Patient’s Experience in Pediatric Primary Immunodeficiency Disorders: Computerized Classification of Questionnaires

Abstract

IntroductionPrimary immunodeficiency disorders (PIDs) are a heterogeneous group of more than 200 rare diseases. Timely diagnosis is of uttermost importance. Therefore, we aimed to develop a diagnostic questionnaire with computerized pattern-recognition in order to support physicians to identify suspicious patient histories.Materials and methodsStandardized interviews were conducted with guardians of children with PID. The questionnaire based on parental observations was developed using Colaizzis’ framework for content analysis. Answers from 64 PID patients and 62 controls were analyzed by data mining methods in order to make a diagnostic prediction. Performance was evaluated by k-fold stratified cross-validation.ResultsThe diagnostic support tool achieved a diagnostic sensitivity of up to 98%. The analysis of 12 interviews revealed 26 main phenomena observed by parents in the pre-diagnostic period. The questions were systematically phrased and selected resulting in a 36-item questionnaire. This was answered by 126 patients with or without PID to evaluate prediction. Item analysis revealed significant questions.DiscussionOur approach proved suitable for recognizing patterns and thus differentiates between observations of PID patients and control groups. These findings provide the basis for developing a tool supporting physicians to consider a PID with a questionnaire. These data support the notion that patient’s experience is a cornerstone in the diagnostic process.

Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

“…Healthcare, research, and clinical development should be patient-centered [65]. Efforts to increase patient involvement in various fields of healthcare show a growing need to proactively engage with patients [100], and patient organizations have a central role to play [101]. AI technologies can help assess patients' experience through the analysis of patient reported outcomes and increase patient recruitment and engagement through social media [100,102].…”

Künstliche Intelligenz zur diagnostischen Unterstützung ausgewählter seltener lysosomaler Speichererkrankungen: Ergebnisse einer Pilotstudie

“…Die genannten Verfahren sind ursprünglich für die Analyse großer Datenmengen entwickelt worden [21], können jedoch auch für kleinere Datensätze angewandt werden, deren komplexe Struktur (z. B. große Anzahl an Fragen mit mehreren Antwortmöglichkeiten in einem Fragebogen) eine computergestützte Auswertung notwendig machen [12,18,24].…”

“…KI wird zunehmend für die diagnostische Unterstützung erprobt und hat in der Pathologie, Radiologie und Dermatologie schon gute Ergebnisse erzielt[13,22,30]. Die Kombination aus Fragebogen und KI wurde bereits für ausgewählte pädiatrisch-pulmonologische Krankheitsbilder und primäre Immundefekte bei Kindern erfolgreich erprobt[18,24]. Die vorliegende Studie nutzte zur qualitativen Auswertung der Interviews das Verfahren nach Colaizzi.…”

Improving the Decision Support in Diagnostic Systems Using Classifier Probability Calibration

“…-Breast cancer dataset (BC) with 699 records [4] -Primary immunodeficiency disorders dataset (P ID) with 126 records [10] -Rare disease dataset (RD) with 1021 records [6] All the data records consist of the same characteristic: multiple attribute columns that describe the patients' symptoms condition and a binary diagnosis column given by a real doctor. The data we use in this paper are from patients that have been individually examined, tested and diagnosed by medical doctors.…”