2 weeks Ago
Share to Facebook Share to Twitter Share to Linkedin Prostate cancer is the second most common cancer for men in the United States (after skin cancer) and is the second leading cause of cancer deaths (after lung cancer). The American Cancer Society predicts that approximately 35,000 American men will die of prostate cancer in 2024 . Thus anything that can help physicians detect and treat prostate cancer sooner could save thousands of lives.
One critical tool for accurate diagnosis of prostate cancer is MRI scanning. A high quality MRI scan can help surgeons detect the presence of tumor, the extent of tumor within the gland, and the presence of any spread into adjacent organs. However, MRI scans must still be interpreted by human radiologists.
And humans can make mistakes. In particular, recent research has shown that human radiologists are more like to interpret a scan as “malignant” later in the workday , when “fatigue, workload, and circadian rhythms may influence decision-making.” This is not a surprise.
Other researchers have shown that “ radiologists are more prone to errors after 10 hours of clinical interpretation .” However, the study performed by Dr. Anton Becker and colleagues was able to quantify this with respect to the specific issue of prostate cancer diagnoses.
(Dr. Becker’s paper also cited the similar “Hungry Judge” effect , in which judges’ rulings in parole boards were reportedly harsher as they became more tired and hungry during the workday, and became more lenient after they were rested and fed.) Prostate Cancer Awareness Month concept.
Banner template with light blue ribbon. Vector ..
. [+] illustration. getty Dr.
Becker and colleagues also suggest that artificial intelligence can help reduce the error rates due to human fatigue. Fortunately, AI algorithms are reaching the point that this might become a practical reality very soon. MORE FOR YOU Election 2024 Swing State Polls: Harris Leads Or Ties Trump In All Battleground States, Latest Survey Finds Kamala Harris Defends Biden Admin’s Economic Record In First Big Interview—But Says ‘More To Do’ ‘The Rings Of Power’ Season 2 Premiere Review: A Dreadful, Jumbled Mockery Of Tolkien’s ‘The Lord Of The Rings’ Researchers at the Mayo Clinic and at Massachusetts General Hospital were able to develop a deep learning AI system that was nearly equivalent in accuracy to expert human radiologists .
Furthermore, a combination of human plus AI did better than either alone. Another team of researchers at UCLA was able to use an AI system to determine the exact degree of tumor spread in a method that was “ 45 times more accurate and consistent “ than conventional methods. Being able to more precisely determine the boundary between tumor cells and normal tissues can enormously helpful in treatment planning, allowing physicians to make best use of “ surgery, focal therapy, radiation therapy, hormone therapy, chemotherapy, or a combination of these treatments “ to destroy or remove the cancerous tissues while causing as little damage as possible to nearby healthy tissues.
function loadConnatixScript(document) { if (!window.cnxel) { window.cnxel = {}; window.
cnxel.cmd = []; var iframe = document.createElement('iframe'); iframe.
style.display = 'none'; iframe.onload = function() { var iframeDoc = iframe.
contentWindow.document; var script = iframeDoc.createElement('script'); script.
src = '//cd.elements.video/player.
js' + '?cid=' + '62cec241-7d09-4462-afc2-f72f8d8ef40a'; script.setAttribute('defer', '1'); script.setAttribute('type', 'text/javascript'); iframeDoc.
body.appendChild(script); }; document.head.
appendChild(iframe); const preloadResourcesEndpoint = 'https://cds.elements.video/a/preload-resources-ovp.
json'; fetch(preloadResourcesEndpoint, { priority: 'low' }) .then(response => { if (!response.ok) { throw new Error('Network response was not ok', preloadResourcesEndpoint); } return response.
json(); }) .then(data => { const cssUrl = data.css; const cssUrlLink = document.
createElement('link'); cssUrlLink.rel = 'stylesheet'; cssUrlLink.href = cssUrl; cssUrlLink.
as = 'style'; cssUrlLink.media = 'print'; cssUrlLink.onload = function() { this.
media = 'all'; }; document.head.appendChild(cssUrlLink); const hls = data.
hls; const hlsScript = document.createElement('script'); hlsScript.src = hls; hlsScript.
setAttribute('defer', '1'); hlsScript.setAttribute('type', 'text/javascript'); document.head.
appendChild(hlsScript); }).catch(error => { console.error('There was a problem with the fetch operation:', error); }); } } loadConnatixScript(document); (function() { function createUniqueId() { return 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'.
replace(/[xy]/g, function(c) { var r = Math.random() * 16 | 0, v = c == 'x' ? r : (r & 0x3 | 0x8); return v.toString(16); }); } const randId = createUniqueId(); document.
getElementsByClassName('fbs-cnx')[0].setAttribute('id', randId); document.getElementById(randId).
removeAttribute('class'); (new Image()).src = 'https://capi.elements.
video/tr/si?token=' + '44f947fb-a5ce-41f1-a4fc-78dcf31c262a' + '&cid=' + '62cec241-7d09-4462-afc2-f72f8d8ef40a'; cnxel.cmd.push(function () { cnxel({ playerId: '44f947fb-a5ce-41f1-a4fc-78dcf31c262a', playlistId: 'aff7f449-8e5d-4c43-8dca-16dfb7dc05b9', }).
render(randId); }); })(); As with other current developments in medical AI, these tools can not (yet) fully replace human physicians. Dr. Takahashi of the Mayo Clinic team noted that “I do not think we can use this model as a standalone diagnostic tool.
” Instead, he regards the AI “as an adjunct in our decision-making process.” And as always, these research results need to be validated in larger groups of patients before they are ready for widespread everyday clinical use. Nonetheless, I’m delighted to hear of such fruitful collaborations between physicians at leading academic medical centers and AI scientists.
The coming years of the AI revolution should bring more such good news to patients and physicians alike..
