The K nearest neighbor algorithm for imputation of missing longitudinal prenatal alcohol data

Sania, Ayesha; Pini, Nicolò; Nelson, Morgan E.; Myers, Michael; Shuffrey, Lauren C.; Lucchini, Maristella; Elliott, Amy J.; Odendaal, Hein J.; Fifer, William P.

doi:10.21203/rs.3.rs-32456/v1

Cited by 3 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result of the methodology for the collection of self-report exposure information, a given participant could potentially have single or multiple segments of missing information on alcohol or smoking consumption. For this reason, we imputed missing daily exposure data using a K-Nearest Neighbor approach ( Sania et al, 2020 ). Further information can be found in the Supplementary Material 1 .…”

Section: Methodsmentioning

confidence: 99%

Effects of Prenatal Exposure to Alcohol and Smoking on Fetal Heart Rate and Movement Regulation

Lucchini¹,

Shuffrey²,

Nugent³

et al. 2021

Front. Physiol.

Self Cite

View full text Add to dashboard Cite

Negative associations of prenatal tobacco and alcohol exposure (PTE and PAE) on birth outcomes and childhood development have been well documented, but less is known about underlying mechanisms. A possible pathway for the adverse fetal outcomes associated with PTE and PAE is the alteration of fetal autonomic nervous system development. This study assessed PTE and PAE effects on measures of fetal autonomic regulation, as quantified by heart rate (HR), heart rate variability (SD-HR), movement, and HR-movement coupling in a population of fetuses at ≥ 34 weeks gestational age. Participants are a subset of the Safe Passage Study, a prospective cohort study that enrolled pregnant women from clinical sites in Cape Town, South Africa, and the Northern Plains region, United States. PAE was defined by six levels: no alcohol, low quit early, high quit early, low continuous, moderate continuous, and high continuous; while PTE by 4 levels: no smoking, quit early, low continuous, and moderate/high continuous. Linear regression analyses of autonomic measures were employed controlling for fetal sex, gestational age at assessment, site, maternal education, household crowding, and depression. Analyses were also stratified by sleep state (1F and 2F) and site (South Africa, N = 4025, Northern Plains, N = 2466). The final sample included 6491 maternal-fetal-dyad assessed in the third trimester [35.21 ± 1.26 (mean ± SD) weeks gestation]. PTE was associated with a decrease in mean HR in state 2F, in a dose dependent fashion, only for fetuses of mothers who continued smoking after the first trimester. In state 1F, there was a significant increase in mean HR in fetuses whose mother quit during the first trimester. This effect was driven by the Norther Plains cohort. PTE was also associated with a significant reduction in fetal movement in the most highly exposed group. In South Africa a significant increase in mean HR both for the high quit early and the high continuous group was observed. In conclusion, this investigation addresses a critical knowledge gap regarding the relationship between PTE and PAE and fetal autonomic regulation. We believe these results can contribute to elucidating mechanisms underlying risk for adverse outcomes.

show abstract

Section: Methodsmentioning

confidence: 99%

Effects of Prenatal Exposure to Alcohol and Smoking on Fetal Heart Rate and Movement Regulation

Lucchini¹,

Shuffrey²,

Nugent³

et al. 2021

Front. Physiol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The study design did not allow consumption data to be collected on every single day of pregnancy, so missing values were imputed using the k-nearest neighbor (kNN) method. Methods for alcohol imputation are cited elsewhere ( 57 ). Since frequency of cigarette use was collected more sparsely, average cigarettes smoked per week during pregnancy was used.…”

Section: Methodsmentioning

confidence: 99%

Nicotinic Receptors in the Brainstem Ascending Arousal System in SIDS With Analysis of Pre-natal Exposures to Maternal Smoking and Alcohol in High-Risk Populations of the Safe Passage Study

et al. 2021

Self Cite

View full text Add to dashboard Cite

Pre-natal exposures to nicotine and alcohol are known risk factors for sudden infant death syndrome (SIDS), the leading cause of post-neonatal infant mortality. Here, we present data on nicotinic receptor binding, as determined by 125I-epibatidine receptor autoradiography, in the brainstems of infants dying of SIDS and of other known causes of death collected from the Safe Passage Study, a prospective, multicenter study with clinical sites in Cape Town, South Africa and 5 United States sites, including 2 American Indian Reservations. We examined 15 pons and medulla regions related to cardiovascular control and arousal in infants dying of SIDS (n = 12) and infants dying from known causes (n = 20, 10 pre-discharge from time of birth, 10 post-discharge). Overall, there was a developmental decrease in 125I-epibatidine binding with increasing postconceptional age in 5 medullary sites [raphe obscurus, gigantocellularis, paragigantocellularis, centralis, and dorsal accessory olive (p = 0.0002–0.03)], three of which are nuclei containing serotonin cells. Comparing SIDS with post-discharge known cause of death (post-KCOD) controls, we found significant decreased binding in SIDS in the nucleus pontis oralis (p = 0.02), a critical component of the cholinergic ascending arousal system of the rostral pons (post-KCOD, 12.1 ± 0.9 fmol/mg and SIDS, 9.1 ± 0.78 fmol/mg). In addition, we found an effect of maternal smoking in SIDS (n = 11) combined with post-KCOD controls (n = 8) on the raphe obscurus (p = 0.01), gigantocellularis (p = 0.02), and the paragigantocellularis (p = 0.002), three medullary sites found in this study to have decreased binding with age and found in previous studies to have abnormal indices of serotonin neurotransmission in SIDS infants. At these sites, 125I-epibatidine binding increased with increasing cigarettes per week. We found no effect of maternal drinking on 125I-epibatidine binding at any site measured. Taken together, these data support changes in nicotinic receptor binding related to development, cause of death, and exposure to maternal cigarette smoking. These data present new evidence in a prospective study supporting the roles of developmental factors, as well as adverse exposure on nicotinic receptors, in serotonergic nuclei of the rostral medulla—a finding that highlights the interwoven and complex relationship between acetylcholine (via nicotinic receptors) and serotonergic neurotransmission in the medulla.

show abstract

“…For the target variable, class imbalance was corrected by performing a simple bootstrapping technique which consisted of oversampling the minority category ('VL Suppressed' = No; number of samples = 8392; random state = 5). Missing values imputation was performed with K-NN (K = 05) which was chosen for its capability to produce estimations close to the reality and preserve the associations in the dataset [20]. The training and the test sets were pre-processed separately to prevent information leakage from the training to the test set, and bootstrapping was performed on the training set only [21].…”

Section: Study Datasetmentioning

confidence: 99%

Development of machine learning algorithms to predict viral load suppression among HIV patients in Conakry (Guinea)

Yehadji

Gray

Vicente

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Viral load (VL) suppression represents a key to the end of the global HIV epidemic. It is critical for healthcare providers and people living with HIV (PLHIV) to be able to predict viral suppression. This study was conducted to explore the possibility of predicting viral suppression among HIV patients using machine learning (ML) algorithms. Methods Anonymized data were used from a cohort of HIV patients managed in eight health facilities in Conakry (Guinea). The data pre-processing steps included variable recoding, record removal, missing values imputation, grouping small categories, creating dummy variables and oversampling (only applied to the training set) of the smallest target class. Support vector machine (SVM), logistic regression (LR), naïve Bayes (NB), random forest (RF) and four stacked models where developed. The optimal parameters of the algorithms were determined with 03 cross-validation. The 30% of the sample was held as a test set to perform model evaluation. Techniques implemented to determine the most predictive variables were applied on LR, RF, and NB (with analysis of variance, ANOVA). Results LR was found to be the most optimal model to detect VL suppression and non-suppression. It produced an area under the curve (AUC) of 83%, with 74% and 78% sensitivity and specificity, respectively. In other words, it can correctly detect 74% of suppressed VL and correctly detect 78% of non-suppressed VL. With LR, Gender, Prior antiretroviral therapy (ART), Method into ART, Cotrimoxazole prophylactic therapy (CPT) at ART start, Second Line treatment, Last pre-ART CD4, Last ART CD4, Stage at ART start, Age, and Duration on ART were identified as the most predictive variables for VL suppression. Conclusion This study demonstrated the capability to predict VL suppression but has some limitations. The results are dependent on the quality of the data and are specific to the Guinea context and thus, there may be limitations with generalizability. Future studies may be conducting a similar study in a different context and develop the most optimal model into an application that can be tested in a clinical context.

show abstract

The K nearest neighbor algorithm for imputation of missing longitudinal prenatal alcohol data

Cited by 3 publications

References 20 publications

Effects of Prenatal Exposure to Alcohol and Smoking on Fetal Heart Rate and Movement Regulation

Effects of Prenatal Exposure to Alcohol and Smoking on Fetal Heart Rate and Movement Regulation

Nicotinic Receptors in the Brainstem Ascending Arousal System in SIDS With Analysis of Pre-natal Exposures to Maternal Smoking and Alcohol in High-Risk Populations of the Safe Passage Study

Development of machine learning algorithms to predict viral load suppression among HIV patients in Conakry (Guinea)

Contact Info

Product

Resources

About