Indicator Selection for Quality Measurement in Maternal Neonatal and Child Health Services: Application of Random Forest Classifier

Quality of Maternal, Neonatal and Child (MNCH) care is an important aspect in ensuring healthy outcomes and survival of mothers and children. To maintain quality in health services provided, organizations and other stakeholders in maternal and child health recommend regular quality measurement. Quality indicators are the key components in the quality measurement process. However, the literature shows neither an indicator selection process nor a set of quality indicators for quality measurement that is universally accepted. The lack of a universally accepted quality indicator selection process and set of quality indicators results in the establishment of a variety of quality indicator selection processes and several sets of quality indicators whenever the need for quality measurement arises. This adds extra processes that render quality measurement process. This study, therefore, aims to establish a set of quality indicators from a broad set of quality indicators recommended by the World Health Organization (WHO). The study deployed a machine learning technique, specifically a random forest classifier to select important indicators for quality measurement. Twenty-nine indicators were identified as important features and among those, eight indicators namely maternal mortality ratio, still-birth rate, delivery at a health facility, deliveries assisted by skilled attendants, proportional breach delivery, normal delivery rate, born before arrival rate and antenatal care visit coverage were identified to be the most important indicators for quality measurement.

Evaluation of drought indices to identify tolerant genotypes in common bean bush(Phaseolus vulgaris L.)

Drought is one of the major abiotic stresses often causing negative impacts on bean crops in the Andean region in Colombia. An experiment under the greenhouse conditions was carried out to assess the effect of a prolonged drought period(15 days) at two different phenological stages(vegetative or reproductive) on grain yield and yield components of five bush bean cultivars(ICA-Cerinza, Bachue, NUA35, Bianca, and Bacatá). Nine tolerance indices including stress susceptibility index(SSI), tolerance(TOL), mean productivity(MP), geometric mean productivity(GMP), stress tolerance index(STI), yield stability index(YSI), yield index(YI), Harmonic mean(HM), and drought sensitivity index(DSI) were calculated based on grain yield under non-stressed(YP) and drought(YS) conditions. Based on the different drought indices, genotypes ICA-Cerinza and NUA35 had the best performance under drought conditions in both studied phases, which reflected in a reduction of grain yield ~≤40%. The biplot analysis also showed a clear superiority of these two genotypes at both phenological stages. Results also showed that SSI was more effective to identify genotypes less affected by drought. The above results allowed us to conclude that ICA-Cerinza and NUA35 may be considered for agricultural areas where long periods of water deficit are expected and can be used in breeding programs for drought tolerance.

Measurement of the wavelength modulation indices with selective reflection spectroscopy

The wavelength modulation indices are measured based on harmonic amplitude ratio of 4famp/6famp (4famp and 6famp are the 4- and 6-th harmonic central peak amplitudes correspondingly) with the Doppler-free selective reflection modulation spectroscopy. The experiments for the 6S1/2(F = 4) → 6P3/2(F' = 5) transition of cesium D2 line with 30-MHz linewidth were carried out. The 4f- and 6f-harmonic signals were detected with two digital lock-in amplifiers separately. The maximum error for modulation indices measurement was ±0.1 within the range of m from 3 to 6. The non-linear modulation behaviour of an external cavity diode laser induced by voltage tuning was studied with this method. The method for modulation indices measurement does not require a solid etalon as usual for measuring the wavelength modulation depth and the absorption linewidth correspondingly.