Digital platform for improving non-radiologists' and radiologists' interpretation of chest radiographs for suspected tuberculosis - a method for supporting task-shifting in developing countries

Shifting X-ray interpretation to non-radiologists can help to address radiologist shortages in developing countries. To determine the change in accuracy of non-radiologists and radiologists for the radiographic diagnosis of paediatric tuberculosis after a short skill-development course. Participants interpreted 15 paediatric chest radiographs before and after a 30-minute course using three possible responses: (1) diagnostic for tuberculosis, (2) abnormal but inconclusive for diagnosis of tuberculosis and (3) normal. We compared proportions of correct diagnoses, sensitivity, and specificity, before and after the course. We included 256 participants comprising 229 non-radiologists (134 radiographers, 32 paediatricians, 39 Medecins Sans Frontieres clinicians and 24 physicians including paediatricians) and 27 radiologists. Mean change proportions of correct diagnosis ranged from -27% to 53% for individuals and 9% to 20% for groups. All groups showed a statistically significant improvement. Mean change in diagnostic sensitivity ranged from -38% to 100% for individuals and from 16% to 41% for groups. All groups showed a statistically significant improvement. Mean change in specificity ranged from -57% to 57% for individuals and from -15% to -4% for groups. The decrease was statistically significant for physicians, paediatricians and radiographers. The course resulted in increased correct diagnoses and improved sensitivity at the expense of specificity. (orig.)