Artificial Intelligence in Medicine

AI for Diagnostics, Drug Development, Treatment Personalisation, and Gene Editing

Machine Learning has made great advances in pharma and biotech efficiency. This post summarizes the top 4 applications of AI in medicine today:

1. Diagnose diseases

Correctly diagnosing diseases takes years of medical training. Even then, diagnostics is often an arduous, time-consuming process. In many fields, the demand for experts far exceeds the available supply. This puts doctors under strain and often delays life-saving patient diagnostics.

Machine Learning – particularly Deep Learning algorithms – have recently made huge advances in automatically diagnosing diseases, making diagnostics cheaper and more accessible.

How machines learn to diagnose

Machine Learning algorithms can learn to see patterns similarly to the way doctors see them. A key difference is that algorithms need a lot of concrete examples – many thousands – in order to learn. And these examples need to be neatly digitized – machines can’t read between the lines in textbooks.

So Machine Learning is particularly helpful in areas where the diagnostic information a doctor examines is already digitized.

Such as:

  • Detecting lung cancer or strokes based on CT scans
  • Assessing the risk of sudden cardiac death or other heart diseases based on electrocardiograms and cardiac MRI images
  • Classifying skin lesions in skin images
  • Finding indicators of diabetic retinopathy in eye images

Since there is plenty of good data available in these cases, algorithms are becoming just as good at diagnostics as the experts. The difference is: the algorithm can draw conclusions in a fraction of a second, and it can be reproduced inexpensively all over the world. Soon everyone, everywhere could have access to the same quality of top expert in radiology diagnostics, and for a low price.

More advanced AI diagnostics are coming soon

The application of Machine Learning in diagnostics is just beginning – more ambitious systems involve the combination of multiple data sources (CT, MRI, genomics and proteomics, patient data, and even handwritten files) in assessing a disease or its progression.

AI won’t replace doctors anytime soon

It’s unlikely that AI will replace doctors outright. Instead, AI systems will be used to highlight potentially malignant lesions or dangerous cardiac patterns for the expert – allowing the doctor to focus on the interpretation of those signals.

2. Develop drugs faster

Developing drugs is a notoriously expensive process. Many of the analytical processes involved in drug development can be made more efficient with Machine Learning. This has the potential to shave off years of work and hundreds of millions in investments.

AI has already been used successfully in all of the 4 main stages in drug development:

Stage 1: Identify targets for intervention

The first step in drug development is understanding the biological origin of a disease (pathways) as well as its resistance mechanisms. Then you have to identify good targets (typically proteins) for treating the disease. The widespread availability of high-throughput techniques, such as short hairpin RNA (shRNA) screening and deep sequencing, has greatly increased the amount of data available for discovering viable target pathways. However, with traditional techniques, it’s still a challenge to integrate the high number and variety of data sources – and then find the relevant patterns.

Machine Learning algorithms can more easily analyse all the available data and can even learn to automatically identify good target proteins.

Stage 2: Discover drug candidates

Next, you need to find a compound that can interact with the identified target molecule in the desired way. This involves screening a large number – often many thousands or even millions – of potential compounds for their effect on the target (affinity), not to mention their off-target side-effects (toxicity). These compounds could be natural, synthetic, or bioengineered.

However, current software is often inaccurate and produces a lot of bad suggestions (false positives) – so it takes a very long time to narrow it down to the best drug candidates (known as leads).

Machine Learning algorithms can also help here: They can learn to predict the suitability of a molecule based on structural fingerprints and molecular descriptors. Then they blaze through millions of potential molecules and filter them all down to the best options – those that also have minimal side effects. This ends up saving a lot of time in drug design.

Stage 3: Speed up clinical trials

It’s hard to find suitable candidates for clinical trials. If you choose the wrong candidates, it will prolong the trial – costing a lot of time and resources.

Machine Learning can speed up the design of clinical trials by automatically identifying suitable candidates as well as ensuring the correct distribution for groups of trial participants. Algorithms can help identify patterns that separate good candidates from bad. They can also serve as an early warning system for a clinical trial that is not producing conclusive results – allowing the researchers to intervene earlier, and potentially saving the development of the drug.

Stage 4: Find Biomarkers for diagnosing the disease

You can only treat patients for a disease once you’re sure of your diagnosis. Some methods are very expensive and involve complicated lab equipment as well as expert knowledge – such as whole genome sequencing.

Biomarkers are molecules found in bodily fluids (typically human blood) that provide absolute certainty as to whether or not a patient has a disease. They make the process of diagnosing a disease secure and cheap.

You can also use them to pinpoint the progression of the disease – making it easier for doctors to choose the correct treatment and monitor whether the drug is working.

But discovering suitable Biomarkers for a particular disease is hard. It’s another expensive, time-consuming process that involves screening tens of thousands of potential molecule candidates.

AI can automate a large portion of the manual work and speed up the process. The algorithms classify molecules into good and bad candidates – which helps clinicians focus on analysing the best prospects.

Biomarkers can be used to identify:

  • The presence of a disease as early as possible - diagnostic biomarker
  • The risk of a patient developing the disease - risk biomarker
  • The likely progress of a disease - prognostic biomarker
  • Whether a patient will respond to a drug - predictive biomarker

3. Personalize treatment

Different patients respond to drugs and treatment schedules differently. So personalized treatment has enormous potential to increase patients’ lifespans. But it’s very hard to identify which factors should affect the choice of treatment.

Machine Learning can automate this complicated statistical work – and help discover which characteristics indicate that a patient will have a particular response to a particular treatment. So the algorithm can predict a patient’s probable response to a particular treatment.

The system learns this by cross-referencing similar patients and comparing their treatments and outcomes. The resulting outcome predictions make it much easier for doctors to design the right treatment plan.

4. Improve gene editing

Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR), specifically the CRISPR-Cas9 system for gene editing, is a big leap forward in our ability to edit DNA cost effectively – and precisely, like a surgeon.

This technique relies on short guide RNAs (sgRNA) to target and edit a specific location on the DNA. But the guide RNA can fit multiple DNA locations – and that can lead to unintended side effects (off-target effects). The careful selection of guide RNA with the least dangerous side effects is a major bottleneck in the application of the CRISPR system.

Machine Learning models have been proven to produce the best results when it comes to predicting the degree of both guide-target interactions and off-target effects for a given sgRNA. This can significantly speed up the development of guide RNA for every region of human DNA.

Summary

AI is already helping us more efficiently diagnose diseases, develop drugs, personalize treatments, and even edit genes.

But this is just the beginning. The more we digitize and unify our medical data, the more we can use AI to help us find valuable patterns – patterns we can use to make accurate, cost-effective decisions in complex analytical processes.

Energy Transmission

Anticipating and Preventing Power Grid Failure

Massive power outages cause chaos for the general public, and they cost utility providers roughly $49 billion a year.

This wouldn’t be much of a problem if massive power outages were rare, but outages affecting more than 50,000 people have increased dramatically in recent years. This means utility companies need to find new ways of anticipating and managing these outages.

These days, smart grids are producing massive amounts of data, which means predicting and managing outages is easier than ever. Unlike traditional power grids, which are one-directional (meaning they only transmit power in one direction), smart grids are two-directional. They can capture data from every possible source in the grid at the same time as they’re providing electricity. They collect and monitor data from sources like smart meters, IoT devices, and power generation stations, providing a clear, real-time look at power usage.

Machine learning can use this data to anticipate and prevent massive power outages in the grid. Machine learning helps identify non-obvious patterns in the data that can be a precursor to grid failure, which helps maintenance teams preempt failure.

Balancing the Grid

Balancing the grid — making sure energy supply matches energy demand — is one of the most important jobs a transmission operator has. But renewable energy sources depend heavily on the weather, making them harder to predict.

Transmission operators spend millions each year fixing planning mistakes that lead to producing too much or too little power. In hybrid systems — which rely on both renewable energy sources and fossil fuels to generate electricity — these mistakes have to be corrected at the last minute by buying more energy or compensating power plants for the excess.

Machine learning is the most accurate method available to forecast the output of renewable energy. Advanced methods, like Long Short-Term Neural Networks (LSTMs), can weigh the many factors involved — wind, temperature, sunlight, and humidity forecasts — and make the best predictions. This saves money for operators and preserves resources for power plants.

Preventing Blackouts and Brownouts With Real-time Monitoring and AI Prediction

Power grids have a lot of obstacles to overcome in providing continuous energy to customers. Weather patterns, usage, internal failure, even wildcard incidents like lightning strikes and interference from wild animals can all affect power delivery.

Machine learning is increasingly being used to help predict potential brownout and blackout conditions. By feeding historical data into the AI and running Monte Carlo simulations to predict potential outcomes, grid operators can use machine learning to identify conditions that could lead to grid failure. And they can act accordingly.

Sensors like phase measurement units (PMU) and smart meters can provide usage information in real-time. When combined with both historical and simulation data, AI can help mitigate potential grid failure, using techniques like grid balancing and demand response optimization. Incidents that would otherwise have affected millions of people can be contained to a smaller area and fixed faster for less money.

Differentiate Power System Disturbances from Cyber Attacks

Cyber attacks are increasingly used to target important infrastructure, like shutting down hospitals with Ransomware attacks (when attackers break into the system and lock legitimate users out until a ransom is paid). With utility grids, a cyber attack can have widespread consequences and affect millions of users.

Detecting these attacks is critical.

Developers are using machine learning to differentiate between a fault (a short-circuit, for example) or a disturbance (such as line maintenance) in the grid and an intelligent cyber attack (like a data injection).

Since deception is a huge component of these attacks, the model needs to be trained to look for suspicious activity – things like malicious code or bots – that get left behind after the deception has occurred.

One such method uses feature extraction with Symbolic Dynamic Filtering (an information theory-based pattern recognition tool) to discover causal interactions between the subsystems, without overburdening computer systems. In testing, it accurately detected 99% of cyber attacks, with a true-positive rate of 98% and a false-positive rate of less than 2%. This low false-positive rate is significant because false alarms are one of the biggest concerns in detecting cyber attacks.

Balance Supply and Demand

Utility providers are looking for ways to better predict power usage while maintaining maintaining energy supply at all times. This becomes critical when renewable power sources (like solar or wind) are introduced into the grid.

Because these renewable power sources rely on elements beyond human control (like the weather), utility providers know they can’t always rely on renewables for continuous production. Knowing precisely when demand levels will peak allows utility providers to connect to secondary power sources (like conventionally generated electricity) to bolster the available resources and ensure constant service provision.

More and more utility providers are turning to machine learning for help. We can feed historical data into machine learning algorithms -- like Support Vector Machines (SVM) -- to accurately forecast energy usage and ensure sufficient levels and constant supply.

Detect Power Grid Faults

Current methods for detecting faults in the grid consume a lot of unnecessary time and resources. This creates a situation where power transmission is interrupted and customers are without electricity while faults are first located, then fixed.  

Machine learning can find faults quickly and more accurately helping you minimize service interruption for your customers.. Support Vector Machines (SVM) are combined with Discrete Wavelet Transformation (DWT) to locate faults in the lines using a traveling wave-based location method.

When we apply  DWT (a form of numerical and functional analysis that captures both frequency and location information) to the transient voltage recorded on the transmission line, we can determine the location of the fault by calculating aerial and ground mode voltage wavelets. So far, this method has detected fault inception angles, fault locations, loading levels, and non-linear high-impedance faults for both aerial and underground transmission lines.

Detect Non-Technical Power Grid Losses

In the energy world, “non-technical losses” means energy theft or fraud from the system.

There are two common types of non-technical losses. The first is when a customer uses more energy than the meter reports. The second involves rogue connections stealing energy from paying customers. To pull off this theft or fraud, bad actors can bypass smart meters completely or insert chips into the system that change how meters track energy use. Meter readers can also be bribed to report lower numbers (though thanks to smart meters, this is increasingly hard to do).

Because these non-technical losses cost $96 billion annually, utility providers are turning to machine learning to combat the problem.

We can help utility providers mine historical customer data to discover irregularities that indicate theft or fraud. These can be things like unusual spikes in usage, differences between reported and actual usage, and even evidence of equipment tampering.

Energy Distribution

Better Predict Energy Demand

Accurately predicting customers’ energy needs is critical for any utility provider. To date, we haven’t found an adequate solution for bulk energy storage, which means energy needs to be transmitted and consumed almost as soon as it’s produced.

We're using machine learning to increase the accuracy of these predictions. Historical energy use data, weather forecasts, and the types of businesses or buildings operating on a given day all play a role in determining how much energy is used.

For example, a hot summer day mid-week means more energy usage because office buildings run air conditioning at a high capacity. Weather forecasts and historical data can help identify those patterns in time to prevent rolling blackouts caused by air conditioners in the summer.

Machine Learning finds complicated patterns in the various influencing factors (such as day, time, predicted wind and solar radiation, major sports events, past demand, mean demand, air temperature, moisture and pressure, wind direction, day of the week, etc.) to explain the development of demand. Because machine learning finds more intricate patterns, its predictions are more accurate. This means energy distributors can increase efficiency and decrease costs when they buy energy – without having to make expensive adjustments.

Energy Generation

Predict Turbine Malfunction

Wind is a great renewable energy source, but wind turbine maintenance is notoriously expensive. It accounts for up to 25% of the cost per kWh. And fixing problems after they occur can be even more expensive.

Machine learning can help you get ahead of this problem. The goal is to reduce maintenance costs by catching problems before the turbine malfunctions. This is particularly important when wind farms are located in hard-to-access places, such as the middle of the ocean, which makes repair costs even higher.

Real-time data gathered with Supervisory Control and Data Acquisition (SCADA) can help identify possible malfunctions in the system far enough in advance to prevent failure.

For example, data from sensors found within the turbines – such as oil, grease, and vibration sensors – have been used to train machine learning models to identify precursors to failure, such as low levels of lubricant.

This method can train machine learning models to predict failures up to 60 days in advance.

Consumption / Retail

Accurately Predict Energy Prices

As personal power generation (using solar or wind power) gets easier and cheaper, consumers and businesses are increasingly producing their own power.

Personal power generation allows people to make, consume, and store their own energy. Depending on where they live, they may even be able to sell surplus power back to the local power utility.

Machine learning can help find the best time to produce, store, or sell this energy. Ideally, energy should be consumed or stored when prices are low and sold back to the grid when prices are high.

By looking at historical data, usage trends, and weather forecasts, machine learning models have made accurate predictions on an hourly basis. People with personal and business energy generation systems can use these predictions to make strategic decisions about whether to use, store, or sell their energy.

For example, Adaptive Neural Fuzzy Inference System (ANFIS) has been used to predict short-term wind patterns for wind power generation. This allows producers to maximize energy production and sell it when energy prices are at their peak.

Reduce Customer Churn

In open energy markets, where customers have a choice of utility providers, understanding which customers are going to churn out can be critical. Churn rates, which is the percentage of customers who stop using your service in a year, can be as high as 25%. Being able to predict churn and stay ahead of it is essential to survival.

Machine learning is helping utility owners predict when a customer is getting ready to churn out. By using techniques such as Cross-industry Standard Process for Data Mining (CRISP-DM), AdaBoost, and Support Vector Machines, as well as historical usage data, utility providers can identify key indicators of whether or not a customer is going to churn. These indicators include things like customer satisfaction, employment status, energy consumption, home ownership or rental status. A change in any of these can indicate a customer is getting ready to terminate their service.

When these indicators are identified far enough in advance, it’s possible to avoid churn by working with customers to solve any problems they’re experiencing.

Energy Trading

Predict Energy Prices

Just like natural gas and oil, wholesale energy is a market commodity. So naturally it's important for traders to be aware of market fluctuations and pricing when it comes to buying and selling energy.

To help make sense of the massive amounts of data used to make trading decisions, traders are increasingly turning to machine learning.

A mix of statistical analysis and machine learning can help commodity traders make better predictions. Classical statistical analysis techniques like time series analysis, Seasonal Autoregressive Integrated Moving Average (SARIMA), and regression models are used to deal with the data. And machine learning makes connections between the various data points.

What’s more, machine learning trains itself to make increasingly accurate predictions using the constant flow of real-time data.

Keep reading

No items found.
No blog posts found.