Search

We undertook a systematic review of the diagnostic accuracy of artificial intelligence-based software for identification of radiologic abnormalities (computer-aided detection, or CAD) compatible with pulmonary tuberculosis on chest x-rays (CXRs). We searched four databases for articles published between January 2005-February 2019. We summarized data on CAD type, study design, and diagnostic accuracy. We assessed risk of bias with QUADAS-2. We included 53 of the 4712 articles reviewed: 40 focused on CAD design methods (“Development” studies) and 13 focused on evaluation of CAD (“Clinical” studies). Meta-analyses were not performed due to methodological differences. Development studies were more likely to use CXR databases with greater potential for bias as compared to Clinical studies. Areas under the receiver operating characteristic curve (median AUC [IQR]) were significantly higher: in Development studies AUC: 0.88 [0.82–0.90]) versus Clinical studies (0.75 [0.66–0.87]; p-value 0.004); and with deep-learning (0.91 [0.88–0.99]) versus machine-learning (0.82 [0.75–0.89]; p = 0.001). We conclude that CAD programs are promising, but the majority of work thus far has been on development rather than clinical evaluation. We provide concrete suggestions on what study design elements should be improved.

A rapid method, using PCR-restriction fragment length and single-strand conformation polymorphism (SSCP), was applied to screen for mutations of the fluoroquinolone resistance determinants in Streptococcus pneumoniae . One hundred nonduplicate Streptococcus pneumoniae isolates with ciprofloxacin MICs of ≥4.0 μg/ml from the Prince of Wales Hospital, Hong Kong, years 2000 to 2003, were examined. For each isolate, PCR amplicons of quinolone resistance-determining regions (QRDRs) of gyrA , gyrB , parC , and parE genes were digested with AluI, HinfI, Sau3AI, and MspI, respectively, and analyzed by SSCP. Each SSCP pattern was given a number, and each isolate obtained a four-digit code, e.g., 1111, that represented the SSCP profile. The SSCP patterns were correlated to mutations characterized from sequence analyses of PCR amplicons. The most common SSCP profile obtained was no. 5232 (40%), which included strains with two amino acid substitutions in the ParC (Lys-137-Asn) and ParE (Ile-460-Val) genes, followed by the SSCP profile 5223 (17%), which included strains with amino acid substitutions in the ParE (Ile-460-Val) gene only. Ten isolates (10%) with amino acid substitutions at GyrA and ParE (±ParC) genes were resistant to levofloxacin with a MIC of ≥16 μg/ml. Other SSCP profiles were unique in distinguishing the common amino acid substitutions in GyrA (Ser-81-Phe) and ParC (Lys-137-Asn, Ser-79-Phe plus Lys-137-Asn, Asp-83-Asn plus Lys-137-Asn, Ser-79-Phe, and Glu-96-Asp). SSCP analysis of restricted fragments generated patterns that were highly discriminative for mutations present in the QRDRs of gyrA , gyrB , parC , and parE . This method provides a database of high resolution profiles on these mutations and allows rapid screening for new mutations of the fluoroquinolone resistance genes.

This study examined the relationship of community-level stressors to behavioral and emotional problems among African-American and white children with special health care needs.The authors interviewed 257 low-income caregivers of children with special health care needs in an urban Midwestern city who brought their child for a primary health care visit to a community health center between September 2001 and May 2002. Sociodemographic characteristics as well as information about the children's behavioral and emotional problems, the health status of the children, perceptions of urban community stress, access to health care, and satisfaction with health care were collected to determine racial differences in the impact of urban stress on behavioral and emotional problems.Urban community stressors, race, and child's health status were significantly associated with behavioral and emotional problems among children with special health care needs. The association between urban stress and total behavioral problems did not differ by race.When caring for children with special health care needs, especially those with emotional or behavioral problems, primary care providers may be better able to identify important aggravating factors if they also assess urban stress. Systems of care are needed that can assist in addressing urban community-level stressors.

This study examined caregiver perceptions of mental health problems and counseling needs in low-income children with special health care needs (CSHCN). Interviewers collected data from 257 caregivers of CSHCN (61% males; 60% African American; Mean age = 8.4 years) attending six Midwestern inner-city health clinics. Measures included the Child Behavior Checklist (CBCL) and an investigator-designed questionnaire. CBCL T-scores indicated that 38% of CSHCN had a behavioral or mental health problem, but only 26% of caregivers perceived the need for treatment or counseling. CSHCN should be assessed and referred appropriately for behavioral and mental health problems during routine health care visits.