Tag Archives: diagnosis

AI is playing an increasingly important role in diagnostic services in healthcare

Researchers at the University of Bonn have trained software to improve our ability to diagnose rare genetic diseases. The program uses a patient’s portrait photograph and analyzes their facial features — such as characteristically shaped brows, nose, or cheeks — to judge how at risk a certain individual is of these ailments.

Dubbed “GestaltMatcher”, the program has successfully diagnosed known diseases in a trial with a very small number of patients.

Automated diagnosis

“The goal is to detect such diseases at an early stage and initiate appropriate therapy as soon as possible,” says Prof. Dr. Peter Krawitz from the Institute for Genomic Statistics and Bioinformatics (IGSB) at the University Hospital Bonn, corresponding author of the paper.

“We are very happy to finally have a phenotype analysis solution for the ultra-rare cases, which can help clinicians solve challenging cases, and researchers to progress rare disease understanding,” says Aviram Bar-Haim of FDNA Inc. in Boston, USA, co-author of the paper, in a press release. “GestaltMatcher helps the physician make an assessment and complements expert opinion.”

The way we perform diagnosis in healthcare will undoubtedly be revolutionized by AI. And, judging from the results of a new study, that revolution is already upon us.

A large number of very rare diseases are rooted in genetic factors. The same hereditary mutations that encode these diseases, however, ale also expressed phenotypically (in the body’s features) in characteristic ways, for example, in the particular shape of the nose, cheeks, or brows. Obviously, these characteristics vary from one disease to another and can be quite subtle, making them a poor diagnosis element — for human doctors, that is.

AI can however pick up on these subtle features and link them to a known disease. The new software analyzes an individual’s facial features from their profile picture, calculates how similar they are to a known set of characteristics, and uses this to estimate the probability that the person in question bears the genes associated with various conditions. The individual’s clinical symptoms and any available genetic data are also factored into the analysis.

The system is a further development of “DeepGestalt”, which the IGSB team trained with other institutions a few years ago. The team worked to improve its ability to learn using a small sample of patients — and the new program is much better in this regard than its predecessor — which is a key feature for software used to diagnose rare diseases, where sample sizes are very limited. Another key improvement is GestaltMatcher’s ability to consider data from patients who have not yet been diagnosed, allowing it to take into account combinations of features that have not yet been described. This, the team explains, allows it to recognize diseases that were previously unknown, and suggest diagnoses based on data available to it.

The program was trained using 17,560 patient photos, most of which came from digital health company FDNA. Around 5,000 of those photographs were contributed by the Institute of Human Genetics at the University of Bonn, along with nine other university sites in Germany and abroad. All in all, these covered 1,115 different rare diseases.

“This wide variation in appearance trained the AI so well that we can now diagnose with relative confidence even with only two patients as our baseline at best, if that’s possible,” Krawitz says.

The data was turned over to the non-profit Association for Genome Diagnostics (AGD), to allow researchers around the world free access to it.

The application is not far off from being available in doctors’ offices in certain countries such as Germany, the team adds. Doctors can simply take portraits of their patients with a smartphone and use the AI to help them in a diagnosis.

AI detects childhood diseases with doctor-like accuracy

A new artificial intelligence (AI) model exhibited an accuracy comparable to that of experienced doctors.

Artificial intelligence has developed dramatically in recent years. In the medical industry, AI is intensely discussed, though more on the lines of image recognition or analysis than diagnosis. For instance, one such algorithm has been taught to assess a person’s age and blood pressure just by looking at a photo of its eye, whereas another one has been able to detect Alzheimer’s from brain scans even before doctors are able to do so. Now, a team of researchers has expanded the range of AI abilities, developing an algorithm that can diagnose common childhood diseases.

Diagnosis was thought of as a strictly human pursuit, especially in modern medicine, where the range of disease entities, diagnostic testing, and biomarkers has increased tremendously in recent years. Subsequently, clinical decision-making has also become more complex and demanding — to be left only in the hands of capable doctors.

However, in the current digital age, the electronic health record has grown into a massive repository of data, data which can be used to emulate how doctors think. To formulate a diagnosis, physicians frequently use a logical approach to establish a diagnosis. They start from the chief complaint, asking targeted questions related to that complaint and other relevant aspects. Then, they check the background, history, and any other bits of useful information, and offer a diagnosis. Of course, experimented doctors do this almost intuitively, without mentally breaking down all the steps, but in a sense, the whole process is very logical.

So could this approach be emulated on a computer? These researchers think so.

Kang Zhang and colleagues developed an AI-based model that applies an automated natural language-processing (NLP) system, using deep learning techniques to identify clinically relevant information from electronic health records. The model searches health records, mentions of symptoms, any lab results, as well as a library of guidelines for best practices.

They trained and calibrated the model on 1.3 million patient visits to a major health center in Guangzhou, China. They had a total of 101.6 million data points.

After this, the AI was capable of identifying common childhood diseases with an accuracy comparable to that of a doctor. Furthermore, it was capable of spitting them into two categories: common (and less dangerous) conditions such as influenza and hand-foot-mouth disease, and dangerous or life-threatening conditions, such as acute asthma attack and meningitis.

Researchers emphasize that the machine isn’t meant to replace the doctor’s diagnosis, but provide a tool to help streamline health practice. It could, for instance, triage patients by potential disease severity, and serve as a diagnosis aid in complicated cases.

“Although this impact may be most obvious in areas in which there are few healthcare providers relative to the population, such as China, healthcare resources are in high demand worldwide, and the benefits of such a system are likely to be universal.”

The study has been published in Nature Medicine.

Illustration: James Archer/anatomyblue

Fiber optic tubes inserted through your veins could accelerate diagnosis

Illustration: James Archer/anatomyblue

Illustration: James Archer/anatomyblue

The backbone of today’s modern telecommunication industry is held by fiber optic cables. These information highways have accelerated data transfer and help people all over the globe stay connected, but that’s not all they’re good for. A group of international researchers are exploring the idea of using fiber optics as a lab-on-chip device. The tubes would be inserted directly into a patient’s veins, then built-in chemical sensors would detect signature molecules. Essentially fiber optics might become a cheap, ready available light-based diagnosis tool, with far reaching consequences.

If you ever took a blood test you know that it takes at least a couple of days, even weeks before your results come in. That’s because even though collecting your sample only took a minute, the underlying process that follows is far more complicated. Before your cholesterol results are delivered to you, the blood sample needs to pass through bulky and expensive lab equipment, typically operated by a trained technician. This is why blood tests are so damn expensive or why health care as a whole is getting more expensive. What about rural or isolated communities that can’t afford hundreds of thousands of dollars worth of equipment or can’t the staff skilled labor to operate the diagnosis machinery?

One possible solution, proposed since the 1960’s and  in constant development since, is the lab-on-chip. The idea is to manufacturer portable, cheap and easy to use laboratory equipment, preferably the kind that does all the work on the spot in a reliable manner. The lab would include an instrument for reading out results and an array of attachable microsize probes for detecting molecules in a fluid sample, such as blood or saliva. Each probe could be used to diagnose one of many different diseases and health conditions and could be replaced for just a few cents.

A laser transmits light into the fiber’s CORE.
When TARGET MOLECULES bind to receptors on the surface of the fiber, they shift the wavelength and intensity of the resonances
A TILTED GRATING reflects certain wavelengths known as resonances out of the core. These resonances depend on the properties of the grating and the fiber’s surface.

on the tip of the fiber reflects the light remaining in the core back to a spectrometer at the opposite end.

 (not pictured) detects changes in the returning light, revealing the concentration of target molecules.
Illustration: James Archer/anatomyblue
A lab on fiber uses near-infrared frequencies to detect precise concentrations of chemicals or biological molecules in a solution. Here’s how it works. Hover over the numbers for more information.

Using integrated circuits inside the human body doesn’t seem very reliable however. Our insides are wet and semiconductor materials risk becoming corroded, malfunctioning the whole mini-lab array. Also, with all of today’s modern tech we still can’t fit power sources, processors, and transmitters in less than a few square centimeters – that’s much too big to squeeze through blood vessels. A glass optical fiber doesn’t have these limitations, however – more or less the same as the ones that already span the globe, ferrying voluminous streams of data and voice traffic at unmatchable speeds.

Measuring light to find diseases

By using light rather than current to read chemical reactions, a photonic chip works reliably in aqueous solutions, is immune to electromagnetic radiation, tolerates a wide range of temperatures, and poses fewer risks to biological tissues. A group at Carleton University, in Ottawa, Canada is currently developing a practical solution for lab on fiber that is easy to make and outputs precise measurements.

It all begins with a standard communications fiber optic cable which is coated on the inside with tiny amounts of germanium oxide, which raises its refractive index, a measure of the speed of light in a material, while the outer cladding is encased in a protective polymer jacket. Fiber optics are so great for data transmission because light doesn’t get lost through the tube’s walls; instead it gets constantly scattered in the core so the signal remains strong. For their lab on fiber approach, the group however need to bind probe segments to the fiber’s core for it to act as a chemical sensor.

Coating this segment probe with a chemical compound, called a reagent, allows the fiber to bind with  target molecules we want to measure, such as blood enzymes or food additives. As light travels through the fiber, some of the light comes in contact with the molecule binding coating which changes the light’s properties. Then by analyzing the characteristics and magnitude of these changes with a standard spectrometer, we can determine the concentration of molecules reacting with the probe.

According to the researchers involved in the research, the lab on fiber is very accurate as some target molecules were detected with concentrations as low as 2 nanograms per liter which translates to roughly a pinch of table salt in a 25-meter swimming pool. Elsewhere, a group reported in 2012 that using a similar set-up they were able to detect the smallest possible variations in snippets of DNA, suggesting the fiber on lab could be used for quick and accurate genetic screening for complex conditions such as cystic fibrosis, cancers, and certain infections.

It might take a while before we see it applied to humans, though, as there are still many challenges that need to be addressed like how to make the coating thick enough to last for months inside the body. A more immediate application is in the industrial sector where it the fibers could be implemented inside machinery or important pipelines.

Source: Spectrum IEEE