While it should not be assumed that using a conversation agent will benefit all information system applications, there are some properties associated with it that make them particularly beneficial for this specific application. Rare disease patients find it difficult to get the correct diagnosis within a reasonable period of time and often need to investigate on their own without much technical knowledge.
NNumerous studies have shown that these problems are not currently being addressed effectively, with the average time to obtain a correct diagnosis being 4.8 years. By using an informed virtual assistant, accessible 24 hours a day and enjoyable, you can support the patient or family member, convey a sense of confidence, which can have motivating effects, and achieve a diagnosis in much less time. Dr. Rachael is able to carry on a normal conversation discussing a variety of topics, as well as having a wealth of knowledge about the symptoms of over 600 rare diseases with the highest incidences currently and we are in the process of increasing this number to 2,000 conditions.
Dr. Rachael is not a conventional bot since she is not programmed with questions and answers detecting patterns or specific words, but is based on a general cognitive engine that uses natural language with a vocabulary of more than 50,000 words (in addition to a dictionary of 30,000 scientific words). This cognitive engine acquires knowledge in the form of natural language, files it in the form of ideograms that describe the meaning of each complete sentence and retrieves said knowledge using a form of abduction, association of ideas, eliminating duplication of ideas and with the help of multivariate logic. of first order. To this cognitive engine has been added a module of frequently asked questions and answers (like that of normal bots), abilities such as access to Wikipedia, Wolfram, the weather forecast, and other functionality associated with conventional assistants such as Siri or Cortana. Therefore, Dr. Rachael is perhaps one of the most advanced virtual assistants today.
IIt is possible to communicate through the keyboard and screen; In addition, we are working on speech recognition (using Sphinx) and speech generation with inflection (using maryTTS). When the user makes a comment, Dr. Rachael will make an appropriate related comment, based on an association of ideas a bit like a person would. If a question posed has a high similarity to a question in the database, Dr. Rachael presents the answer directly to the user. If no such question is found, the closest general comment available is provided. When the user mentions a symptom that Dr. Rachael recognizes, a counter is increased to form a small group of conditions that could be associated with the patient's condition. Each comment can most of the time relate to more than one condition, and when a given statement relates to more than one condition, all associated condition counters are incremented by one. If a given statement is related to a single condition, then only the counter associated with this condition is incremented by one. The final response is a suggestion of the patient's probable conditions that are calculated based on the conditions with a probability greater than 10% that are shown in a list as main conditions along with their estimated probability, so that a specialist can evaluate them further.
At the end of each session, the user is provided with a table listing all conditions with a probability greater than 10% for which the user or family member may be at risk; as well as a previously formulated general description of each condition. This allows the patient or family to get a firm suggestion even if the session lasts a long time or is even completed over many sessions, hopefully helping in the right direction towards a proper diagnosis in the shortest time possible. This type of feedback is an integral part of Dr. Rachael's approach, which has previously been applied to eating disorder diagnosis, mental health, and personality testing.