Aalia Technologies, breaking language barriers through a medical voice assistant

Aalia Technologies is a startup that offers a solution to the difficulties caused by language barriers in the medical environment. It has developed AaliaTech, a medical voice assistant that translates the practitioner’s questions into the patient’s native language, taking into account their medical and cultural context. 

The Observatory of the French Language estimates that 3% of the population living in France have no, or very little, knowledge of French. More than 2 million people thus face difficulties in accessing basic services such as housing or health. The French National Authority for Health reports that one in five patients consider the language barrier as one of the main obstacles in accessing healthcare. The difficulty in understanding problems lengthens medical appointments, sometimes distorts practitioners’ diagnoses and thus increases the number of hospitalisations and unnecessary tests. As a result, some patients do not seek treatment. 

The voice assistant technology is based on three features: 

• Voice recognition – The solution can transform spoken words into written text. Naturally it is also possible to directly type the text you wish to translate.
• Automatic Natural Language Processing (NLP) – This technology allows the machine to understand the meaning of the text received. This requires a sophisticated combination of linguistics, computer science and artificial intelligence (AI). AI allows the solution to be autonomous and to improve its translations through machine learning providing an appropriate translation.
• Voice synthesis – The solution delivers an oral version of the translation (in addition to the written version). This enables illiterate patients to understand what the doctor is saying.

According to the Academic Emergency Medicine (AEM), a patient who does not speak the same language as the health care team has a 70% higher chance of being admitted to hospital, a figure that is much lower when an interpreter is involved. However, professional interpreters are not available 24 hours a day and their service is expensive: between €25 and €30 for 15 minutes of telephone interpreting. Though non-French-speaking patients can be assisted by a professional interpreter or a bilingual relative, this extra organisational effort can be cumbersome and/or costly, especially when the number of appointments grows. In addition to the financial aspect, requesting an interpreter inevitably compromises medical confidentiality and increases the length of medical appointments by 30 to 50% (AEM), thus contributing to the overcrowding of emergency services.

Alerted by several health professionals to the consequences of language barriers in the medical environment, Samah Ghalloussi put her skills in programme development and data science at their service. And so AaliaTech was born, a medical voice assistant translator for use by practitioners. Samah Ghalloussi set up his project in close collaboration with many healthcare professionals in order to be as close as possible to the field and to continuously improve the solution thanks to user feedback.

AaliaTech is an artificial intelligence programme that records the practitioner’s words and translates them into the language of the patient. After selecting a language, all you have to do is ask your question in writing or orally and a written or audio translation, adapted to the medical and cultural context of the patient, is proposed after a few seconds. The programme also engages in reformulating the practitioner’s question to ensure a total match between what the system has understood and what it translates. In this way, the proposed translation corresponds exactly to the question asked and medical confidentiality is securely maintained. The tool is more aimed at the practitioner, as it is easier to anticipate what they are saying – questions or diagnoses – than what the patient answers. This guarantees the quality of the translations.

To make AaliaTech accessible, a mobile application you can find on Android and iOS has been created. At the same time, Samah Ghalloussi and his team are striving to enrich the database by progressively integrating less widespread languages and dialects. Today, AaliaTech can translate into 65 different languages and dialects.

AaliaTech decided to make its solution known to medical centers and hospitals, particularly for their emergency services. It regularly happens that non-French speaking patients arrive there in the middle of the night without being able to be taken care of due to a lack of available interpreters. AaliaTech thus enables hospitals to improve their operational and financial efficiency by being able to receive an non-French speaking patient at any time.

Today, the solution is tested by a diverse panel of healthcare professionals (in France and Morocco) who contribute to its improvement by sharing their experience and business expertise. AaliaTech is currently being tested on two French Red Cross learning sites: a migration center in Calais and a follow-up care and rehabilitation centre in Bourg-en-Bresse. In particular, this tool helps the Association to communicate with illiterate people.