Scientists design two AI algorithms to improve early detection of cognitive impairment

Researchers of the Pharmacy and Mathematics departments of the CEU UCH university in Valencia have collaborated in the design of two artificial intelligence algorithms that improve the screening of positive cases in the early detection of cognitive impairment in chemists. These algorithms also make it possible to identify the main risk factors of developing some type of dementia in the future. The study, published by scientific journal Frontiers of Pharmacology, lies within the framework of the research project financed with the kNOW Alzheimer grant, headed by Pharmacy Degree Vice-Dean Lucrecia Moreno in collaboration with researchers María Dolores Guerrero and Maite Climent, president of the SEFAC-CV, and professors of the Embedded Systems and Artificial Intelligence Group of the CEU UCH, Juan Pardo and Javier Muñoz.

In the preliminary phase of the study, 728 people over the age of 65 were assessed in the offices of chemists through two internationally-validated tests for the detection of cognitive impairment: the Short Portable Mental State Questionnaire (SPMSQ) and the Mini-Mental State Examination (MMSE), in its Spanish version. Through these two tests, conducted in 14 Valencian chemists associated with SEFAC, the Spanish Society of Family and Community Pharmacy, a total 128 cases of possible minor cognitive impairment were detected, a 17.4% of the total, who were referred to primary health care centres so they could be diagnosed and then sent to the neurologist. Furthermore, a total 167 analysis variables were registered for early detection with these tests. Among them, factors like age, sex, the educational level, the amount of daily sleeping hours, reading habits, subjective complaints of memory loss and medication.

Algorithm to minimise false negatives
In the current phase of the study, which has been published in the Frontiers in Pharmacology journal, the results obtained in the tests conducted on 728 elderly people, have been subjected to a massive screening procedure, thanks to the designing of two mathematic algorithms or decision trees. The first is a discriminating decision tree that allows the identification of false negative test results, or cases of people who could suffer minor cognitive impairment despite the results of the test, as well as ruling out false positives. This first algorithm will therefore allow for an improved screening of the assessment conducted in chemists with the tests, in order to refer to doctors the positives detected, for a clinical diagnosis. It will also help improve the monitoring of people who, even though they admit suffering from memory loss symptoms, don't test positive.

Predictive model and risk factors
The second algorithm has been designed to define patterns and design a predictive model, detecting those of the 167 assessment variables obtained by the two tests which are the most significant for the early detection of cognitive impairment. This predictive model is the one which makes it possible to identify the most prominent risk factors in relation to minor cognitive impairment.

Applied to the over 700 cases analysed, this predictive model has confirmed as risk factors for screening and, therefore, as the most significant variables for the detection of minor cognitive impairment, the following: being a woman, sleeping more than 9 hours a day, being over 79 years of age, and low amounts of reading. Furthermore, consuming psychoanaleptic, nootropic or anti-depressant medicines as well as anti-inflammatory drugs are other examples of the most relevant variables detected by the algorithm.

Research team
As professor Lucrecia Moreno highlights, "the early detection of cognitive impairment, as a preliminary phase of the development of dementias such as Alzheimer's disease is essential in societies such as ours, where population is ageing. The offices of chemists are appropriate places for screening people with clear risk factors, especially if we provide the appropriate computer tools, such as the algorithms we have designed in this study, for the processing of the data resulting from assessing elderly people."

Doctor Lucrecia Moreno has headed the research team comprised of researchers Maite Climent, communitary pharmacist; María Dolores Guerrero, professor at the Department of Pharmacy of the CEU UCH; and professors of the Department of Mathematics, Physics and Technological Sciences of the CEU UCU, Juan Pardo Albiach, head researcher of the ESAI group, and Javier Muñoz Almaraz, member of the group.

Comments

The opinions expressed here are the views of the writer and do not necessarily reflect the views and opinions of News Medical.
Post a new comment
Post

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.

You might also like...
Advancements in reinforcement learning for personalized patient care