Peter Donkor

Groundwater (GW) is a key source of drinking water and irrigation to combat growing food insecurity and for improved water access in rural sub-Saharan Africa. However, there are limited studies due to data scarcity in the region. New modeling techniques such as Machine learning (ML) are found robust and promising tools to assess GW recharge with less expensive data. The study utilized ML technique in GW recharge prediction for selected locations to assess sustainability of GW resources in Ghana. Two artificial neural networks (ANN) models namely Feedforward Neural Network with Multilayer Perceptron (FNN-MLP) and Extreme Learning Machine (FNN-ELM) were used for the prediction of GW using 58 years (1960–2018) of GW data. Model evaluation between FNN-MLP and FNN-ELM showed that the former approach was better in predicting GW with R² ranging from 0.97 to 0.99 while the latter has an R² between 0.42 to 0.68. The overall performance of both models was acceptable and suggests that ANN is a useful forecasting tool for GW assessment. The outcomes from this study will add value to the current methods of GW assessment and development, which is one of the pillars of the sustainable development goals (SDG 6).

INTRODUCTION: Information on occupational injuries to health care workers (HCWs) in Africa is limited. We sought to determine the prevalence of occupational injuries among HCWs at a Ghanaian hospital, determine the most common types of injuries, and assess HCWs´ knowledge regarding occupational safety. METHODS: we interviewed 246 HCWs at a government hospital regarding occupational injuries during the prior year. The sample included: nurses (77.6%), physicians (9.3%), laboratory staff (5.7%), and non-clinical staff (6.9%). RESULTS: the 12-month prevalence of occupational injury was 29.7%. Incidence was 1.63 injuries per person-year. Leading mechanisms were needlesticks (35.4% of injuries), cuts from sharp objects (34.6%), hit by object (25.2%), and violence (24.4%). Most (62.2%) respondents had training in occupational safety. Most reported adherence to safety practices, including properly disposing sharps (86.6%) and using personal protective equipment (85.8%). However, there were gaps in knowledge. Few HCWs knew the officer in-charge for post-exposure prophylaxis (5.3%) or that there was a hospital occupational safety unit (26.4%). Many (20.8%) reported difficulty in seeking care for their injury. On multivariable analysis, correlates of injury included stress at work (aOR 2.68; 95% CI 1.26, 5.71) and being a laboratory worker (aOR 3.26; 95% CI 1.02, 10.50). CONCLUSION: occupational injuries to HCWs were unacceptably frequent. There is, however, a solid foundation to build on. Most HCWs had training in occupational safety and many reported adherence to safety practices. Health care workers need to be better informed of existing resources. Care for injuries needs to be improved, such as by increasing capacity for post-exposure prophylaxis.

Objective: Capacity assessments serve as surrogates for surgical output in low‐ and middle‐income countries where detailed registers do not exist. The relationship between surgical capacity and output was evaluated in Ghana to determine whether a more critical interpretation of capacity assessment data is needed on which to base health systems strengthening initiatives.Methods: A standardized surgical capacity assessment was performed at 37 hospitals nationwide using WHO guidelines; availability of 25 essential resources and capabilities was used to create a composite capacity score that ranged from 0 (no availability of essential resources) to 75 (constant availability) for each hospital. Data regarding the number of essential operations performed over 1 year, surgical specialties available, hospital beds, and functional operating rooms were also collected. The relationship between capacity and output was explored.Results: The median surgical capacity score was 37 [interquartile range (IQR) 29–48; range 20–56]. The median number of essential operations per year was 1480 (IQR 736–1932) at first‐level hospitals; 1545 operations (IQR 984–2452) at referral hospitals; and 11,757 operations (IQR 3769–21,256) at tertiary hospitals. Surgical capacity and output were not correlated (p > 0.05).Conclusions: Contrary to current understanding, surgical capacity assessments may not accurately reflect surgical output. To improve the validity of surgical capacity assessments and facilitate maximal use of available resources, other factors that influence output should also be considered, including demand‐side factors; supply‐side factors and process elements; and health administration and management factors.