Pneumonia is one of the major causes of child mortality, yet with a timely diagnosis, it is usually curable with antibiotic therapy. In many developing regions, diagnosing pneumonia remains a challenge, due to shortages of medical resources. Lung ultrasound has proved to be a useful tool to detect lung consolidation as evidence of pneumonia. However, diagnosis of pneumonia by ultrasound has limitations: it is operator-dependent, and it needs to be carried out and interpreted by trained personnel. Pattern recognition and image analysis is a potential tool to enable automatic diagnosis of pneumonia consolidation without requiring an expert analyst. This paper presents a method for automatic classification of pneumonia using ultrasound imaging of the lungs and pattern recognition. The approach presented here is based on the analysis of brightness distribution patterns present in rectangular segments (here called “characteristic vectors“) from the ultrasound digital images. In a first step we identified and eliminated the skin and subcutaneous tissue (fat and muscle) in lung ultrasound frames, and the “characteristic vectors”were analyzed using standard neural networks using artificial intelligence methods. We analyzed 60 lung ultrasound frames corresponding to 21 children under age 5 years (15 children with confirmed pneumonia by clinical examination and X-rays, and 6 children with no pulmonary disease) from a hospital based population in Lima, Peru. Lung ultrasound images were obtained using an Ultrasonix ultrasound device. A total of 1450 positive (pneumonia) and 1605 negative (normal lung) vectors were analyzed with standard neural networks, and used to create an algorithm to differentiate lung infiltrates from healthy lung. A neural network was trained using the algorithm and it was able to correctly identify pneumonia infiltrates, with 90.9% sensitivity and 100% specificity. This approach may be used to develop operator-independent computer algorithms for pneumonia diagnosis using ultrasound in young children.

Worldwide, rural communities face barriers when accessing health services. In response, numerous initiatives have focused on fostering technological innovations, new management approaches and health policies. Research suggests that the most successful innovations are those involving stakeholders at all levels. However, there is little evidence exploring the opinions of local health providers that could contribute with further innovation development and research. The aims of this study were to explore the perspectives of medical doctors (MDs) working in rural areas of Peru, regarding the barriers impacting the diagnostic process, and ideas for diagnostic innovations that could assist them. Data gathered through three focus group discussions (FGG) and 18 individual semi-structured interviews (SSI) with MDs who had completed their medical service in rural areas of Peru in the last two years were analyzed using thematic analysis. Three types of barriers emerged. The first barrier was the limited access to point of care (POC) diagnostic tools. Tests were needed for: i) the differential diagnosis of malaria vs. pneumonia, ii) dengue vs. leptospirosis, iii) tuberculosis, iv) vaginal infections and cervical cancer, v) neurocysticercosis, and vi) heavy metal toxicity. Ultrasound was needed for the diagnosis of obstetric and intra-abdominal conditions. There were also health system-related barriers such as limited funding for diagnostic services, shortage of specialists, limited laboratory services and access to telecommunications, and lack of institutional support. Finally, the third type of barriers included patient related-barriers to follow through with diagnostic referrals. Ideas for innovations proposed included POC equipment and tests, and telemedicine. MDs at primary health facilities in rural Peru face diagnostic challenges that are difficult to overcome due to a limited access to diagnostic tools. Referrals to specialized facilities are constrained by deficiencies in the organization of health services and by barriers that impede the patients’ travel to distant health facilities. Technological innovations suggested by the participants such as POC diagnostic tools and mobile-health (m-health) applications could help address part of the problem. However, other types of innovation to address social, adaptation and policy issues should not be dismissed.

BackgroundIndigenous children and adolescents of the Peruvian Amazon live in precarious conditions that could increase the risk of malnutrition. A particular problem in the Corrientes river communities is the high exposure to lead among children and adolescents.ObjectiveThis study aimed to determine the nutritional status of children and adolescents in indigenous communities in the Corrientes river basin and examine risk factors for anemia, stunting, underweight, and wasting.DesignThis was a cross-sectional assessment in children and adolescents aged 0–17 years from six communities (n=330). Data collection included measurement of hemoglobin levels, anthropometrics, blood lead levels (BLLs); a parental questionnaire including demographic and dwelling information; parents’ occupation; and the child's duration of breastfeeding and food consumption. Analysis included univariate, bivariate, and logistic regression.ResultsOverall, anemia prevalence was 51.0%, stunting (proxy for chronic malnutrition) 50.0%, and...

Delays in receiving adequate care for children suffering from pneumonia can be life threatening and have been described associated with parents’ limited education and their difficulties in recognizing the severity of the illness. The “three delays” was a model originally proposed to describe the most common determinants of maternal mortality, but has been adapted to describe delays in the health seeking process for caregivers of children under five. This study aims to explore the caregivers’ perceived barriers for seeking and receiving health care services in children under five years old admitted to a referral hospital for community-acquired pneumonia in the Peruvian Amazon Region using the three-delays model framework. There were two parts to this mixed-method, cross-sectional, hospital-based study. First, medical charts of 61 children (1 to 60 months old) admitted for pneumonia were reviewed, and clinical characteristics were noted. Second, to examine health care-seeking decisions and actions, as well as associated delays in the process of obtaining health care services, we interviewed 10 of the children’s caregivers. Half of the children in our study were 9 months old or less. Main reasons for seeking care at the hospital were cough (93%) and fever (92%). Difficulty breathing and fast breathing were also reported in more than 60% of cases. In the interviews, caregivers reported delays of 1 to 14 days to go to the closest health facility. Factors perceived as causes for delays in deciding to seek care were apparent lack of skills to recognize signs and symptoms and of confidence in the health system, and practicing self-medication. No delays in reaching a health facility were reported. Once the caregivers reached a health facility, they perceived lack of competence of medical staff and inadequate treatment provided by the primary care physicians. According to caregivers, the main delays to get health care services for pneumonia among young children were identified in the initial decision of caregivers to seek healthcare and in the health system to provide it. Specific interventions targeted to main barriers may be useful for reducing delays in providing appropriate health care for children with pneumonia.

Pneumonia is one of the major causes of child mortality. Unfortunately, in developing countries there is a lack of infrastructure and medical experts in rural areas to provide the required diagnostics opportunely. Lung ultrasound echography has proved to be an important tool to detect lung consolidates as evidence of pneumonia. This paper presents a method for automatic diagnostics of pneumonia using ultrasound imaging of the lungs. The approach presented here is based on the analysis of patterns present in rectangular segments from the ultrasound digital images. Specific features from the characteristic vectors were obtained and classified with standard neural networks. A training and testing set of positive and negative vectors were compiled. Vectors obtained from a single patient were included only in the testing or in the training set, but never in both. Our approach was able to correctly classify vectors with evidence of pneumonia, with 91.5% sensitivity and 100% specificity.