Computer assisted diagnosis of malformation syndromes: An evaluation of three databases (LDDB, POSSUM, and SYNDROC)

Abstract

Computer programs which can be used as an aid to diagnose multiple congenital anomaly syndromes have been used for many years, but up to now they have been evaluated very rarely. The diagnostic abilities of three of these systems [LDDB (London Dysmorphology Database), POSSUM (Pictures of Standard Syndromes and Undiagnosed Malformations), and SYNDROC] were analyzed. All three programs are based on an algorithm which defines a diagnosis by a set of phenotypic components all having the same weight (descriptive algorithm). A second algorithm is applied by SYNDROC to rank competing diagnoses in order of probability. This pseudo‐Bayesian algorithm provides a coefficient of certitude (CC). For a test the clinical findings of 102 patients who had received a firm diagnosis were used. Two search strategies were tried: “novice's strategy” with all findings taken for a search and “expert's strategy” with a selected set of anomalies. Only those diagnoses that were suggested with the 1st rank, defined as the highest degree of agreement, or the highest CC were studied. The greatest resemblance between suggestions of the databases and the clinical diagnosis was obtained with the expert strategy. The highest number of matches were produced by SYNDROC (80 with expert strategy) and the lowest by POSSUM (54 with novice strategy). The overall agreement between the databases is about 40% for the 1st rank. This number reflects that different authors use different pivotal signs for the description of a syndrome. With the pseudo‐Bayesian algorithm 59 cases obtained the highest CC value. Great difficulties exist with the subjective estimates for the calculation of these values; the absolute CC values seem to be meaningless. A small number of unusual cases with special combinations of anomalies provide serious problems for correct diagnosis. © 1996 Wiley‐Liss, Inc.

Diagnostic Approach to Cerebellar Disease in Children

“…The clinical examination should also include observation of how the infant develops, in particular whether dysmorphisms or other malformations become evident with time. The London dysmorphology computer database 46 proved an invaluable aid in expediting the diagnosis in 16% of our cases.…”

Thinking outside “The Box”: Case‐based didactics for medical education and the instructional legacy of Dr John M. Graham, Jr

“…Cross-referencing a manual search from the back of Smith's Recognizable Patterns of Human Malformation is a common method to initiate a dialogue and discussion about ways to narrow a differential (Jones et al, 2021). Students are encouraged to use computerassisted databases such as the London Dysmorphology Database (LDDB), Pictures of Standard Syndromes and Undiagnosed Malformations (POSSUMweb), or other commercial resources (Pelz et al, 1996). Face2Gene is a desktop browser and smartphone phenotyping application which has integrated both POSSUMweb and LDDB into its interface and may help guide clinicians in the right direction (Gurovich et al, 2019).…”

“…craniofacial teams, neurocutaneous clinics, skeletal dysplasia clinics…). The Sherlock Holmes approach: optimal for seasoned clinicians that can combine experience with efficiency (targeted but detailed history, exhaustive physical examination, and ability to separate common traits from rare salient features)(Aase, 1990;Pelz et al, 1996). genomicseducation.net) lists educational resources categorized by topics and also indicates applicable genomic medicine competencies for each resource.…”

Decision support system in psychiatry: Past and future

“…The experience of the developers area of bioinformatics systems for solving the problems of molecular biology, which is conducted on hundreds and most of whom are already in a free on-line access 4 , restricted to clinical medicine without involving data about mental disorders. Offered several DSS for differential diagnosis of monogenic diseases accompanied by mental retardation, which include information about optional symptomatology, accompanying basic pathology [45][46][47][48]. Basis of algorithm of automated search diagnosis DSS "NeuroGen" and "OftalmoGen" is a method of deterministic linear classification decisive function.…”