RESUMO
BACKGROUND: Machine-learning or deep-learning algorithms for clinical diagnosis are inherently dependent on the availability of large-scale clinical datasets. Lack of such datasets and inherent problems such as overfitting often necessitate the development of innovative solutions. Probabilistic modeling closely mimics the rationale behind clinical diagnosis and represents a unique solution. OBJECTIVE: The aim of this study was to develop and validate a probabilistic model for differential diagnosis in different medical domains. METHODS: Numerical values of symptom-disease associations were utilized to mathematically represent medical domain knowledge. These values served as the core engine for the probabilistic model. For the given set of symptoms, the model was utilized to produce a ranked list of differential diagnoses, which was compared to the differential diagnosis constructed by a physician in a consult. Practicing medical specialists were integral in the development and validation of this model. Clinical vignettes (patient case studies) were utilized to compare the accuracy of doctors and the model against the assumed gold standard. The accuracy analysis was carried out over the following metrics: top 3 accuracy, precision, and recall. RESULTS: The model demonstrated a statistically significant improvement (P=.002) in diagnostic accuracy (85%) as compared to the doctors' performance (67%). This advantage was retained across all three categories of clinical vignettes: 100% vs 82% (P<.001) for highly specific disease presentation, 83% vs 65% for moderately specific disease presentation (P=.005), and 72% vs 49% (P<.001) for nonspecific disease presentation. The model performed slightly better than the doctors' average in precision (62% vs 60%, P=.43) but there was no improvement with respect to recall (53% vs 56%, P=.27). However, neither difference was statistically significant. CONCLUSIONS: The present study demonstrates a drastic improvement over previously reported results that can be attributed to the development of a stable probabilistic framework utilizing symptom-disease associations to mathematically represent medical domain knowledge. The current iteration relies on static, manually curated values for calculating the degree of association. Shifting to real-world data-derived values represents the next step in model development.
Assuntos
Algoritmos , Inteligência Artificial/normas , Diagnóstico Diferencial , Modelos Estatísticos , HumanosRESUMO
Drug-resistant spinal tuberculosis (TB) is an emerging health problem in both developing and developed countries. In this review article, we aim to define management protocols for suspicion, diagnosis, and treatment of such patients. Spinal TB is a deep-seated paucibacillary lesion, and the demonstration of acid-fast bacilli on Ziehl-Neelsen staining is possible only in 10%-30% of cases. Drug resistance is suspected in patients showing the failure of clinicoradiological improvement or appearance of a fresh lesion of osteoarticular TB while on anti tubercular therapy (ATT) for a minimum period of 5 months. The conventional culture of Mycobacterium tuberculosis remains the gold standard for both bacteriological diagnosis and drug sensitivity testing (DST); however, the high turn around time of 2-6 weeks for detection with added 3 weeks for DST is a major limitation. To overcome this problem, rapid culture methods and molecular methods have been introduced. From a public health perspective, reducing the period between diagnosis and treatment initiation has direct benefits for both the patient and the community. For all patients of drug-resistant spinal TB, a complete Drug-O-Gram should be prepared which includes details of all drugs, their doses, and duration. Patients with confirmed multidrug-resistant TB strains should receive a regimen with at least five effective drugs, including pyrazinamide and one injectable. Patients with resistance to additional antitubercular drugs should receive individualized ATT as per their DST results.