This study shows that narrative medical reports produced before two years include several clinical concepts which are significantly associated with individuals with DS compared to FS, this latter condition representing the main differential diagnosis at the onset. These concepts are consistent with the main clinical findings constituting the criteria for differentiating DS from FS in first two years of life.
A series of these concepts refers to the different epileptic phenotype which distinguishes DS from FS at the early stages. Concept “Deviation” (p<0,01), which is found within sentences describing focal seizures, is indicative of the higher tendency of subjects with DS to present seizures with focal signs compared to those with FS.(16,24,25) The increased frequency of concepts “Prolonged Seizures” (p=0,05) and “Status epilepticus” (p=0,07), proves the major trend of these subjects to experience long-lasting seizures, and “Sedation” (p=0,02) reflects the high need of rescue medications to stop them, or the post-ictal phase of these long-lasting seizures or a longer post ictal period due to long-lasting seizures.(13,26,27) Furthermore, some concepts related to characteristic DS seizure types were also significantly prevalent in the DS Cohort, as “Myoclonia” (p=0,02) and “Clonic” (p=0,02).(16,28,29) Interestingly, the concept “Startle” (p=0,07), which is mostly used in narrative reports to depict myoclonic seizure semiology, was higher in the DS Cohort.
Some important non-seizure concepts also emerged such as “Regression” (p=0,03) and “Psychomotor delay” (p=0,07), exclusively reported in the DS Cohort, reflecting the developmental impairment which is present in individuals with DS.(25,30) In addition, “Ataxia” (p=0,02) was significantly more reported DS Cohort, reflecting the peculiar gait disorder commonly observed in individuals with DS, and representing an early motor-marker of this condition.(29,31)
Interestingly, the concept “febrile seizures” was found with significant higher frequency in the FS Cohort (p=0,01) probably because it was used for a “diagnostic” purpose in the clinical reports.
There were some trends for other concepts, but they did not reach statistical difference. For example “hemiparesis” (OR=4,6), that often occur after long-lasting hemiclonic seizures that are typical of DS.(16,28,32) “Photosensitivity” (OR=4,6), that can be early reported in one third of individuals with DS and its recognition can add to the criteria of a positive diagnosis.(33,34) “Pyramidal syndrome” (OR=4,6), was a possible neurological findings at the first year of the disease, in addition to the onset of motor delay.(33)
The study was carried out in a tertiary epilepsy center, so it is plausible that some words have been chosen as a consequence of the clinical suspicion of Dravet Syndrome by highly experienced specialist in epileptology (e.g. “myoclonia”, “ataxia”). Anyway, some documents were reported in some instances by physicians with no high expertise in epilepsy (e.g. emergency care or intensive care physicians), emphasizing the uniformity of expressions used for reporting disease and individuals description, and suggesting that most of key-concepts may have also been found into non-specialists medical reports (e.g. “deviation”, “prolonged seizures”, “startle”).
Several studies shows a substantial worldwide issue of diagnostic delay of DS, with a mean age at diagnosis that is usually over two years, resulting in “unnecessary, costly, and, at times, invasive testing, and use of ineffective therapies, which can exacerbate seizures, increase the risk of status epilepticus, and worsen cognitive outcome”.(17,35–37) Moreover, DS is certainly less recognized in adult population and in developing countries.(19,20)
Computer-based models using EHRs able to suggest diagnosis/avoid misdiagnosis are gaining ground.(3,38) These models are mostly based on structured data, as image-based or laboratory data.(39,40) Recently, more complex models of artificial intelligence are emerging, which are able to elaborate diagnosis by extracting clinically relevant information from unstructured data in EHRs.(41)
On the basis of our findings, further extensive studies might focus on elaborating a specific computer algorithm which combines significative concepts and their age of appearance within narrative specialists and non-specialists reports, in order to automatically produce an alert signal suggesting possible diagnosis of DS.
Some results of our analysis set out some insights. For example, the major incidence of concept “pneumonia” (p=0,03) in DS Cohort compared to FS Cohort appears to be relevant, since it can represent both a facilitator and a complication of status epilepticus.(42) In addition, a number of concepts related to peri-ictal nosocomial and respiratory complications were found with higher frequency in reports of individuals with DS (“nosocomial infections”, “acute respiratory insufficiency”, “aspiration pneumonia”, “FiO2”, “stridor”) (OR=4,6 for each concept) underlying that convulsive status epilepticus is an important life-threatening condition in this population.(42,43)
Furthermore, in this study the concept “Dravet Syndrome” was found in 72% of individuals of DS Cohort before the age of two years. This is concordant with the literature showing the early recognition of DS in France.(37)
Interestingly, some clinical concepts were found with higher frequency into the reports of individuals who received the diagnosis/suspicion of DS before two years: the “long-lasting seizure” concepts (“Status epilepticus”, “Prolonged seizures”, “Sedation”), the “myoclonic” concepts (“Myoclonia”, “Startles”), the “drug resistance” concepts (“Ketogenic diet”), as well as “Ataxia”, and “Photosensitivity”. Although statistical significance was not reached (probably because of small numbers), these findings may support that these clinical concepts are the most DS diagnosis orienting. From this data, it can be assumed that subjects belonging to the sub-group who did not receive a diagnosis/suspicion within two years presented a less “typical” phenotype, explaining why more than two years were needed to make the diagnosis/suspicion. In these individuals, presenting “intermediate” features between individuals with only FS and those with DS presenting the “complete” clinical picture, median age at first seizure was significantly lower than in FS cohort (6,1 months vs 12,4 months), confirming once again that age at first seizure might be the strongest predictor of DS in infants who experience repeated febrile seizures.(24)