Applicability of artificial intelligence-based computer-aided detection (AI-CAD) for pulmonary tuberculosis to community-based active case finding.

BACKGROUND: Artificial intelligence-based computer-aided detection (AI-CAD) for tuberculosis (TB) has become commercially available and several studies have been conducted to evaluate the performance of AI-CAD for pulmonary tuberculosis (TB) in clinical settings. However, little is known about its applicability to community-based active case-finding (ACF) for TB. METHODS: We analysed an anonymized data set obtained from a community-based ACF in Cambodia, targeting persons aged 55 years or over, persons with any TB symptoms, such as chronic cough, and persons at risk of TB, including household contacts. All of the participants in the ACF were screened by chest radiography (CXR) by Cambodian doctors, followed by Xpert test when they were eligible for sputum examination. Interpretation by an experienced chest physician and abnormality scoring by a newly developed AI-CAD were retrospectively conducted for the CXR images. With a reference of Xpert-positive TB or human interpretations, receiver operating characteristic (ROC) curves were drawn to evaluate the AI-CAD performance by area under the ROC curve (AUROC). In addition, its applicability to community-based ACFs in Cambodia was examined. RESULTS: TB scores of the AI-CAD were significantly associated with the CXR classifications as indicated by the severity of TB disease, and its AUROC as the bacteriological reference was 0.86 (95% confidence interval 0.83-0.89). Using a threshold for triage purposes, the human reading and bacteriological examination needed fell to 21% and 15%, respectively, detecting 95% of Xpert-positive TB in ACF. For screening purposes, we could detect 98% of Xpert-positive TB cases. CONCLUSIONS: AI-CAD is applicable to community-based ACF in high TB burden settings, where experienced human readers for CXR images are scarce. The use of AI-CAD in developing countries has the potential to expand CXR screening in community-based ACFs, with a substantial decrease in the workload on human readers and laboratory labour. Further studies are needed to generalize the results to other countries by increasing the sample size and comparing the AI-CAD performance with that of more human readers.

[Association between smoking and tuberculosis infection].

PURPOSE: Several reports show smoking as a risk factor of tuberculosis (TB) infection, especially in prisoners, emigrants, the homeless, or people in areas where TB is endemic. These reports mostly used the tuberculin test to detect TB. However, there is no report evaluating smoking as a risk factor of TB infection among people coming into contact with TB with the use of the Interferon-Gamma Release Assays (IGRA) test. MATERIAL & METHOD: We compared TB infection in smokers and non-smokers who came into contact with TB infection by using the IGRA test. We retrospectively collected information about people coming into contact with TB who visited the Daiichi Dispensary from July 1, 2011 to June 30, 2012. They were divided into 2 groups (IGRA positive or negative) and smoking (present/past or never). RESULT: Out of 390 subjects who came into contact with TB examined, 229 were male and 161 were female. The mean age was 39.0 years, 98 were present smokers, 69 were past smokers, and 223 were never-smokers. There were 19 IGRA-positive and 371 IGRA-negative subjects. The IGRA positive rate was 4.9%. Out of 19 IGRA-positive subjects, 13 were smokers or ever-smoker (68.4%). Out of 371 IGRA-negative subjects, 154 cases were smoker or ever-smoker (41.5%). Smoking experience (present and past) was statistically significant in the IGRA-positive group. There were no significant differences in sex, age, drinking habits, and level of contact. Multivariate analysis showed smoking was only one independent risk factor for being IGRA-positive (odds ratio 3.06, 95% confidence interval: 1.14-8.21, p = 0.027). DISCUSSION: Our results suggest that smoking experience in subjects coming into contact with TB is a risk factor for TB infection. TB cases in smokers are reported to be more severe and have delayed detection of disease. They are also more likely to infect those who come in contact with them. If TB source cases and their contacts are both smokers and co-exist in a narrow and limited area, the contacts might be at higher risk of exposure to TB-contaminated air than non-smokers.

Analysis of an interferon-gamma release assay for monitoring the efficacy of anti-tuberculosis chemotherapy.

The reported effect of anti-tuberculosis chemotherapy on interferon-gamma (IFN-γ) release in response to specific Mycobacterium tuberculosis antigens has been inconsistent. The objective of this study was therefore to determine the effect of anti-tuberculosis chemotherapy on IFN-γ response to ESAT-6 and CFP-10. QuantiFERON®-TB Gold (QFT-G) was performed, and the IFN-γ response to ESAT-6 and CFP-10 were measured, for 50 people with culture-confirmed tuberculosis prior to initiating treatment and periodically for up to 120 weeks following initiation of said treatment. IFN-γ responses and bacteriological response were compared. The average IFN-γ response to ESAT-6 and CFP-10 and the proportion of QFT-G results that were positive decreased during chemotherapy and for several weeks thereafter, reaching lows at weeks 48 to 56. Furthermore, these measures were lower at 48 weeks for those with bacteriological reversion prior to the second monthly visit than for those with slower reversion. Although it was shown that anti-tuberculosis treatment generally reduced the specific release of IFN-γ, the effect is so variable that it could be used as a monitor of progress of chemotherapy with great care and reservation.

[Liver dysfunction during treatment of latent tuberculosis infection].

PURPOSE: The indications for treatment for latent tuberculosis infection were revised in 2007 to reflect that any subject with a higher risk of tuberculosis regardless of age should be treated. We worried about the incidence of liver dysfunction due to isoniazid (INH) in patients older than 30 yrs. of age. We evaluated the frequency of liver dysfunction due to INH according to age and discussed the possibility of its prevention. METHODS: We reviewed the clinical records of 99 patients younger than 29 yrs. and 229 patients older than 30 yrs. who were treated for latent tuberculosis infection from August 2007 to December 2008 at our clinic. The liver function tests (AST and ALT) were performed before the treatment, one and a half months after the start of the treatment, and almost every month during the treatment. We defined liver dysfunction as an AST and/or ALT greater than 100 IU/L. RESULTS: Seven out of the 99 younger patients (7.1%) and 42 out of the 229 (18.3%) older patients developed liver dysfunction. The difference between the two age groups was statistically significant according to the chi-square test (p < 0.01). After the occurrence of liver dysfunction, 35 out of 49 patients (71%) completed the treatment by maintaining the same or a decreased dose of INH, while the medication was discontinued in 9 patients who were then followed up by chest X-ray examination. Two of these 49 patients discontinued the medication by themselves. CONCLUSIONS: The frequency of liver damage due to INH was higher in persons older than 30 yrs. In this group, 3 persons developed severe liver damage with ALT and/or AST higher than 1000 IU/L. Early detection is required to avoid serious damage. Thus, we decided to perform liver function tests more often, i.e., at 2 weeks after the onset of treatment and every month thereafter.

[A case of pulmonary nocardiosis with Nocardia beijingensis].

A 60-year-old woman seen at the National Hospital Organization Nagasaki Medical Center of Neurology with a cough and abnormal chest radiography was found in CT to have interstitial shadows in the bilateral lower lung fields. She was diagnosed with interstitial pneumonia and treated with steroids. Treatment was effective, and the predonisolone dosage was gradually tapered. When dosage was 17.5 mg/day, her chest Xray showed exacerbation. Cyclophosphamide at 50mg/day was added, and chest radiography improved. Two months later, her chest radiography showed infiltration with cavities in the left lung field. Although several antibiotics (sulbactam/cefoperazone, levofloxacin) were administered, no improvement was seen. Sputa on hospital day 60 showed the presence of gram-positive branched rods, identified as Nocardia beijingensis. We administered sulfamethoxazole/trimethoprim, meropenem and levofloxacin together, and shadows improved. With recurrent aggravation of interstitial pneumonia, however, new cavity shadows occurred in the bilateral lung due to Aspergillus fumigatus. Shadows worsened and she died of respiratory failure. Testing for pulmonary nocardiosis should be added to differential diagnosis procedures as an opportunistic infection in immune-compromised hosts.