Goal: Chest auscultations offer a non-invasive and low-cost tool for monitoring lung disease. However, they present many shortcomings, including inter-listener variability, subjectivity, and ...vulnerability to noise and distortions. This work proposes a computer-aided approach to process lung signals acquired in the field under adverse noisy conditions, by improving the signal quality and offering automated identification of abnormal auscultations indicative of respiratory pathologies. Methods: The developed noise-suppression scheme eliminates ambient sounds, heart sounds, sensor artifacts, and crying contamination. The improved high-quality signal is then mapped onto a rich spectrotemporal feature space before being classified using a trained support-vector machine classifier. Individual signal frame decisions are then combined using an evaluation scheme, providing an overall patient-level decision for unseen patient records. Results: All methods are evaluated on a large dataset with >1000 children enrolled, 1-59 months old. The noise suppression scheme is shown to significantly improve signal quality, and the classification system achieves an accuracy of 86.7% in distinguishing normal from pathological sounds, far surpassing other state-of-the-art methods. Conclusion: Computerized lung sound processing can benefit from the enforcement of advanced noise suppression. A fairly short processing window size (<;1 s) combined with detailed spectrotemporal features is recommended, in order to capture transient adventitious events without highlighting sharp noise occurrences. Significance: Unlike existing methodologies in the literature, the proposed work is not limited in scope or confined to laboratory settings: This work validates a practical method for fully automated chest sound processing applicable to realistic and noisy auscultation settings.
Pneumonia is the leading infectious cause of under-5 mortality in sub-Saharan Africa. Clinical prediction tools may aide case classification, triage, and allocation of hospital resources. We ...performed an external validation of two published prediction tools and compared this to a locally developed tool to identify children admitted with pneumonia at increased risk for in-hospital mortality in Malawi.
We retrospectively analyzed the performance of the Respiratory Index of Severity in Children (RISC) and modified RISC (mRISC) scores in a child pneumonia dataset prospectively collected during routine care at seven hospitals in Malawi between 2011-2014. RISC has both an HIV-infected and HIV-uninfected tool. A local score (RISC-Malawi) was developed using multivariable logistic regression with missing data multiply imputed using chained equations. Score performances were assessed using c-statistics, sensitivity, specificity, positive predictive value, negative predictive value, and likelihood statistics.
16,475 in-patient pneumonia episodes were recorded (case-fatality rate (CFR): 3.2%), 9,533 with complete data (CFR: 2.0%). The c-statistic for the RISC (HIV-uninfected) score, used to assess its ability to differentiate between children who survived to discharge and those that died, was 0.72. The RISC-Malawi score, using mid-upper arm circumference as an indicator of malnutrition severity, had a c-statistic of 0.79. We were unable to perform a comprehensive external validation of RISC (HIV-infected) and mRISC as both scores include parameters that were not routinely documented variables in our dataset.
In our population of Malawian children with WHO-defined pneumonia, the RISC (HIV-uninfected) score identified those at high risk for in-hospital mortality. However the refinement of parameters and resultant creation of RISC-Malawi improved performance. Next steps include prospectively studying both scores to determine if incorporation into routine care delivery can have a meaningful impact on in-hospital CFRs of children with WHO-defined pneumonia.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
This Viewpoints article details our recommendation for the World Health Organization Integrated Management of Childhood Illness guidelines to consider additional referral or daily monitoring criteria ...for children with chest indrawing pneumonia in low-resource settings. We review chest indrawing physiology in children and relate this to the risk of adverse pneumonia outcomes. We believe there is sufficient evidence to support referring or daily monitoring of children with chest indrawing pneumonia and signs of severe respiratory distress, oxygen saturation <93% (when not at high altitude), moderate malnutrition, or an unknown human immunodeficiency virus (HIV) status in an HIV-endemic setting. Pulse oximetry screening should be routine and performed at the earliest point in the patient care pathway as possible. If outpatient clinics lack capacity to conduct pulse oximetry, nutritional assessment, or HIV testing, then we recommend considering referral to complete the evaluation. When referral is not possible, careful daily monitoring should be performed.
Full text
Available for:
BFBNIB, NUK, PNG, UL, UM, UPUK
The mortality impact of pulse oximetry use during infant and childhood pneumonia management at the primary healthcare level in low-income countries is unknown. We sought to determine mortality ...outcomes of infants and children diagnosed and referred using clinical guidelines with or without pulse oximetry in Malawi.
We conducted a data linkage study of prospective health facility and community case and mortality data. We matched prospectively collected community health worker (CHW) and health centre (HC) outpatient data to prospectively collected hospital and community-based mortality surveillance outcome data, including episodes followed up to and deaths within 30 days of pneumonia diagnosis amongst children 0-59 months old. All data were collected in Lilongwe and Mchinji districts, Malawi, from January 2012 to June 2014. We determined differences in mortality rates using <90% and <93% oxygen saturation (SpO2) thresholds and World Health Organization (WHO) and Malawi clinical guidelines for referral. We used unadjusted and adjusted (for age, sex, respiratory rate, and, in analyses of HC data only, Weight for Age Z-score WAZ) regression to account for interaction between SpO2 threshold (pulse oximetry) and clinical guidelines, clustering by child, and CHW or HC catchment area. We matched CHW and HC outpatient data to hospital inpatient records to explore roles of pulse oximetry and clinical guidelines on hospital attendance after referral. From 7,358 CHW and 6,546 HC pneumonia episodes, we linked 417 CHW and 695 HC pneumonia episodes to 30-day mortality outcomes: 16 (3.8%) CHW and 13 (1.9%) HC patients died. SpO2 thresholds of <90% and <93% identified 1 (6%) of the 16 CHW deaths that were unidentified by integrated community case management (iCCM) WHO referral protocol and 3 (23%) and 4 (31%) of the 13 HC deaths, respectively, that were unidentified by the integrated management of childhood illness (IMCI) WHO protocol. Malawi IMCI referral protocol, which differs from WHO protocol at the HC level and includes chest indrawing, identified all but one of these deaths. SpO2 < 90% predicted death independently of WHO danger signs compared with SpO2 ≥ 90%: HC Risk Ratio (RR), 9.37 (95% CI: 2.17-40.4, p = 0.003); CHW RR, 6.85 (1.15-40.9, p = 0.035). SpO2 < 93% was also predictive versus SpO2 ≥ 93% at HC level: RR, 6.68 (1.52-29.4, p = 0.012). Hospital referrals and outpatient episodes with referral decision indications were associated with mortality. A substantial proportion of those referred were not found admitted in the inpatients within 7 days of referral advice. All 12 deaths in 73 hospitalised children occurred within 24 hours of arrival in the hospital, which highlights delay in appropriate care seeking. The main limitation of our study was our ability to only match 6% of CHW episodes and 11% of HC episodes to mortality outcome data.
Pulse oximetry identified fatal pneumonia episodes at HCs in Malawi that would otherwise have been missed by WHO referral guidelines alone. Our findings suggest that pulse oximetry could be beneficial in supplementing clinical signs to identify children with pneumonia at high risk of mortality in the outpatient setting in health centres for referral to a hospital for appropriate management.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Pneumonia is a leading cause of mortality in children <5 years globally. Early identification of hospitalized children with pneumonia who may fail antibiotics could improve outcomes. We conducted a ...secondary analysis from the Malawi CPAP IMPACT trial evaluating risk factors for antibiotic failure among children hospitalized with pneumonia.
Participants were 1-59 months old with World Health Organization-defined severe pneumonia and hypoxemia, severe malnutrition, and/or HIV exposure/infection. All participants received intravenous antibiotics per standard care. First-line antibiotics were benzylpenicillin and gentamicin for five days. Study staff assessed patients for first-line antibiotic failure daily between days 3-6. When identified, patients failing antibiotics were switched to second-line ceftriaxone. Analyses excluded children receiving ceftriaxone and/or deceased by hospital day two. We compared characteristics between patients with and without treatment failure and fit multivariable logistic regression models to evaluate associations between treatment failure and admission characteristics.
From June 2015-March 2018, 644 children were enrolled and 538 analyzed. Antibiotic failure was identified in 251 (46.7%) participants, and 19/251 (7.6%) died. Treatment failure occurred more frequently with severe malnutrition (50.2% (126/251) vs 28.2% (81/287), p<0.001) and amongst those dwelling ≥10km from a health facility (22.3% (56/251) vs 15.3% (44/287), p = 0.026). Severe malnutrition occurred more frequently among children living ≥10km from a health facility than those living <10km (49.0% (49/100) vs 35.7% (275/428), p = 0.014). Children with severe malnutrition (adjusted odds ratio (aOR) 2.2 (95% CI 1.52, 3.24), p<0.001) and pre-hospital antibiotics ((aOR 1.47, 95% CI 1.01, 2.14), p = 0.043) had an elevated aOR for antibiotic treatment failure.
Severe malnutrition and pre-hospital antibiotic use predicted antibiotic treatment failure in this high-risk severe pneumonia pediatric population in Malawi. Our findings suggest addressing complex sociomedical conditions like severe malnutrition and improving pneumonia etiology diagnostics will be key for better targeting interventions to improve childhood pneumonia outcomes.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Stethoscopes are used ubiquitously in clinical settings to ‘listen’ to lung sounds. The use of these systems in a variety of healthcare environments (hospitals, urgent care rooms, private offices, ...community sites, mobile clinics, etc.) presents a range of challenges in terms of ambient noise and distortions that mask lung signals from being heard clearly or processed accurately using auscultation devices. With advances in technology, computerized techniques have been developed to automate analysis or access a digital rendering of lung sounds. However, most approaches are developed and tested in controlled environments and do not reflect real-world conditions where auscultation signals are typically acquired. Without a priori access to a recording of the ambient noise (for signal-to-noise estimation) or a reference signal that reflects the true undistorted lung sound, it is difficult to evaluate the quality of the lung signal and its potential clinical interpretability. The current study proposes an objective reference-free Auscultation Quality Metric (AQM) which incorporates low-level signal attributes with high-level representational embeddings mapped to a nonlinear quality space to provide an independent evaluation of the auscultation quality. This metric is carefully designed to solely judge the signal based on its integrity relative to external distortions and masking effects and not confuse an adventitious breathing pattern as low-quality auscultation. The current study explores the robustness of the proposed AQM method across multiple clinical categorizations and different distortion types. It also evaluates the temporal sensitivity of this approach and its translational impact for deployment in digital auscultation devices.
•Lack of quality assessment and standardization hurdles lung sound analysis.•Study develops an ambience independent objective auscultation quality metric.•This non-linear measure distinguishes spectrally similar abnormality and noise.•Measure validated against clinical labels, ambience, and temporal disruptions.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
The pneumococcal conjugate vaccine's (PCV) impact on childhood pneumonia during programmatic conditions in Africa is poorly understood. Following PCV13 introduction in Malawi in November 2011, we ...evaluated the case burden and rates of childhood pneumonia.
Between January 1, 2012-June 30, 2014 we conducted active pneumonia surveillance in children <5 years at seven hospitals, 18 health centres, and with 38 community health workers in two districts, central Malawi. Eligible children had clinical pneumonia per Malawi guidelines, defined as fast breathing only, chest indrawing +/- fast breathing, or, ≥1 clinical danger sign. Since pulse oximetry was not in the Malawi guidelines, oxygenation <90% defined hypoxemic pneumonia, a distinct category from clinical pneumonia. We quantified the pneumonia case burden and rates in two ways. We compared the period immediately following vaccine introduction (early) to the period with >75% three-dose PCV13 coverage (post). We also used multivariable time-series regression, adjusting for autocorrelation and exploring seasonal variation and alternative model specifications in sensitivity analyses. The early versus post analysis showed an increase in cases and rates of total, fast breathing, and indrawing pneumonia and a decrease in danger sign and hypoxemic pneumonia, and pneumonia mortality. At 76% three-dose PCV13 coverage, versus 0%, the time-series model showed a non-significant increase in total cases (+47%, 95% CI: -13%, +149%, p = 0.154); fast breathing cases increased 135% (+39%, +297%, p = 0.001), however, hypoxemia fell 47% (-5%, -70%, p = 0.031) and hospital deaths decreased 36% (-1%, -58%, p = 0.047) in children <5 years. We observed a shift towards disease without danger signs, as the proportion of cases with danger signs decreased by 65% (-46%, -77%, p<0.0001). These results were generally robust to plausible alternative model specifications.
Thirty months after PCV13 introduction in Malawi, the health system burden and rates of the severest forms of childhood pneumonia, including hypoxemia and death, have markedly decreased.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
PDF
