Dataset Information

Predictive Modeling for Perinatal Mortality in Resource-Limited Settings.

ABSTRACT:

Importance

The overwhelming majority of fetal and neonatal deaths occur in low- and middle-income countries. Fetal and neonatal risk assessment tools may be useful to predict the risk of death.

Objective

To develop risk prediction models for intrapartum stillbirth and neonatal death.

Design, setting, and participants

This cohort study used data from the Eunice Kennedy Shriver National Institute of Child Health and Human Development Global Network for Women's and Children's Health Research population-based vital registry, including clinical sites in South Asia (India and Pakistan), Africa (Democratic Republic of Congo, Zambia, and Kenya), and Latin America (Guatemala). A total of 502 648 pregnancies were prospectively enrolled in the registry.

Exposures

Risk factors were added sequentially into the data set in 4 scenarios: (1) prenatal, (2) predelivery, (3) delivery and day 1, and (4) postdelivery through day 2.

Main outcomes and measures

Data sets were randomly divided into 10 groups of 3 analysis data sets including training (60%), test (20%), and validation (20%). Conventional and advanced machine learning modeling techniques were applied to assess predictive abilities using area under the curve (AUC) for intrapartum stillbirth and neonatal mortality.

Results

All prenatal and predelivery models had predictive accuracy for both intrapartum stillbirth and neonatal mortality with AUC values 0.71 or less. Five of 6 models for neonatal mortality based on delivery/day 1 and postdelivery/day 2 had increased predictive accuracy with AUC values greater than 0.80. Birth weight was the most important predictor for neonatal death in both postdelivery scenarios with independent predictive ability with AUC values of 0.78 and 0.76, respectively. The addition of 4 other top predictors increased AUC to 0.83 and 0.87 for the postdelivery scenarios, respectively.

Conclusions and relevance

Models based on prenatal or predelivery data had predictive accuracy for intrapartum stillbirths and neonatal mortality of AUC values 0.71 or less. Models that incorporated delivery data had good predictive accuracy for risk of neonatal mortality. Birth weight was the most important predictor for neonatal mortality.

SUBMITTER: Shukla VV

PROVIDER: S-EPMC7675108 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predictive Modeling for Perinatal Mortality in Resource-Limited Settings.

Shukla Vivek V VV Eggleston Barry B Ambalavanan Namasivayam N McClure Elizabeth M EM Mwenechanya Musaku M Chomba Elwyn E Bose Carl C Bauserman Melissa M Tshefu Antoinette A Goudar Shivaprasad S SS Derman Richard J RJ Garcés Ana A Krebs Nancy F NF Saleem Sarah S Goldenberg Robert L RL Patel Archana A Hibberd Patricia L PL Esamai Fabian F Bucher Sherri S Liechty Edward A EA Koso-Thomas Marion M Carlo Waldemar A WA

JAMA network open 20201102 11

<h4>Importance</h4>The overwhelming majority of fetal and neonatal deaths occur in low- and middle-income countries. Fetal and neonatal risk assessment tools may be useful to predict the risk of death.<h4>Objective</h4>To develop risk prediction models for intrapartum stillbirth and neonatal death.<h4>Design, setting, and participants</h4>This cohort study used data from the Eunice Kennedy Shriver National Institute of Child Health and Human Development Global Network for Women's and Children's ...[more]

PMID: 33206194

Similar Datasets

Project description:BackgroundAlthough laparoscopic surgery has made remarkable progress and become the standard approach for various surgical procedures worldwide over the past 30 years, its establishment in low-resource settings, particularly in public hospitals, has been challenging. The lack of equipment and trained expertise has hindered its widespread adoption in these settings. Cholecystectomy is one of the most commonly performed procedures using laparoscopy world wide AIM: The aim of the study is to determine whether laparoscopic cholecystectomy is feasible in a resource challenged setting METHODS: The research focused on individuals who underwent laparoscopic or open cholecystectomies at Yekatit 12 Hospital in Addis Ababa, Ethiopia, over a one-year period. Comprehensive data collection was conducted prospectively, encompassing both intraoperative and postoperative parameters. Follow-up was carried out via phone calls. The surgical procedures employed innovative techniques, including the reuse of sterilized single-use equipment and the utilization of local resources. The evaluation involved a comparison of demographic information, intraoperative details (such as critical view determination and operative duration), and postoperative complications, including assessments of pain and wound infections RESULTS: From August 2021 to September 2022, 119 patients were assessed. Among these patients, 65 (54.6%) underwent open cholecystectomies, while the remaining 54 (45.4%) underwent laparoscopic cholecystectomies. The average duration of the laparoscopic cholecystectomies was 90.7 min, which is 17.7 min behind the open. Patients in the laparoscopy group had significantly shorter hospital stays than the open group, and 94% were discharged by post operative day 2. The conversion rate from laparoscopic to open surgery was determined to be 3.3% CONCLUSION: To sum up, the safe execution of laparoscopic cholecystectomies is feasible in public hospitals and settings with limited resources, given adequate training and resource distribution. The study findings showcased superior outcomes, including reduced hospitalization duration and fewer complications, while maintaining comparable levels of operative duration and patient satisfaction in both groups.

Project description:Background and aimsPrognostic models provide evidence-based predictions and estimates of future outcomes, facilitating decision-making, patient care, and research. A few of these models have been externally validated, leading to uncertain reliability and generalizability. This study aims to externally validate four models to assess their transferability and usefulness in clinical practice. The models include the respiratory index of severity in children (RISC)-Malawi model and three other models by Lowlavaar et al.MethodsThe study used data from the Clinical Information Network (CIN) to validate the four models where the primary outcome was in-hospital mortality. 163,329 patients met eligibility criteria. Missing data were imputed, and the logistic function was used to compute predicted risk of in-hospital mortality. Models' discriminatory ability and calibration were determined using area under the curve (AUC), calibration slope, and intercept.ResultsThe RISC-Malawi model had 50,669 pneumonia patients who met the eligibility criteria, of which the case-fatality ratio was 4406 (8.7%). Its AUC was 0.77 (95% CI: 0.77-0.78), whereas the calibration slope was 1.04 (95% CI: 1.00 -1.06), and calibration intercept was 0.81 (95% CI: 0.77-0.84). Regarding the external validation of Lowlavaar et al. models, 10,782 eligible patients were included, with an in-hospital mortality rate of 5.3%. The primary model's AUC was 0.75 (95% CI: 0.72-0.77), the calibration slope was 0.78 (95% CI: 0.71-0.84), and the calibration intercept was 0.37 (95% CI: 0.28-0.46). All models markedly underestimated the risk of mortality.ConclusionAll externally validated models exhibited either underestimation or overestimation of the risk as judged from calibration statistics. Hence, applying these models with confidence in settings other than their original development context may not be advisable. Our findings strongly suggest the need for recalibrating these model to enhance their generalizability.

Project description:BackgroundIn an external validation study, model recalibration is suggested once there is evidence of poor model calibration but with acceptable discriminatory abilities. We identified four models, namely RISC-Malawi (Respiratory Index of Severity in Children) developed in Malawi, and three other predictive models developed in Uganda by Lowlaavar et al. (2016). These prognostic models exhibited poor calibration performance in the recent external validation study, hence the need for recalibration.ObjectiveIn this study, we aim to recalibrate these models using regression coefficients updating strategy and determine how much their performances improve.MethodsWe used data collected by the Clinical Information Network from paediatric wards of 20 public county referral hospitals. Missing data were multiply imputed using chained equations. Model updating entailed adjustment of the model's calibration performance while the discriminatory ability remained unaltered. We used two strategies to adjust the model: intercept-only and the logistic recalibration method.ResultsEligibility criteria for the RISC-Malawi model were met in 50,669 patients, split into two sets: a model-recalibrating set (n = 30,343) and a test set (n = 20,326). For the Lowlaavar models, 10,782 patients met the eligibility criteria, of whom 6175 were used to recalibrate the models and 4607 were used to test the performance of the adjusted model. The intercept of the recalibrated RISC-Malawi model was 0.12 (95% CI 0.07, 0.17), while the slope of the same model was 1.08 (95% CI 1.03, 1.13). The performance of the recalibrated models on the test set suggested that no model met the threshold of a perfectly calibrated model, which includes a calibration slope of 1 and a calibration-in-the-large/intercept of 0.ConclusionsEven after model adjustment, the calibration performances of the 4 models did not meet the recommended threshold for perfect calibration. This finding is suggestive of models over/underestimating the predicted risk of in-hospital mortality, potentially harmful clinically. Therefore, researchers may consider other alternatives, such as ensemble techniques to combine these models into a meta-model to improve out-of-sample predictive performance.

Project description:BackgroundMycetoma is a chronic mutilating disease of the skin and the underlying tissues caused by fungi or bacteria. Although recently included in the list of neglected tropical diseases by the World Health Organization, strategic control and preventive measures are yet to be outlined. Thus, it continues to pose huge public health threat in many tropical and sub-tropical countries. If not detected and managed early, it results into gruesome deformity of the limbs. Its low report and lack of familiarity may predispose patients to misdiagnosis and delayed treatment initiation. More so in situation where diagnostic tools are limited or unavailable, little or no option is left but to clinically diagnose these patients. Therefore, an overview of clinical course of mycetoma, a suggested diagnostic algorithm and proposed use of materials that cover the exposed susceptible parts of the body during labour may assist in the prevention and improvement of its management. Furthermore, early reporting which should be encouraged through formal and informal education and sensitization is strongly suggested.Main textAn overview of the clinical presentation of mycetoma in the early and late phases, clues to distinguish eumycetoma from actinomycetoma in the field and the laboratory, differential diagnosis and a suggested diagnostic algorithm that may be useful in making diagnosis amidst the differential diagnosis of mycetoma is given. Additionally, a proposed preventive measures which may be helpful in the community is also provided. Since treatment is currently based on expert opinion, we encourage active research to establish treatment guideline for it.ConclusionSince delay in visiting health facility results into gruesome complication, early presentation, recognition and initiation of appropriate choice of regimen is helpful in reducing complications. The clinical overview of mycetoma and the suggested algorithm may enhance suspicion and possibly increase recognition of mycetoma in the community and further guide in differentiation of eumycetoma from actinomycetoma. There is an urgent need for research funding for mycetoma, a disease plagued by severe physical disabilities and social stigma leading to isolation.

Dataset Information

Predictive Modeling for Perinatal Mortality in Resource-Limited Settings.

Importance

Objective

Design, setting, and participants

Exposures

Main outcomes and measures

Results

Conclusions and relevance

Publications

Predictive Modeling for Perinatal Mortality in Resource-Limited Settings.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets