AI helps to predict cancers’ trajectories
Many years ago, people in the UK referred to cancers as “a growth.” While it might have lacked scientific precision, it encapsulated cancers’ changing characteristics. The country’s Institute of Cancer Research (ICR) at London’s Royal Marsden Hospital, and part of University College London (UCL), says tumours’ constantly changing nature’s one of the biggest challenges in treating cancer, especially when they evolve into drug-resistant forms.
It reports that its ICR scientists, working with colleagues at Edinburgh University have used AI to identify patterns in DNA mutations in cancers. The information can forecast future genetic changes to predict how cancers will progress and evolve. The technique, Repeated Evolution of Cancer (REVOLVER), predicts cancers’ next moves so doctors can monitor tumour’s progress and design the most effective treatment for each patient.
Three organisations financed the research, published in Nature Methods. They were the Wellcome Trust, the European Research Council and Cancer Research UK. Their support for REVOLVER’s created what’s seen as a powerful AI tool. It’s revealed previously hidden mutation patterns located in complex data sets.
Teams from ICR and the University of Edinburgh working with colleagues from the Birmingham University, Stanford University and Queen Mary Universities London found a link between some sequences of repeated tumour mutations and survival outcomes. It suggests that repeating patterns of DNA mutations could be prognoses indicators. This can help to specify future treatment.
AI success stories provide material to consider in Africa’s new eHealth strategies, to support leading specialist hospitals to set up a wide range of AI initiatives. They could focus on Africa’s current and emerging health and healthcare priorities.
- 454 views
- September 04, 2018
- Ameera Hamid
Cancer detecting pen to be piloted in Texas
We often hear from surgeons that distinguishing cancerous tissues during surgery may be difficult. This is a challenge that has been tackled by a group of researchers from the university of Texas who have developed a revolutionary pen. The MasSpec Pen is coupled to a mass spectrometer and can identify cancerous tissue during surgery in real time.
The MasSpec Pen is able to diagnose cancer within twenty seconds during surgery. The pen is placed over a tissue and uses touch to make a diagnosis. A foot pedal triggers the device to release water droplets which extract molecules from the tissue. The water is drawn into the mass spectrometer. It then analyses the molecular compositions to determine if the tissue is cancerous or not. This also eliminates time waiting for results to return from the pathologist.
While the diagnosis may be quick, the accuracy is still spot on. During a trial, 300 patient samples were analysed and the MasSpec Pen was able to detect four types of cancer; breast, thyroid, ovarian and lung cancer with over 96 % accuracy. This could allow surgeons to remove all cancerous tissue and prevent further complications later on. Similarly, it will eliminate the risks of unnecessary removal of normal tissue.
Over the next several months, three of the devices will be installed in Texas hospitals. The cost of this revolutionary pen is still being debated, but this could well be a useful tool for rural and remote hospitals in Africa to quickly and easily detect cancers.
- 408 views
- May 28, 2018
- Nontobeko Shabangu
Rwandan hospital uses telepathology to diagnose cancer
The Rwanda Military Hospital (RMH) has a new tool that enables medical professionals to carry out pathology test using telecommunications technology to facilitate the transfer of image-rich pathological data for diagnosis, education, and research. The OMNYX VL4 system consists of an indoor scanner, cameras, a microscope, and computers says an article in ITNEWS Africa.
The system scans the samples and then displays the results on a computer screen. The images can then be shared online with other medical professionals in the hospital and hospitals globally. RMH has partnered with US doctors who’ll work remotely reviewing the images and responding within 24 hours.
“Testing and treating cancer is a big challenge globally, and here in Rwanda, we have a specific challenge of not having many specialised doctors in both testing and treatment of the disease. So, this new system comes as a way of helping us to test and diagnose cancer faster as we communicate among us so that we can be able to administer immediate treatment that will give patients more chances to recover,” said Lt Col Fabien Ntaganda, the head of laboratory services at RMH.
The new technology can test for all types of cancers. Doctors will be able to provide the diagnosis and treatment plans within five days compared to the average two weeks it usually takes..
Other East African countries, including Uganda and Tanzania, are looking to roll out the technology soon. They aren’t the only African countries that can benefit from the technology.
- 707 views
- October 18, 2017
- Lesley Dobson
Whatsapp helps to demystify cancer in Tanzania
Cancer rates are soaring in Africa and people are taking note. The answer to why the disease is spreading so rapidly on the continent is not straightforward. Doctors and health workers attribute the spike to poor health education, environmental changes, high HIV rates, improved diagnostics and the fact that people are simply living longer.
WHO has recently warned that Non-Communicable Diseases (NCD) are likely to kill more people in Africa than infectious disease. It set these out as a forecast by 2030. Cancer’s a major contributor.
The Ocean Road Cancer Institute (ORCI), Tanzania’s major cancer centre, has estimated that the country’s heading for 30,000 new cancer cases a year. The diseases’s a huge public health concern.
Combating the increase in misleading cancer information is part of Tanzania’s contributing. An article in allAfrica says it includes false cancer cures claims and alarming stories on social media linking some foods and human behaviour with cancer. Experts are trying to demystify the disease by curbing this damaging information.
Radiotherapists in Tanzania say WhatsApp, the cross-platform instant messaging service for smartphones, can help to tackle the problem. In February, radiotherapists formed Saratani.info a set of WhatsApp groups to disseminate cancer awareness. Currently, there are five groups. Each one has 251 members, so 1,255 people have so far joined. Each group has five educators, including radiotherapists, doctors and nurses.
Mr Franklin Mtei, Saratani.info’s founder, and managing director of the Tanzanian Cancer Society (Tacaso), formed in 2014, leads the team of educators. They’re expected to become future cancer ambassadors. Other group members included people from the general public, the private sector, public officials, students, entrepreneurs, professionals and non-professionals.
The groups were formed by adding the WhatsApp users that the radiologists already had in their own phone books. Other people were invited through Facebook. People can join and leave any of the groups voluntarily through their Facebook Page.
A co-founder of Tacaso, Mr Ally Idris, a radiotherapist, says people's perception about cancer in Tanzania has been wrong for many years. Society’s information gap is huge. Many people believe that cancer is contagious, while others think that treatment by radiations causes more cancer.
The founders want their initiative to provide services beyond the WhatsApp groups. They plan to expand across Tanzania, targeting vulnerable people who lack information about cancer, its causes, prevention and how to access treatment. It’s an initiative that could benefit all Africa.
- 757 views
- July 05, 2017
- Lesley Dobson
Protecting our children from HPV
One in every eight women in South Africa die from complications of cervical cancer. Each year, 5,743 new cases of cervical cancer are reported. Almost half of these, 3,027 cases are fatal.
About 80% of cervical cancers are caused by the Human Papilloma Virus (HPV). It infects the genital area and causes anything from a small genital wart to cervical and other cancers. Vaccination can prevent the virus infection developing on the cervix.
In 2014, the South African National Departments of Health (NdoH) and Basic Education launched a national vaccination campaign to prevent cervical cancer by vaccinating girls aged over nine against HPV. The vaccination was aimed at 500 000 girls from 17 000 public and special schools to provide them with protection before they can be exposed to HPV infection.
In co-ordination with the government’s Integrated School Health Programme (IHSP), school health nurses visit schools twice a year to vaccinate the girls. None of them are vaccinated without parental consent.
As the vaccination campaign grew, collecting data became more complex and challenging. NDoH approached the Health Information Systems Program South Africa (HISP-SA) to lead implementation of a mobile data capturing application. It supports data capture during the campaigns.
The app’s part of the NDoH's routine health information system, DHIS2, sometimes referred to as webDHIS. It was customised for the campaign by HISP-SA’s Lusanda Ntoni and piloted in three provinces. Then, it was developed further using findings from field visits, and implemented during the 2016 campaign.
A Standard Operating Procedure (SOP) document helps vaccinators and data capturers to transfer HPV data from registers into the tracker capture app. There’s also a guideline for programme managers and information officers on accessing dashboards with information from the campaign on webDHIS. These were updated as the app was implemented.
To date, the app’s been implemented in all nine provinces in South Africa, a task co-ordinated by HISP SA’s HPV project manager, Margaret Modise. It’s simplified HPV dashboards for monitoring and reporting and shows how a simple mHealth initiative can enhance the productivity of vaccination campaigns. Will this way of capturing data lead to more large-scale campaigns in South Africa?
- 919 views
- June 30, 2017
- Hlobisile Vilakazi
There’s lots of projects to improve breast cancer diagnoses
WHO has a report showing breast cancer as the most common cancer in women, both in developed and under developed countries. The breast cancer mortality rate was estimated at 508,000 in 2011. Although breast cancer is thought to be a disease of the developed world, almost 50% of breast cancer cases and 58% of deaths occur in less developed countries. Incidence rates vary greatly worldwide, from 19.3 per 100,000 women in Eastern Africa to 89.7 per 100,000 in Western Europe. In most developing regions, incidence rates are below 40 per 100,000. Africa has the lowest e rates, but here, breast cancer incidence rates are increasing.
An article in FierceBiotech says Philips, the Dutch technology company, is partnering with PathAI, a company that develops artificial intelligence (AI) for pathology, to develop solutions that improve the precision and accuracy of routine breast cancer diagnosis. A report by Tissue Pathology says the two companies are developing deep-learning algorithms that will detect and diagnose several diseases, with the first being breast cancer. The outcome’ll be an app that automatically identifies cancerous lesions in breast tissue.
Tumour analysis is essential to diagnosis, but conducting it manually is time consuming and laborious for pathologists. The app will ease the burden on pathologists.
Philips’ Illumeo platform uses adaptive intelligence to help radiologists work more efficiently. Its IntelliSite Pathology Solution is an automated digital pathology system that includes a slide scanner, image management system and software tools. Last June, the company bought PathXL, a Northern Ireland company focusing on image analysis and digital pathology.
There’s plenty of similar research underway. Samsung is another company that’s applying AI to diagnose breast cancer from medical imaging. It uses deep-learning algorithms too to detect breast cancer lesions in ultrasound images.
Breast Cancer News has reported that researchers from Houston Methodist Hospital have developed software to predict breast cancer risk from patient charts and mammograms. Harvard Health Publications has reported that a Harvard-MIT team has used AI to diagnose breast cancer from slides of lymph node cells.
These developments are a step into the future of disease diagnosis. How far behind do developing nations lag in implementing these innovations?
- 811 views
- April 12, 2017
- Hlobisile Vilakazi
Kenya’s cancer screening app ETiCCS’s now available
Cervical cancer is the second most common cause of death for women worldwide. In Kenya, it’s the leading cause of death for women of reproductive age. Kenyan Network of Cancer Organizations says there are approximately 39,000 new cases of cancer each year in Kenya, leading to more than 27,000 deaths. The star has a report estimating increases in cervical cancers cases from 3,000 to 4,200 by 2025. It’s largely due to lack of access to healthcare resources and treatments.
To address this gap and improve the quality of life among women in Africa, and particularly Kenya, the SAP’s Design and Co-Innovation Center together with Heidelberg University Hospital has optimised a cervical cancer screening test that combines practical medical research with cloud technology from SAP. The digitised screening test, called Emerging Technologies in Cervical Cancer Screening (ETiCCS) strives to support the fight against cancer in developing countries.
An article in IT online reports that ETiCCS was piloted during a one-year study, which tested 800 women at the Moi Teaching and Referral Hospital in Eldoret, Kenya. The program is ongoing and SAP East Africa plans to include the countrywide self-sampling and IoT scenarios, deep learning, pattern recognition, remote diagnostics support and validation into the program. SAP East Africa will collaborate with technology including SAP HANA Cloud Platform, as development continues SAP HANA Cloud allows seamless communication between healthcare providers including those in remote areas and environments with unstable Internet connectivity.
The technology will allow the healthcare screening services to:Keep medical records safely stored in the cloud providing instant access to results. Enabling labs to accelerate the screening process and empower medical staff through improved quality control embedded in the screening process Enforce compliance with data privacy and security requirements, meaning labs can make informed diagnoses regardless of location or regionEnable healthcare professionals to uncover critical patient insights and adapt the solution to other screening processes and field research.
The ETiCCS program has already enabled hundreds of women in Kenya access to screening for cervical cancer.
- 1,178 views
- March 03, 2017
- Gontse Ramela
AI’s good at diagnosing skin cancer
Conventionally, skin cancer’s primarily diagnosed visually. It starts with a clinical screenings, then, if needed, followed by dermoscopic analyses, a biopsies and histopathological examinations. A team mainly from Stanford University, California, has reported in Nature that mHealth can provide an alternative. It’s a technological step up for Africa’s mHealth.
Classifying skin lesions using images is challenging, owing to fine-grained variabilities in their appearance. Convolutional Neural Networks (CNN) offer potential for dealing with fine-grained object categories. The team demonstrates skin lesion classifications using a single CNN, trained end-to-end directly from images using only pixels and disease labels as inputs. Trained CNN used a dataset of 129,450 clinical images and 2,000 skin lesions.
Its performance was tested against 21 dermatologists using proven clinical images from biopsies in two use cases:Keratinocyte carcinomas versus benign seborrheic keratosis, identifying the most common cancersMalignant melanomas versus benign nevi, identifying deadliest skin cancer.
CNN achieved performance in both use cases that matched all tested experts. It shows that the algorithms in Artificial Intelligence (AI) can classify skin cancer as well as dermatologists. Equipped with CNN, mHealth can potentially extend dermatologists’ reach beyond their clinics. An impact is lower-cost universal access to vital diagnostic services.
As healthcare researcher teams extend AI across other conditions, it offers Africa’s mHealth initiatives a much wider role and impact. It seems that mHealth can have much more to offer.
- 875 views
- February 07, 2017
- Tom Jones
IHE wants comments on endoscopy
Four aspects of endoscopy can be seen as the instrument, the technique, a diagnostic tool and minimally invasive surgery. It’s a very valuable medical technology. Looking inside people is a clever way to avoid cutting them open.
Endoscope’s aren’t a modern idea. Primed Canada says its inventor identified by most medical historians is Philip Bozzini. In 1805, he used a tube, lichtleiter, a light guiding instrument, he created, to examine urinary tracts. Antoine Jean Desormeaux, a French surgeon renamed it the endoscope. It’s claimed that in 1868, Adolph Kussmaul was the first person to use an endoscope to see the inside of a stomach of a living person. In 1878, two doctors, Max Nitze and Josef Leiter, invented an endoscope to inspect the urinary tract and bladder.
None of these men concerned themselves with the informatics or eHealth standards and interoperability of their innovations. Integrating the Healthcare Enterprise (IHE) does. It’s released for consultation two supplements:
Endoscopy Image Archiving (EIA)
Endoscopy Ordering Workflow (EWF).
The IHE Endoscopy Technical Committee wanted comments on these by 18 January 2017. They will now complete the supplements as part of the planned IHE Endoscopy Technical Framework.
- 792 views
- February 06, 2017
- Tom Jones
eHealth can help Africa's cancer care
Cancers are on the march, but disproportionately affect developing countries. India’s using Medic Mobile. It’s part of the British Council's Global Innovation Initiative and partnerships with University of Edinburgh, Weill Cornell Medical College, New York and Christian Medical College Vellore, India.
Medic Mobile says more than 60% of world's new annual cancer cases occur in Africa, Asia and Central and South America. They account for 70% of the world's cancer deaths. Cancer’s become a serious public health issue in India. It has only eleven health workers for every 10,000 citizens, and rural and urban populations experience vastly different healthcare.
World Health Rankings for all cancers in 2014 show India’s death rate as about 70 per 100,000. Africa’s average’s about 87. Ten African countries have a death rate lower than India’s. Gabon’s the lowest at about 51. Gambia, Namibia and Niger are all below 60 too. Zimbabwe’s the highest at about 210 per 100,000. It’s an outlier. Burundi’s second highest at about 130. If India sees cancers as a public health priority, Africa’s facing challenges too.
Cancers in rural parts of India are rarely diagnosed due to lack of public awareness and healthcare. The delays in diagnoses pose treatment challenges. Leveraging low-cost, low-technology mHealth can improve healthcare access, reduce costs, and strengthen health systems to meet cancer care challenges in remote communities. A study’s analysing the impact that the mHealth tools have on cancer outcomes in low-resource settings as health workers and nurses us it to screen high-risk people, refer some of them to facilities for care and follow them up for treatment.
Three sites are Padhar, Vellore and Mungeli. Only Vellore's Rural Unit for Health and Social Affairs (RUHSA) currently has a paper-based early cancer detection system. Padhar and Mungeli have no early cancer screening or detection system and only provide cancer care in facilities. The lack of early detection at these two sites means that many late-stage oral and cervical cancer patients have low chances of successful treatment. The project will train health workers, nurses, dental assistants and project coordinators to use mHealth to screen, record, and refer patients.
Health workers are being trained to identify oral cancer lesions and refer the patients with precancerous lesions to the hospital. The health workers will use mHealth to create a profile for each new patient and generate a unique patient ID. Cervical cancer screening requires a Visual Inspection with Acetic acid (VIA), so nurses will screen women for cervical cancer by visiting community centres in the villages. Women who test VIA positive are counselled by nurses to visit the hospital’s gynaecology department where they’ll have a second VIA test, and a biopsy if needed, then appropriate medical treatment. Nurses will use mHealth to report on the second test results and treatment confirmation.
This’s a simple, effective mHealth model that Africa’s health systems can adopt. A small start leading to a steady roll out with adjustments from learning has much to commend it.
Image from Kera News
- 697 views
- June 15, 2016
- Tom Jones
Rome Business School eHealth Masters
Better managers for a better world
Cyber-security: themes for Africa's eHealth
Cyber-crime is on the increase, and Africa’s health sector is not immune to the growing and changing threats.
African eHealth Forum 2016 Report
Successful eHealth connects us with our information in ways that transform what we expect from our health...
African eHealth Forum 2015 Report
Acfee hosts the annual African eHealth Forum. It’s where Acfee’s Advisory Board, its industry partners...