Research Article

Text Messaging-Based Medical Diagnosis Using Natural Language Processing and Fuzzy Logic

Table 1

Summary of related work on the medical diagnosis system.

ReferencesMethodsContributionsLimitations

Ayush et al. [44]Developed integral model including probability and fuzzy models for determination of human constitutional typesProposed MDES system creates and supports decision system to users via providing reliable information about disease manifestationIt has not enough practical evidence for effectiveness and efficiency
Korenevskiy [45]Synthesis of fuzzy decision rulesSimple to calculate with high possibility of diagnosis and predetermined level of reliabilityIt requires larger training samples
Atutxa et al. [21]ICD-10 encoding based on neural networksMultilingual ICD-10 coding. The method is interpretable and it outperforms alternative approaches.Worse performance was detected on larger datasets
Combi et al. [22]MagiCoder, an NLP algorithmSimple, efficient in terms of computational complexity for Italian pharmacovigilance languageInability to handle negations in textual medical records
Lu et al. [14]Combined classic enhanced sequential inference model (ESIM) and BiLSTM networkAchieved higher accuracy compared to existing methods without knowledge enhancedChallenges of concepts with multiple definition was not addressed
Kloehn et al. [24]Proposed a novel algorithm SubSimplifyImproved quality in English and Spanish by providing multiword explanations for difficult termsThere is a possibility of the proposed model generating incomplete explanations
Sarker et al. [25]Combination of fuzzy matching and intersectionIncreased accuracy against human annotationsInability to detect negations in expressions