As indicated by recent reports from the United Nations, there has been an outbreak of cholera in North-Eastern Nigeria which is believed to have claimed the lives of nearly 100 people in the last two weeks.
According to these reports, over 3,000 cases of cholera have been recorded in Yobe and Borno; two Nigerian states that can be thought of as worse bit by the well-documented Boko Haram insurgency.
Figures from the UN Office for the Coordination of Humanitarian Affairs (OCHA) make for gloomy reading. There has been a total of 3,126 recorded cases of the disease with 97 fatalities already taken into account since the disease first broke out a fortnight ago in Borno, where people, numbering in hundreds of thousands, are known to be currently taking refuge in Internally-Displaced Persons (IDP) camps as a result of the violence erupted by the insurgency.
Since the turn of the year, it is reported that the death toll due to cholera outbreaks in the Lake Chad region is over 500 – a figure that is believed to represent the worst outbreak of the disease in four years. With heavy rains and flooding rampant this time of year — which serves up an ideal environment for the spread of the disease — it is feared that up to six million people might be at risk. And that might be just for starters.
Recent reports from the Democratic Republic of Congo indicate a worrying and troubling development. It appears there is now confirmation of a new case of Ebola on the country’s border with Uganda. The new case of the virus is reported to have occurred almost 200 km away from the nearest other known case in Congo’s most recent Ebola outbreak, which is believed to have claimed up to 97 lives since July and infected another 46 in the country’s Ituri and North Kivu provinces.
The same disease is known to have killed over 11,000 people in West Africa between 2014 and 2016, with statistics hinting at a disturbing fatality rate of 40% of all the reported cases. African countries like Guinea, Sierra Leone, Nigeria, and Liberia were bedeviled by the virus, which eventually found its way to the UK, US, and Spain.
With these in mind, the assertion that the healthcare system in parts of Africa is both inefficient and inadequate might not be very far from the truth. It is reactive rather than proactive, at best. The most recent cases of cholera and Ebola make good pointers. These diseases are anything but first-timers; bodies have been left behind in their wake in the past. And it does worry to think about how many more lives will have to be lost before a there is a return to the drawing board and proactive measures are put in place to forestall future occurrence of epidemics and pandemics which the continent appears to be very susceptible to.
What if we could have caught wind of these disease outbreaks months before it did happen? Wouldn’t that buy us some time to take preemptive steps toward curtailing its spread? Think about that. This informs the need to ditch the old ways and embrace newer, reliable, and more efficient ways of keeping diseases at bay — proactive measures that can, at the very least, significantly curb the spread of disease if not completely prevent them. And smart technologies might just provide the answer.
Terms like data analytics, machine learning, and artificial intelligence, are regarded in some circles as the stuff of geeks with no real practical use or problem-solving application in the real world — perhaps, just another fad that will keep the tech scene abuzz for a couple of years and then fade out just as soon as the next one shows up. There may even be individuals who feel like they might wince or gag the next time they hear those three terms, having heard them being mentioned far too often without even the slightest idea what they entail.
Be that as it may, this may be a chance to learn about some ways in which these smart technologies can come in handy in solving some of the world’s problems — especially those ones associated with epidemics and pandemics.
By leveraging smart technologies, there is a good chance that the carnage and devastation left behind by the spate of killer diseases in parts of Africa and the rest of the world in the past can be significantly reduced. These technologies can do a good job of providing a heads up with regards to the imminent outbreaks of diseases that can potentially hurt a significant demography. They have the capacity to put health bodies in the know beforehand as per looming epidemics, thus helping to direct and channel preemptive efforts to areas that are at most risk or in most need, which could imply the reduction of the impact of the disease, if not its entire prevention.
By utilizing the full potential that comes with accessing large amounts of data, the computational power that is required for the storage and analysis of the data accessed in real-time, as well as the complex algorithms that are adept at identifying data patterns, health authorities can be alerted of looming problems before they escalate into full-blown disasters. Essentially, disease outbreaks that have gone on to become epidemics and even pandemics in the past can be effectively reduced to isolated cases through the adoption of smart technologies.
Advanced data analytics, on its own part, can help bring about better patient treatment, cost savings, and more effective distribution of resources — which could prove helpful in the management of both long-term and short-term diseases, as well as pandemics.
The efficacy of data analytics at predicting disease outbreaks is anything but a bogus claim as it may be worthwhile to note that x-raying streams of data obtained from social media platforms, online forums, and keyword searches, is believed to have weighed in significantly in predicting the 2012-2013 U.S. flu season a good three months before the first official warning was put out by the Center for Disease Control (CDC). Having said that, it becomes all the more interesting when some thought is given to the kind of impact such an analytical power would have if it is leveraged across the global healthcare system — right down to the individual level.
The Evolution Of Data
Africa, like every developing ecosystem, has favored the manually-intensive, paper-based systems in the record of infections and deaths that accompany major disease outbreaks. This system can be said to be flawed not only because errors are bound to occur but also because it is difficult to clearly understand the reach and impact of these disease outbreaks since the data collected often proves historical and anecdotal at best.
A case for the adoption of smart technologies could be built by citing the earlier mentioned outbreak of Ebola where health workers were mandated by the CDC to instantly submit information connected to the outbreak via text messages in a mobile data collection system. Even though the adoption of this low-cost system came with fewer errors as one of its perks, a bigger achievement came in the form of the detailed maps and population movements information which made it easy for analysts to have a handle on which areas were at most risk and where treatment centers should be set up.
While this approach certainly represented an upgrade from what used to be the case with the paper-based systems of the past, it did have its own Achilles Heel. The mobile data system is more or less historic, and it is not exactly efficient at providing real-time data on population movements that can serve to keep tabs on the developments. This weakness can be thought to have propelled the creation of more reliable systems.
Despite the best efforts and promises of the mobile data system, the glaring truth remains that mobile devices represent just one data source, out of what seems like a plethora of them. Social media, keyword searches, airline ticket sales, media reports, health and physician reports, transactional data from retailers and pharmacies, as well as geospatial data and a number of others, are amongst examples of data sources that can be referred to by health authorities in today’s world.
These data sources can function to point them in the right direction and trigger action that will serve to not only better manage diseases and outbreaks when they do occur, but also see them coming beforehand. And possibly draw up an impact assessment on the amount of damage that could be done if nothing is done to forestall — some sort of doomsday prognosis if a solution is not sought.
By leveraging smart technologies, both structured and unstructured data can be mined, and this can help health authorities keep tabs on infected populations, as well as who they come in contact with, especially in the case of contagious diseases like Ebola.
These technologies can also allow for the measurement of the success of containment policies, as well as education campaigns and treatments, while also giving an indication of the next line of action if efforts have seemed abortive and futile. They could as well give an insight as per the connection of diseases with environmental factors, and direct corrective action accordingly. Through such a system, we might finally be able to act on information to save lives through better understanding and treatment of diseases, and not through gathering the ruins in the aftermath of pandemics.
Until recently, the norm has largely been to extrapolate one standard procedure and incorporate it into the treatment of all cases of a particular infirmity, say cancer or HIV, with little regard for the peculiarities of some cases and the unique medical and health profiles of some individuals. It is not out of place to assert that there exist treatments which are largely regarded as routine and standard but still come up short when administered to certain individuals. And perhaps until recently, this may have been little understood.
But this does not have to be the case as smart technologies like data analytics boast the potential to analyze and create what can be called ‘medical maps’, by taking into cognizance, such biological aspects as chemical composition, physiology, DNA, RNA, and similar others. This can aid health professionals in administering treatments that are attuned to the unique therapeutic needs of each patient, thereby yielding optimum results.
Data analytics can also be beneficial to healthcare in a number of other ways which include the following;
- The data obtained can aid governments in the development of proactive measures towards the promotion and protection of the health of the populace. Through this means, services can also be prioritized with a view to cutting costs and making sure healthcare reach more citizens.
- Through the adoption of personalized therapy, effective treatments and faster results will be the case for patients and this will also bring about fewer hospital admissions.
- Data analytics can help cultivate a better understanding of the impact of lifestyle and diet on health. And medical aid providers can leverage this information as a point of reference. This can help them educate individuals with a view to improving their health and wellbeing, and this could imply lower medical bills.
- Data analytics can layout a pathway to novel innovations and spark insights that can ultimately bring about improvements in treatment outcomes. Medical researchers can be furnished with vital knowledge regarding the genetics of disease-causing germs. This is because data analytics can handle such details as studying data and results obtained from clinical trials, as well as juxtapose the said data with that gotten from academia, industry, and patient records. This may well spark the next big idea in the world of medicine.
Artificial Intelligence (AI) And Machine Learning
As data analytics continue to be increasingly enmeshed with machine learning, intelligent algorithms, and natural language processing, it is something of a given that the efforts of humans in the area of producing faster and more accurate medical diagnostics are expected to be increasingly supplemented by technological innovations.
This notion is supported by the idea that artificial intelligence is already being deployed in medicine where it is seeing some use in the identification of different types of cancer, as well as in the prediction of relapse in cases of leukemia.
Machine learning can aid the extraction of valuable information from staggering amounts of unstructured data which are obtainable from such sources as clinical notes, academic journals, and even scholarly articles. This can lead to the provision of even larger datasets that can potentially transform the medical industry into a proactive entity from its largely reactive stance.
Many a doomsday theorist are quick to hint at the idea that we might be in for a machine invasion and that all these technologies may one day supersede our intelligence and rise against us. We can, however, only wish for more of such stories about the potentials that are yet untapped in data analytics, AI and machine learning.
These smart technologies have an important role to play as they can augment human knowledge and skills with a view to fostering developments that can spark significant improvements in the lives of individuals. At this point, it seems more likely that the machines will actually change our lives for the better and make things a whole lot easier for everyone.