Can machine learning models predict maternal and newborn healthcare providers' perception of safety during the COVID-19 pandemic? A cross-sectional study of a global online survey.

BACKGROUND: Maternal and newborn healthcare providers are essential professional groups vulnerable to physical and psychological risks associated with the COVID-19 pandemic. This study uses machine learning algorithms to create a predictive tool for maternal and newborn healthcare providers' perception of being safe in the workplace globally during the pandemic. METHODS: We used data collected between 24 March and 5 July 2020 through a global online survey of maternal and newborn healthcare providers. The questionnaire was available in 12 languages. To predict healthcare providers' perception of safety in the workplace, we used features collected in the questionnaire, in addition to publicly available national economic and COVID-19-related factors. We built, trained and tested five machine learning models: Support Vector Machine (SVM), Random Forest (RF), XGBoost, CatBoost and Artificial Neural Network (ANN) for classification and regression. We extracted from RF models the relative contribution of features in output prediction. RESULTS: Models included data from 941 maternal and newborn healthcare providers from 89 countries. ML models performed well in classification and regression tasks, whereby RF had 82% cross-validated accuracy for classification, and CatBoost with 0.46 cross-validated root mean square error for regression. In both classification and regression, the most important features contributing to output prediction were classified as three themes: (1) information accessibility, clarity and quality; (2) availability of support and means of protection; and (3) COVID-19 epidemiology. CONCLUSION: This study identified salient features contributing to maternal and newborn healthcare providers perception of safety in the workplace. The developed tool can be used by health systems globally to allow real-time learning from data collected during a health system shock. By responding in real-time to the needs of healthcare providers, health systems could prevent potential negative consequences on the quality of care offered to women and newborns.

A mixed-methods study of maternal health care utilisation in six referral hospitals in four sub-Saharan African countries before and during the COVID-19 pandemic.

INTRODUCTION: In sub-Saharan Africa, referral hospitals are important sources of key maternal health services, especially during a crisis such as the COVID-19 pandemic. This study prospectively assessed the effect of the COVID-19 pandemic on maternal health service utilisation in six large referral hospitals in Guinea, Nigeria, Tanzania and Uganda during the first year of the pandemic. METHODS: Mixed-methods design combining three data sources: (1) quantitative data based on routine antenatal, childbirth and postnatal care data collected March 2019-February 2021, (2) qualitative data from recurring rounds of semi-structured interviews conducted July 2020-February 2021 with 22 maternity skilled heath personnel exploring their perceptions of service utilisation and (3) timeline data of COVID-19 epidemiology, global, national and hospital-level events. Qualitative and quantitative data were analysed separately, framed based on the timeline analysis and triangulated when reporting. RESULTS: Three periods including a first wave, slow period and second wave were identified. Maternal health service utilisation was lower during the pandemic compared with the prepandemic year in all but one selected referral hospital. During the pandemic, service utilisation was particularly lower during the waves and higher or stable during the slow period. Fear of being infected in hospitals, lack of transportation, and even when available, high cost of transportation and service closures were key reasons affecting utilisation during the waves. However, community perception that the pandemic was over or insinuation by Government of the same appeared to stabilise use of referral hospitals for childbirth. CONCLUSION: Utilisation of maternal health services across the continuum of care varied through the different periods and across countries. In crisis situations such as COVID-19, restrictions and service closures need to be implemented with consideration given to alternative options for women to access and use services. Information on measures put in place for safe hospital use should be communicated to women.

'We are not going to shut down, because we cannot postpone pregnancy': a mixed-methods study of the provision of maternal healthcare in six referral maternity wards in four sub-Saharan African countries during the COVID-19 pandemic.

INTRODUCTION: Referral hospitals in sub-Saharan Africa are located in crowded urban areas, which were often epicentres of the COVID-19 pandemic. This paper prospectively assesses how maternal healthcare was provided in six referral hospitals in Guinea, Nigeria, Tanzania and Uganda during the first year of the COVID-19 pandemic. METHODS: Mixed-methods design using three data sources: (1) qualitative data from repeated rounds of semi-structured interviews conducted between July 2020 and February 2021 with 22 maternity skilled heath personnel (SHP) on perceptions of care provision; (2) quantitative monthly routine data on caesarean section and labour induction from March 2019 to February 2021; and (3) timeline data of COVID-19 epidemiology, national and hospital-level events. Qualitative and quantitative data were analysed separately, framed based on timeline analysis, and triangulated during reporting. RESULTS: We identified three periods: first wave, slow period and second wave. The first wave was challenging for SHP given little knowledge about COVID-19, lack of infection prevention and control training, and difficulties reaching workplace. Challenges that persisted beyond the first wave were shortage of personal protective equipment and no rapid testing for women suspected with COVID-19. We noted no change in the proportion of caesarean sections during the pandemic, and a small increase in the proportion of labour inductions. All hospitals arranged isolation areas for women suspected/confirmed with COVID-19 and three hospitals provided care to women with suspected/confirmed COVID-19. Breastfeeding was not discouraged and newborns were not separated from mothers confirmed with COVID-19. Care provision was maintained through dedication of SHP, support from hospital management and remote communication between SHP. CONCLUSION: Routine maternal care provision was maintained in referral hospitals, despite first wave challenges. Referral hospitals and SHP contributed to guideline development for pregnant women suspected/confirmed with COVID-19. Maternity SHP, women and pregnancy must always be included in priority setting when responding to health system shocks, including outbreaks.

Critical comparative analysis of data sources toward understanding referral during pregnancy and childbirth: three perspectives from Nigeria.

BACKGROUND: The highest risk of maternal and perinatal deaths occurs during and shortly after childbirth and is preventable if functional referral systems enable women to reach appropriate health services when obstetric complications occur. Rising numbers of deliveries in health facilities, including in high mortality settings like Nigeria, require formalised coordination across the health system to ensure that women and newborns get to the right level of care, at the right time. This study describes and critically assesses the extent to which referral and its components can be captured using three different data sources from Nigeria, examining issues of data quality, validity, and usefulness for improving and monitoring obstetric care systems. METHODS: The study included three data sources on referral for childbirth care in Nigeria: a nationally representative household survey, patient records from multiple facilities in a state, and patient records from the apex referral facility in a city. We conducted descriptive analyses of the extent to which referral status and components were captured across the three sources. We also iteratively developed a visual conceptual framework to guide our critical comparative analysis. RESULTS: We found large differences in the proportion of women referred, and this reflected the different denominators and timings of the referral in each data source. Between 16 and 34% of referrals in the three sources originated in government hospitals, and lateral referrals (origin and destination facility of the same level) were observed in all three data sources. We found large gaps in the coverage of key components of referral as well as data gaps where this information was not routinely captured in facility-based sources. CONCLUSIONS: Our analyses illustrated different perspectives from the national- to facility-level in the capture of the extent and components of obstetric referral. By triangulating across multiple data sources, we revealed the strengths and gaps within each approach in building a more complete picture of obstetric referral. We see our visual framework as assisting further research efforts to ensure all referral pathways are captured in order to better monitor and improve referral systems for women and newborns.

The impact of COVID-19 on the provision of respectful maternity care: Findings from a global survey of health workers.

BACKGROUND: Significant adjustments to maternity care in response to the COVID-19 pandemic and the direct impacts of COVID-19 can compromise the quality of maternal and newborn care. AIM: To explore how the COVID-19 pandemic negatively affected frontline health workers' ability to provide respectful maternity care globally. METHODS: We conducted a global online survey of health workers to assess the provision of maternal and newborn healthcare during the COVID-19 pandemic. We collected qualitative data between July and December 2020 among a subset of respondents and conducted a qualitative content analysis to explore open-ended responses. FINDINGS: Health workers (n = 1127) from 71 countries participated; and 120 participants from 33 countries provided qualitative data. The COVID-19 pandemic negatively affected the provision of respectful maternity care in multiple ways. Six central themes were identified: less family involvement, reduced emotional and physical support for women, compromised standards of care, increased exposure to medically unjustified caesarean section, and staff overwhelmed by rapidly changing guidelines and enhanced infection prevention measures. Further, respectful care provided to women and newborns with suspected or confirmed COVID-19 infection was severely affected due to health workers' fear of getting infected and measures taken to minimise COVID-19 transmission. DISCUSSION: Multidimensional and contextually-adapted actions are urgently needed to mitigate the impacts of the COVID-19 pandemic on the provision and continued promotion of respectful maternity care globally in the long-term. CONCLUSIONS: The measures taken during the COVID-19 pandemic had the capacity to disrupt the provision of respectful maternity care and therefore the quality of maternity care.

A double-edged sword-telemedicine for maternal care during COVID-19: findings from a global mixed-methods study of healthcare providers.

INTRODUCTION: The COVID-19 pandemic has led to a rapid implementation of telemedicine for the provision of maternal and newborn healthcare. The objective of this study was to document the experiences with providing telemedicine for maternal and newborn healthcare during the pandemic among healthcare professionals globally. METHODS: The second round of a global online survey of maternal and newborn health professionals was conducted, disseminated in 11 languages. Data were collected between 5 July and 10 September 2020. The questionnaire included questions regarding background, preparedness and response to COVID-19, and experiences with providing telemedicine. Descriptive statistics and qualitative thematic analysis were used to analyse responses, disaggregated by country income level. RESULTS: Responses from 1060 maternal and newborn health professionals were analysed. Telemedicine was used by 58% of health professionals and two-fifths of them reported not receiving guidelines on the provision of telemedicine. Key telemedicine practices included online birth preparedness classes, antenatal and postnatal care by video/phone, a COVID-19 helpline and online psychosocial counselling. Challenges reported lack of infrastructure and technological literacy, limited monitoring, financial and language barriers, lack of non-verbal feedback and bonding, and distrust from patients. Telemedicine was considered as an important alternative to in-person consultations. However, health providers emphasised the lower quality of care and risk of increasing the already existing inequalities in access to healthcare. CONCLUSIONS: Telemedicine has been applied globally to address disruptions of care provision during the COVID-19 pandemic. However, some crucial aspects of maternal and newborn healthcare seem difficult to deliver by telemedicine. More research regarding the effectiveness, efficacy and quality of telemedicine for maternal healthcare in different contexts is needed before considering long-term adaptations in provision of care away from face-to-face interactions. Clear guidelines for care provision and approaches to minimising socioeconomic and technological inequalities in access to care are urgently needed.

Voices from the frontline: findings from a thematic analysis of a rapid online global survey of maternal and newborn health professionals facing the COVID-19 pandemic.

INTRODUCTION: The COVID-19 pandemic has substantially impacted maternity care provision worldwide. Studies based on modelling estimated large indirect effects of the pandemic on services and health outcomes. The objective of this study was to prospectively document experiences of frontline maternal and newborn healthcare providers. METHODS: We conducted a global, cross-sectional study of maternal and newborn health professionals via an online survey disseminated through professional networks and social media in 12 languages. Information was collected between 24 March and 10 April 2020 on respondents' background, preparedness for and response to COVID-19 and their experience during the pandemic. An optional module sought information on adaptations to 17 care processes. Descriptive statistics and qualitative thematic analysis were used to analyse responses, disaggregating by low-income and middle-income countries (LMICs) and high-income countries (HICs). RESULTS: We analysed responses from 714 maternal and newborn health professionals. Only one-third received training on COVID-19 from their health facility and nearly all searched for information themselves. Half of respondents in LMICs received updated guidelines for care provision compared with 82% in HICs. Overall, 47% of participants in LMICs and 69% in HICs felt mostly or completely knowledgeable in how to care for COVID-19 maternity patients. Facility-level responses to COVID-19 (signage, screening, testing and isolation rooms) were more common in HICs than LMICs. Globally, 90% of respondents reported somewhat or substantially higher levels of stress. There was a widespread perception of reduced use of routine maternity care services, and of modification in care processes, some of which were not evidence-based practices. CONCLUSIONS: Substantial knowledge gaps exist in guidance on management of maternity cases with or without COVID-19. Formal information-sharing channels for providers must be established and mental health support provided. Surveys of maternity care providers can help track the situation, capture innovations and support rapid development of effective responses.