Hi Leo,<br><br>that's great. Only two thoughts:<br><font face="Calibri" size="3">1. the term "long pre-clinical phase" sounds like a drug development trajectory.<br>How about "extended period of development before serious symptoms are noticed"?<br>
2. You can say "is likely to" rather than "may" when you talk about the possibility of classifying images using AI. We know we can do it, the only major challenge (I think) is "can we get high enough quality images to train on, and train care workers to take good photos?" (or provide real time feedback from the device about when the photo is bad - an essential facility you would need for the latter wound care example you talk about where a non-expert [the patient] is taking the photo)?<br>
</font><br>-Gari<br><br><div class="gmail_quote">2008/5/3 Leo Anthony Celi <<a href="mailto:leoanthonyceli@yahoo.com">leoanthonyceli@yahoo.com</a>>:<br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div style="margin: 0in 0in 0pt;"><span style="font-size: 10pt;">This is 4 minutes and 56 seconds on rehearsal.</span></div> <div style="margin: 0in 0in 0pt;"><b><span style="font-size: 10pt;"></span></b> </div> <div style="margin: 0in 0in 0pt;">
<b><span style="font-size: 10pt;">Script for the Demonstration Video</span></b></div> <div style="margin: 0in 0in 10pt;"><font face="Calibri" size="3">Around the world, a woman dies of cervical cancer every 2 minutes.<span> </span>Over 80% of
the deaths occur in the developing world, with sub-Saharan Africa being the worst-affected .<span> </span>This is likely a consequence of the spread of HIV in the region.<span> </span>Transmission of the human papilloma viruses that cause cervical cancer is facilitated by the presence of HIV infection. In addition, progression is accelerated by the immunosuppression that results from HIV. </font></div>
<div style="margin: 0in 0in 10pt;"><font face="Calibri" size="3">In Zambia, cervical cancer strikes 63 women in 100,000, affecting women at a time of life when they are critical to social and economic stability.<span> </span>But cervical cancer has a long pre-clinical phase, and thus, is highly preventable through yearly pap smears that facilitate detection and treatment of pre-cancerous lesions. <span> </span>Such
screening, which is routine in countries like the US, is not possible in most countries because of the resources it requires.</font></div> <div style="margin: 0in 0in 10pt;"><font size="3"><font face="Calibri">Visual inspection of the cervix after painting with vinegar, or VIA, to detect pre-cancerous lesions has emerged as a cheaper alternative in developing countries.<span> </span>Studies have demonstrated that this cheaper prevention program is effective in reducing the incidence of and the death rate from cervical cancer.<span> </span></font></font></div>
<div style="margin: 0in 0in 10pt;"><font size="3"><font face="Calibri">Since 2006, through the Center for Infectious Disease Research in Zambia or CIDRZ, ??? have undergone cervical cancer screening through VIA performed by nurses.<span> </span>In up to 10% of cases, it is difficult to say whether
the findings on VIA are precancerous or not.<span> </span>Currently, the nurses would err on the safe side, diagnose these indeterminate cases as precancerous, treat them with cryotherapy, and arrange follow-up visits for these women.<span> </span>A significant number of false-positives is thus inevitable in this set-up, leading to unnecessary follow-up visits.<span> </span>This further constrains an already severely-constrained labor resources.<span> </span>Needless to say, input from a specialist would be very helpful in these situations.<span> </span></font></font></div>
<div style="margin: 0in 0in 10pt;"><font size="3"><font face="Calibri">The goal of this project is to facilitate, using information and communication technology, real-time specialist support for nurses.<span> </span>This is the only way to be able to scale cervical cancer screening using VIA to the rest of the country.<span> </span></font></font></div>
<div style="margin: 0in 0in 10pt;"><font face="Calibri" size="3">We developed a software application that allows the nurses to take photographs of the cervix, and transmit the images accompanied by relevant clinical information to a central server using GPRS.<span> </span>The server then alerts a specialist-on-call that a nurse is requesting decision support.<span> </span>The URL of the image and the clinical information is sent to the doctor via MMS.<span> </span>The doctor then calls the nurse and reviews the case after accessing the data from the server, and a decision is made.<span> </span>The plan of treatment is entered into the central server
by the doctor.</font></div> <div style="margin: 0in 0in 10pt;"><font face="Calibri" size="3">Archiving and information management at a central server is necessary in order to be able to track the progress of a patient, including clinical outcomes.<span> </span>It is also crucial for quality assurance and quality improvement.<span> </span>All the images, diagnosis and treatment plans are reviewed by the nurses and specialists regularly at a later time. <span> </span>What we'd like to see is a reduction over time of not only misdiagnoses, but also of indeterminate cases requiring specialist support.<span> </span>Finally, once a large database of cervical images has accumulated that are linked to both diagnoses that have been QA'd and clinical outcomes, it may be possible to come up with artificial intelligence tools that can classify
images of indeterminate cervical lesions, further reducing the need for specialist support.</font></div> <div style="margin: 0in 0in 10pt;"><font face="Calibri" size="3">Although this software application was initially developed to facilitate cervical cancer screening, it will be useful for a wide variety of scenarios in health care delivery.<span> </span>Consider this hypothetical case.<span> </span>A gentleman from a far-flung region is brought to Lusaka complaining of abdominal pains.<span> </span>A blockage is found in his intestines, requiring an operation to remove a portion of his intestines.<span> </span>He is discharged after the surgery with instructions for regular follow-up to monitor the healing of the wound from the operation.<span> </span>A week later, the patient notices some redness
around the edges of the wound.<span> </span>But because it is a full-day trip to Lusaka, he decides against the trip and he monitors the wound himself. A few days later, the patient dies as a result of a massive infection of the surgical wound.<span> </span>This software application can be a tremendous help for follow-up of patients who live in remote areas, especially if visual inspection is crucial in the clinical examination, such as in dermatology and wound care.</font></div>
<br>_______________________________________________<br>
Cidrz mailing list<br>
<a href="mailto:Cidrz@mit.edu">Cidrz@mit.edu</a><br>
<a href="http://mailman.mit.edu/mailman/listinfo/cidrz" target="_blank">http://mailman.mit.edu/mailman/listinfo/cidrz</a><br>
<br></blockquote></div><br><br clear="all"><br>-- <br>G. D. Clifford, PhD, SMIEEE<br>Principal Research Scientist,<br>Massachusetts Institute of Technology,<br>Instructor in Biomedical Engineering, HST,<br>(Harvard-MIT Division of Health Sciences & Technology)<br>
Engineering Manager for the L.C.P. at M.I.T.<br>(Laboratory for Computational Physiology),<br>Rm E25-505DA, 45 Carleton St., Cambridge MA 02142<br>Tel: +16172537937 / +448444368530<br>Fax: +16172587859 email: <a href="mailto:gari@alum.mit.edu">gari@alum.mit.edu</a><br>
<a href="http://alum.mit.edu/www/gari">http://alum.mit.edu/www/gari</a>