Newsgate360 – Riyadh: Mark Lambrecht, Director, SAS Global Health and Life Sciences Practice talked about how could artificial intelligence help tackle COVID-19 outbreak and said that during critical event situations, leaders of organizations in many industries turn to technology to address new challenges. AI – machine learning in particular – holds great promise for improving the ability to reduce the impact of infectious diseases. Machine learning is designed to consider large amounts of data, find patterns in that data and detect anomalies, and in many cases offer predictions. In the case of disease outbreaks like COVID-19, AI and machine learning are incredibly valuable in helping equip and enable better decision-making, particularly in two areas.
First, AI helps to automate data analysis, identify patterns and build models on risk factors to aid in scenario analysis of infection transmission. AI especially excels at seeing connections and correlations that humans would not find or observe. To increase the accuracy and precision of AI, diverse information sources are combined into analytical data sets, e.g. official incidence records, clinical emergency data, physician’s records, social media, flight records, school absence, and sales data of anti-fever medication.
Additionally, AI and advanced analytics can help in automation tasks for physicians and citizens, such as in the use of chatbots to rapidly survey citizens for symptoms. These systems can deal with thousands of patients per hour, unlike call centers, and generate high quality reports. AI can also help by examining data from similar viral diseases and using that data to predict what types of vaccines and medicines might be more effective. It can be applied to clinical discovery, trials and manufacturing to ensure safe and efficient antiviral medicines and vaccines.
Expertise into these techniques does not come overnight – it requires knowledge, organized data streams and a proactive attitude that deliver great value when a pandemic such as COVID-19 strikes.
On how can data analytics of current patient data assist pharmaceutical companies and research institutes in advancement and expedition of medical research towards a vaccine, Lambrecht spoke on developing new treatments, creating vaccines and antiviral medications for newly discovered viruses is a difficult and time-consuming process, traditionally involving lots of trial and error. AI and data analytics can help in the clinical discovery, trials and manufacturing to ensure safe and efficient antiviral medicines and vaccines. Data analytics can leverage real world evidence at every stage of the product life cycle – from finding new areas for discovery, to developing drugs and therapies more efficiently, to better understanding product and drug safety, effectiveness, adherence, and economic and societal value and get better, safer therapies to market faster. More specifically, data analytics can:
- Quickly combine and analyze huge quantities of data using predictive analytics with embedded AI.
- Use patented analytic models to uncover emerging issues with greater speed and accuracy than traditional early warning techniques, and proactively take corrective action to improve outcomes.
- Control processes using predictive modeling techniques – e.g., neural networking, regression analysis and clustering.
- Automatically monitor all pharma-manufacturing processes to help ensure continuous product quality.
Lambrecht, also spoke about hospitals and airports and how they already use predictive analytics technologies to better predict when nurses and doctors will be needed, score patients for the risk to develop sepsis, or score travelers for possible security or health issues. When starting to implement predictive analytic technology, an analytics culture needs to be established and impactful use cases need to be identified. This requires considerable investment – a true data-driven analytics strategy supported by hospital or airport management over years. These investments need to occur well before a pandemic like SARS-CoV-2 starts.
In the health care industry, where human lives hang in the balance every day, there is arguably no more important time than now to make use of all available resources. By using predictive analytic models to more efficiently allocate available bed space and hospital resources, even to neighboring health systems, health officials hope to reduce mortality rates in areas hardest hit by the virus. These analytical methods include:
- Applying and refining epidemiological models to project COVID-19 infections within a region.
- Predicting the potential numbers of infected people that will require medical intervention and what the level of care might look like.
- Forecasting the number of required caregivers based on scenario modeling.
- The insights generated by analytics could lead health care systems to take several actions, or a combination of them:
- Repurposing beds for a higher level of care.
- Using day surgery/outpatient centers as new bed space.
- Exploring the possibility of reopening shuttered facilities.
- Reallocating clinicians, vital equipment and supplies to where they’re needed most.
In addition, Lambrecht explained how AI can help avoid the potential destabilization of the food system amidst COVID-19. This pandemic is a wake-up call to all industries, including retailers and their consumer-packaged goods (CPG) suppliers. Patterns in consumer demand are varying across countries and product categories more so than usual. Today’s best forecasting and demand planning practices incorporate a wide variety of causal factors that provide insights to shifting demand. These factors might include changes in promotional or marketing strategies that would apply to specific brands or customers. Or they may represent economic or competitive activity that would affect an entire product category. Leading forecasting technologies leverage automated machine learning and artificial intelligence (AI) to integrate and reconcile these forecasts up and down a business hierarchy.
An organization with these practices in place has instant visibility on which products, plants and customers are most significantly affected by the disruption. For example, many retailers are experiencing huge spikes across local geographies in excess of 800% for over-the-counter cold and flu medicines while food items are in excess of 25-50%. A CPG company can quickly determine the impact of extreme pantry loading or hoarding, identify substitutability between products and categories or any significant shift between online and in-store shopping patterns.
On how can AI assist medical supply chains assist with the prevention of over/undersupply, he said: If the event is unprecedented like the COVID-19 pandemic, progressive demand planners across all industries, especially medical supply, quickly go into high-level “best, middle, and worse case” scenario mode to understand the range of potential effects while letting the models reconcile the hierarchies. As a company progresses through the event, the models will start to pick up on the latest trends and the range of likely outcomes will start to shrink. Models can also help to optimize scarce resources over hospitals and patients to maximize utilization and avoid unnecessary suffering.
It’s no longer just about collaborating across internal departments: it’s about humans partnering with machines in an autonomous supply chain with full transparency. There is a mandate to leverage the collaboration between humans and machines to fight an invisible enemy that threatens our way of life and our economy like none other. Together, we can detect abnormalities faster, identify immediate shifts in demand patterns, and make decisions in real time.
On the global data being stored and analyzed centrally and if it can help prevent another pandemic, Lambrecht said that along with the heroic work of individuals on the front lines of the public health response, data and analytics are the lifeblood for decision-making during infectious-disease outbreaks. During critical event situations such as the COVID-19 global pandemic, leaders of organizations across all industries turn to data and analytics to help prepare, respond and recover.
Governments hold much of the critical data needed to understand current conditions during an outbreak, but analytics offer an ability to synthesize this data with other non-health (social indicators) and non-governmental data to get the most insights from this unified data. Analytics can provide insights about the spread of a disease and the effectiveness of public health action, which can improve the response.
Collaboration and rapid information sharing are essential to have the best chance of predicting, preventing, responding to and recovering from infectious disease outbreaks. Public health and scientific data must be shared freely and rapidly with stakeholders and key decision makers so they can act. Events like the COVID-19 pandemic require public and private sectors to work closely together and share data to limit disease spread and save lives.
While there is no centralized data collection and sharing initiative on a global scale, there are many open source data sets and models online that are being used globally to share and analyze data. The more data people have about case counts, incidence and mortality rates, how a disease spreads and how contagious it is, the better decisions they can make to limit, prevent and treat the disease.