screening tools available to detect breast cancer
\ndemonstrates that we still have a way to go before we can fulfill that promise.
\nBut with the help of better technology, we are getting closer to that
\nrealization.<\/span><\/p>\n
\ndata on thousands of patients who develop breast cancer, for instance, and
\ndiscover that the age range, family history and menstruation history of those
\nwho develop the disease differs significantly from those who remain free of it.
\nThat in turn allows policy makers to create a screening protocol that suggests
\nwomen of a certain age who have experienced early menarche or late menopause
\nare more likely to develop the malignancy. That risk assessment is consistent
\nwith the fact that more reproductive years means more exposure to the hormones
\nthat contribute to breast cancer. Similarly, there\u2019s evidence to show that
\nwomen with first degree relatives with the cancer and those with a history of
\novarian cancer or HRT use are at greater risk.<\/span><\/p>\n
\nrisk scoring systems, including the Gail score, the IBIS score, and BCSC
\ntool.\u00a0 The <\/span>National
\nCancer Institute<\/span><\/a>, which
\nuses the Gail model, explains: \u201cThe Breast Cancer Risk Assessment Tool allows
\nhealth professionals to estimate a woman’s risk of developing invasive breast
\ncancer over the next 5 years and up to age 90 (lifetime risk). The tool uses a
\nwoman\u2019s personal medical and reproductive history and the history of breast
\ncancer among her first-degree relatives (mother, sisters, daughters) to
\nestimate absolute breast cancer risk\u2014her chance or probability of developing
\ninvasive breast cancer in a defined age interval.\u201d While the screening tool
\nsaves lives, it can also be misleading. If, for example, it finds that a woman
\nhas a 1% likelihood of developing breast cancer, what that really means is a
\nlarge population of women with those specific risk factors has a one in 100
\nrisk of developing the disease. There is no way of knowing what the threat is
\nfor any one patient in that group. Similar problems exist for the International
\nBreast Cancer Intervention Study <\/span>(IBIS) score<\/span><\/a>, based on the
\nTyrer-Cuzick Model, and the <\/span>Breast Cancer Surveillance Consortium<\/span><\/a> (BCSC) Risk Calculator. These
\n3 assessment tools can give patients a false sense of security if they don\u2019t
\ndive into the details. BCSC, for instance, cannot be applied to women younger
\nthat 35 or older than 74, nor does it accurately measure risk for anyone who
\nhas previously had ductal carcinoma in situ (DCIS), or had breast augmentation.
\nSimilarly, the NCI tool doesn\u2019t accurately estimate risk in women with BRCA1 or
\nBRCA1 mutation, as well as certain other subgroups.<\/span><\/p>\n
\nmedical oncologist with specialty interest in precision medicine in breast
\ncancer and artificial intelligence, she discussed the research she and her
\ncolleagues are doing to improve the risk assessment process and identify more
\nhigh-risk women. Dr. Haddad pointed out that there are numerous obstacles that
\nprevent women from obtaining the best possible risk assessment. Too many women
\ndo not have a primary care practitioner who might use a risk tool. And those
\nthat do have a PCP are more likely to have an evaluation based on the Breast
\nCancer Risk Assessment tool (the Gail model). \u201cWe prefer the Tyrer-Cuzick model
\nin part because it incorporates more personal information for each individual
\npatient including a detailed family history, a woman\u2019s breast density from her
\nmammogram, as well as her history of atypia or other high risk benign breast
\ndisease,\u201d says Dr. Haddad. Unfortunately, the Tyrer-Cuzick method requires many
\nmore data elements to assess breast cancer risk, which discourages busy
\nclinicians from using it.<\/span><\/p>\n