Machine learning could help determine if FAP genetic testing…

Machine learning, a form of artificial intelligence, can help doctors identify people suspected of having familial amyloid polyneuropathy (FAP) and who should undergo genetic testing for the disease, a study in Italy has suggested.

Machine learning uses algorithms to analyze data, learn from its analyzes and make a prediction based on this information.

Heart damage or cardiomyopathy, unexplained weight loss, and gastrointestinal problems are strongly associated with a genetic diagnosis of [FAP]indicating that these symptoms may represent the most sensitive red flags” in diagnosing FAP, the researchers wrote.

I study, Machine learning for early detection of ATTRv amyloidosis in non-endemic areas: a multicenter study from Italywas published in Brain sciences.

Recommended reading

An illustration of bells with the word

In the absence of genetic testing for FAP, diagnostic delays can be common

FAP, also known as hereditary transthyretin amyloidosis with polyneuropathy, is a progressive adult-onset disease caused by mutations in theTTRgene.

This results in the accumulation of toxic clumps of the protein transthyretin in the tissues, particularly in the peripheral nerves those found outside the brain and spinal cord leading to nerve damage or polyneuropathy. Transthyretin aggregates can also build up in the heart, affecting its function (cardiomyopathy).

FAP is characterized by a wide range of disease symptoms that vary greatly between patients and are similar to other diseases, making diagnosis very difficult and, in most cases, delayed, the researchers wrote. Nowadays, several treatment options are available; therefore, avoiding misdiagnosis is critical to initiating therapy in the early stages of the disease.

The use of machine learning in genetic screening for [FAP] could lead to a more sensitive and specific diagnostic approach, thus contributing to a significant reduction of the diagnostic delay [FAP] in non-endemic areas, as well as ensuring early treatment of this rare inherited disease, they added.

To test this hypothesis, scientists in Italy evaluated whether machine learning could help discriminate between patients with and without FAP, thereby helping to identify those who should undergo genetic testing for FAP.

We aim to develop a simple genetic testing guide that can be useful for clinicians, they wrote.

They reviewed information on 397 adults with chronic polyneuropathy and at least one “red flag” that raised suspicion of FAP. All had undergone genetic testing for the disease at a neuromuscular center in Palermo, Messina, Naples or Rome.

After excluding first-degree family members, the analysis included 93 patients (mean age 68 years; 77% men) who tested positive for FAP-causing mutations and 96 age- and gender-matched individuals who tested negative.

Among the mutation-positive cases, the most common symptoms were carpal tunnel syndrome on both hands and problems in the autonomic nervous system (51% for each symptom), followed by ataxia or loss of coordination (48%), loss of unexplained weight (45%) and cardiomyopathy (42%).

The autonomic nervous system is responsible for controlling involuntary bodily functions, such as heart rate, blood flow, and gastrointestinal and bladder function.

To understand how well machine learning could distinguish between polyneuropathy patients who were positive for relevant genetic mutations and those who were negative, the researchers trained a machine learning algorithm called XGBoost (XGB) that uses several “decision trees,” built in sequence, to create a pattern ending.

Good sensitivity, specificity in identifying mutation positive patients

The model distinguished patients with positive and negative test result with 70.7% accuracy, 71.2% sensitivity (true positive rate), and 70.4% specificity (true negative rate). .

The findings suggest the XGB model’s ability to correctly identify both positive and negative samples, the researchers wrote, adding that the model outperformed other standard models.

The researchers then used another AI algorithm to interpret the modeling results and understand which factors are most important in determining who should be recommended to undergo a genetic test for FAP.

They found that ataxia, unexplained weight loss, gastrointestinal symptoms, and cardiomyopathy were strongly associated with a positive genetic test result. In turn, autoimmune disease, ocular involvement, diabetes, renal symptoms, and signs of inferior spinal canal narrowing have been associated with a negative outcome.

While bilateral carpal tunnel syndrome and autonomic dysfunction were the most common symptoms of patients with FAP, these symptoms were also experienced at similar rates among those with a negative test, being similarly distributed in both screen-positive and non-screened patients. negative ones, wrote the team.

Our data supports the use of [AI] algorithms in clinical screening to raise suspicion of [FAP]thereby contributing to a potential reduction in diagnostic delay in non-endemic areas, wrote the researchers.

FAP should be suspected if progressive [polyneuropathy] is observed in combination with ataxia, gastrointestinal problems, unexplained weight loss and cardiomyopathy, they added, recommending further studies to “explore the clinical application of [a machine learning] algorithm” in an early diagnosis.

#Machine #learning #determine #FAP #genetic #testing..
Image Source :

Leave a Comment