Background: Nosocomial outbreaks of tuberculosis (TB) have been attributed
to unrecognized pulmonary TB, Accurate assessment in identifying index case
s of active TB is essential in preventing transmission of the disease.
Objectives: To develop an artificial neural network using clinical and radi
ographic information to predict active pulmonary TB at the time of presenta
tion at a health-care facility that is superior to physicians' opinion,
Design: Nonconcurrent prospective study,
Setting: University-affiliated hospital.
Participants: A derivation group of 563 isolation episodes and a validation
group of 119 isolation episodes. Interventions: A general regression neura
l network (GRNN) was used to develop the predictive model.
Measurements: Predictive accuracy of the neural network compared with clini
cians' assessment,
Results: Predictive accuracy was assessed by the c-index, which is equivale
nt to the area under the receiver operating characteristic curve. The GRNN
significantly outperformed the physicians' prediction, with calculated c-in
dices (+/- SEM) of 0.947 +/- 0.028 and 0.61 +/- 0.045, respectively (p < 0.
001), When the GRNN was applied to the validation group, the corresponding
c-indices were 0.923 +/- 0.058 and 0.716 +/- 0.095, respectively.
Conclusion: An artificial neural network can identify patients with active
pulmonary TB more accurately than physicians' clinical assessment.