24 Jul, 2017

Algorithms Detect Heart Disease Faster Than Humans


The latest artificial intelligence trend in the healthcare industry has the ability to detect heart problems in patients using algorithms.

This stride in the healthcare industry has been developed by Stanford University and is making rapid movements using innovation and digital transformation that ultimately improves patient care.

This new innovation can perform tasks such as:

  • Diagnose 14 types of heart rhythm defects (called arrhythmias)
  • Sort through data from rural locations, where people don’t have access to cardiologists.

Researchers are saying that this technique has the potential to be even more effective than humans, providing data that leads to accurate pinpointed patient diagnosis.

“Recently, artificial intelligence and deep learning have upped the ante, promising algorithms that can not only make data-based healthcare decisions free from human error, but also process sets of data far more vast than any one human being ever could.” According to Gizmodo.

Why Algorithms?

An algorithm is a form of artificial intelligence that is used in healthcare made up of any formula or computation that can be proven to be useful in the medical field.

“Increasingly, medical algorithms are working behind the scenes to aid in diagnosis, treatment, short- and long-term prognosis, care management, and claims processing.” Healthcare Dive reports. 

Stanford University Machine Learning Group leveraged the power algorithms have on this industry by developing their very own in order to help patients with arrhythmias to receive heart diagnosis data quickly.

In a normal doctor visit for patients with arrhythmias, they will receive an electrocardiogram which is developed to reveal the root of the problem.

These ECG’s can come in the form of a wearable device, making it easy for patients to be mobile for two weeks while being detected.

The problem with using ECG’s is that it takes hours to collect the data needed to spot arrhythmias, which can create life or death situations for patients, often times being impossible to differentiate between harmless and harmful heart rhythms.

“However, a normal ECG does not rule out serious heart disease. For example, you may have an irregular heart rhythm that ‘comes and goes’ and the recording can be normal between episodes. Also, not all heart attacks can be detected by ECG.” According to PatientInfo. 

With that being said, Stanford University adjunct professor, Andrew Ng, sought to solve this problem by integrating artificial intelligence in heart detection strategies.

How Does it Work?

Andrew Ng collaborated with the heartbeat monitor company iRhythm to use data collected by ECG’s wearable monitor.

 “The group took approximately 30,000; 30-second clips from various patients wearing a small chest patch for two weeks and carry out their normal day-to-day activities while the device records each heartbeat for analysis.” HITConsultant reports. 

By using this method, information regarding the patient’s heart condition was proven to be diagnosed as accurately as cardiologists’ diagnoses.

 “The researchers then compared which more closely matched the consensus opinion – the algorithm or the cardiologists working independently. The researchers found that the algorithm is competitive with the cardiologists, and able to outperform cardiologists on most arrhythmias.”

The researchers worked with 6 different doctors in order to prove how accurate the algorithms are, which were able to compare the two diagnoses.

Rhythm and noise were the two important features that characterized arrhythmias.

Noises were labeled, identified and distinguished, displaying the pattern of the activity of the heart.

“The noise label is assigned when the device is disconnected from the skin or when the baseline noise in the ECG makes identification of the underlying rhythm impossible. The morphology of the ECG during a single heartbeat, as well as the pattern of the activity of the heart over time, determine the underlying rhythm.” Stanford announced in its paper. 

The findings included:

  • Algorithms have the ability to outperform cardiologists.
  •  Heart problems can be detected using precise data found through rhythm and noise.
  • A model was developed that exceeds cardiologists performance while detecting arrhythmias.

“Given that more than 300 million ECGs are recorded annually, high-accuracy diagnosis from ECG can save expert clinicians and cardiologists considerable time and decrease the number of misdiagnoses. Furthermore, we hope that this technology coupled with low-cost ECG devices enables more widespread use of the ECG as a diagnostic tool in places where access to a cardiologist is difficult.”  Stanford announced in a report. 

Find the full report developed by Stanford University here.

What Does This Mean?

Integrating artificial intelligence into the healthcare industry has the ability to replace doctors altogether because it can perform tasks that doctors can do, but faster and more efficient.

“AI in healthcare and medicine could organize patient routes or treatment plans better, and also provide physicians with literally all the information they need to make a good decision.” TMF reports. 

This means that the healthcare industry is transforming how patient and doctor relationships are carried out, changing the priorities of patients and exposing new tools that will improve the industry.


The Millennium Alliance is pleased to announce that application for our bi-annual Digital Healthcare Transformation Assembly is now open! Seats are reserved for the C-Level executives leading the digital healthcare revolution to come together on December 5-6, 2017.

It is clear that we are entering a time where digital transformation is being integrated into the healthcare industry, changing the landscape and how tasks are carried out, such as detecting sickness. Giving patients the ability to receive data regarding their health in a quick and accurate way, shifts priorities and creates new opportunities for providers.

If you are a business professional in the healthcare industry, it is crucial to understand the new technologies that are sweeping the market, in order to be informed and ahead of the digital wave. The need for customer-centric transformation is more vital than ever, to be open and transparent to patients as they navigate new policies. Healthcare systems and insurance carriers are being forced to respond to new demand rapidly.

The Digital Healthcare Transformation Assembly has been created to provide new, innovative knowledge for all of our partners, affiliates, and members. Joining together with like minded individuals in our unique format helps develop new relationships and learn cutting edge intelligence to take back home and help tackle the biggest business issues of today.

Trackback URL: https://mill-all.com/blog/2017/07/24/algorithms-detect-heart-disease/trackback/

Leave a comment:

Your email address will not be published.