Strong Predictor Research Articles

Importance of Terrain and Climate for Predicting Soil Organic Carbon Is Highly Variable across Local to Continental Scales.

Soil organic carbon (SOC) plays a vital role in global carbon cycling and sequestration, underpinning the need for a comprehensive understanding of its distribution and controls. This study explores the importance of various covariates on SOC spatial distribution at both local (up to 1.25 km) and continental (USA) scales using a deep learning approach. Our findings highlight the significant role of terrain attributes in predicting SOC concentration distribution with terrain, contributing approximately one-third of the overall prediction at the local scale. At the continental scale, climate is only 1.2 times more important than terrain in predicting SOC distribution, whereas at the local scale, the structural pattern of terrain is 14 and 2 times more important than climate and vegetation, respectively. We underscore that terrain attributes, while being integral to the SOC distribution at all scales, are stronger predictors at the local scale with explicit spatial arrangement information. While this observational study does not assess causal mechanisms, our analysis nonetheless presents a nuanced perspective about SOC spatial distribution, which suggests disparate predictors of SOC at local and continental scales. The insights gained from this study have implications for improved SOC mapping, decision support tools, and land management strategies, aiding in the development of effective carbon sequestration initiatives and enhancing climate mitigation efforts.

Factors Influencing Online Shopping Behavior of Customers: A Case Study of an E-Commerce Platform

As time goes by, the advancement of technology has brought tremendous impact to all fields. Consumers’ purchasing behavior has changed due to the existence of e-commerce. This study aims to examine the factors influencing online shopping behavior by conducting a case study on Shopee. This study was carried out through data collection by using a survey questionnaire and secondary data analysis and collection obtained from other sources such as online related websites. There were 150 Shopee users who responded to the survey. The results indicated that perceived convenience emerged as the strongest predictor (β = 0.457), followed by perceived ease of use (β = 0.280) and perceived trust (β = 0.250). Interestingly, perceived usefulness was not found to be a significant factor (β = -0.055). These findings suggest that online businesses should prioritize convenience, user experience (UX) design, and trust-building strategies. Further research could explore the reasons behind the unexpected usefulness result and cultural influences on online shopping behavior

The Importance of Providing Training to Informal Caregivers of Hospice Patients: Caregiver Experience With Hospice Care Based on Consumer Assessment of Healthcare Providers & Systems Surveys.

Informal caregivers aid hospice patients at the end of life. Little is known of their preparation and confidence in providing care, and how this relates to experiences of hospice care. Examine factors associated with informal caregivers' rating of home hospice care. Data come from 828 completed CAHPS® surveys mailed between January 2022 and December 2023 from a single non-profit Hospice organization. Multivariate logistic regression analyses examined the independent influence of various aspects of hospice care on ratings of hospice. Nine of every 10 respondents rated hospice care high (9 or 10). Most aspects of hospice care were rated favorably. Nearly all respondents felt the patient was treated with dignity and respect (96%). The measure with the greatest room for improvement was getting help as soon as needed (82% "always"). Multivariate analyses revealed 6 factors that independently predicted overall rating of hospice care. The strongest predictor was always getting help as soon as needed, followed by believing the hospice team cared about the patient. Three measures of caregiver training were significantly associated with higher ratings of hospice care being trained to: safely move the patient, what to do if patient became restless, and on pain medications. When informal caregivers feel trained to assess and manage the symptoms, they rate hospice care more favorably. Greater attention to informal caregiver training and support are imperative to improving hospice care.

The role of perceived powerlessness and other barriers to climate action

AbstractThe impacts of anthropogenic climate change are rapidly worsening, but current efforts to mitigate this crisis are insufficient. Therefore, it is critically important to understand how to motivate more individuals to take action to protect against future climate change impacts. This study examines the individual‐level factors that predict motivations to act, as well as potential barriers to action in a sample of Canadian adults. Participants completed a questionnaire that assessed a) demographics; b) climate change knowledge, opinions, and scepticism; and c) psychological factors that may impede action. The responses were analyzed to determine the factors that explain whether individuals would change their actions in light of climate change and to what extent climate change considerations impact their actions. Predictors of action included how informed individuals were about climate change, perceived severity of its effects, perceived urgency to act, and climate change scepticism. The strongest predictor was perceived powerlessness; individuals who felt a sense of powerlessness were less likely to change their actions and reported that the threat of climate change had less influence over their behaviours. Powerlessness in turn was associated with age and political affiliation. Implications of these findings, and possible solutions to overcome the barrier of perceived powerlessness, are discussed.

Anxiety Symptom Trajectories Predict Depression Symptom Trajectories up to Four Years After CBT for Youth Anxiety Disorders.

Long-term data on depression symptoms after cognitive behavioral therapy (CBT) for youth anxiety disorders are scant. We examined depression symptoms up to four years post CBT for anxiety addressing youth age and gender, family social class, and parent mental health as predictors. The sample comprised 179 youth (M age at pre-treatment = 11.5 years; SD = 2.1) in a randomized controlled trial. Clinically assessed anxiety diagnoses and youth and parent-reported anxiety and depression symptoms were measured before, after, and one and four years after CBT. Parent self-reported mental health was measured before CBT. We used regression analyses to determine whether full diagnostic recovery at post-CBT predicted depression trajectories across the four-year assessment period. We used growth curve models to determine whether anxiety trajectories predicted depression trajectories across the four-year assessment period. Youth who lost their anxiety diagnoses after CBT had significantly lower parent-reported depression levels over time, but not lower youth self-reported depression levels. The anxiety symptom trajectory predicted the depression symptom trajectory up to four years post-treatment. There was more explained variance for within-informant (youth-youth; parent-parent) than cross-informants. Being older, female, having lower socio-economic status and parents with poorer mental health were associated with more youth-rated depression over time. However, these demographic predictors were not significant when anxiety symptoms trajectories were added to the models. Successful CBT for anxiety in children is associated with less depression symptoms for as long as four years. Anxiety symptom improvement appears to be a stronger predictor that demographic variables and parent mental health.

Marital quality in a context of displacement: the role of union formation characteristics among Syrian refugee and Jordanian youth

Marital quality is an important determinant of well-being and is related to how unions are formed. Both processes of union formation and marital relationships may be influenced by stressful conditions, including insecurity and displacement. We leverage unique representative data on young Syrian refugees in Jordan to learn more about the interplay between displacement, union formation characteristics and marital quality. Through comparisons with youth from the Jordanian host population, we assess the role of key contextual predictors of marital quality, such as consanguinity and young people’s role in choosing their spouse, with a focus on gender differences. We measure marital quality with six separate items capturing aspects of equality, respect and interpersonal communication and a unidimensional scale identified through exploratory factor analysis. Results show that consanguinity, marital duration and number of children are generally unrelated to marital quality in both populations. In contrast, involvement in spouse choice emerges as the strongest predictor, with both Syrians and Jordanians in family-arranged unions experiencing lower-quality marriages. Among Syrians, women suffer more from lower marital quality, especially when arranged unions happen at a young age, and marriages formed after displacement to Jordan appear more fragile. The study is one of the first to explore predictors of marital quality in a non-Western, conflict-affected population. The findings emphasise the importance of the demographic study of family dynamics in situations of insecurity and displacement moving beyond a narrow focus on marriage timing to cover a wider range of marriage outcomes related to family well-being.

A Comprehensive Study of Positive Body Image as a Predictor of Psychological Well-Being in Anorexia Nervosa.

Recent data suggest a close association between positive body image (PBI) and eating disorder recovery. Nevertheless, the specific mechanisms through which PBI may facilitate recovery from anorexia nervosa (AN) remain unknown. To advance understanding of these mechanisms, this study examined core indices of PBI within AN, exploring its association with emotion regulation and well-being outcomes. Data were collected from 159 female participants, 64 with AN diagnosis and 95 healthy controls (HCs), who completed measures of PBI (body appreciation, functionality appreciation, and body responsiveness), emotion regulation, and psychological well-being (depression, anxiety, stress, and psychological quality of life). The AN group reported lower levels of PBI and psychological well-being, along with greater difficulties in regulating emotions, relative to HCs. PBI variables significantly predicted emotion regulation and psychological well-being in AN, accounting for 36% to 72% of the variance, with body appreciation emerging as the strongest predictor. These findings lend credence to the view that PBI can serve as a catalyst for psychological health. We hypothesize that enhancing PBI can improve interoceptive awareness, which is crucial for emotion regulation and reducing maladaptive food-related coping. Emphasizing a mind-body connection in lifestyle could be a relevant element to consider for both treating and preventing AN.

Assessment of the appropriate cutoff points for anthropometric indices and their relationship with cardio-metabolic indices to predict the risk of metabolic associated fatty liver disease

BackgroundResearch on Metabolic Associated Fatty Liver Disease (MAFLD) is still in its early stages, with few studies available to identify and predict effective indicators of this disease. On the other hand, early diagnosis and intervention are crucial to reduce the burden of MAFLD. Therefore, the aim of this research was to investigate the effectiveness of eleven anthropometric indices and their appropriate cut-off values as a non-invasive method to predict and diagnose MAFLD in the Iranian population.MethodsIn this cross-sectional study, we analyzed baseline data from the Hoveyzeh Cohort Study, a prospective population-based study conducted in Iran that enrolled a total of 7836 subjects aged 35 to 70 years from May 2016 through August 2018.ResultsThe optimal cut-off values of anthropometric indices for predicting MAFLD risk were determined for waist circumference(WC) (102.25 cm for males and 101.45 cm for females), body mass index (BMI) (27.80 kg/m2 for males and 28.75 kg/m2 for females), waist-to-hip ratio (WHR) (0.96 for both males and females), waist-to-height ratio (WHtR) (0.56 for males and 0.63 for females), body adiposity index (BAI) (23.24 for males and 32.97 for females), visceral adiposity index (VAI) (1.64 for males and 1.88 for females), weight-adjusted waist index (WWI) (10.63 for males and 11.71 for females), conicity index (CI) (1.29 for males and 1.36 for females), body roundness index (BRI) (4.52 for males and 6.45 for females), relative fat mass (RFM) (28.18 for males and 44.91 for females) and abdominal volume index (AVI) (18.85 for males and for 21.37 females). VAI in males (sensitivity: 77%, specificity: 60%, Youden’s Index: 0.37) and RFM in females (sensitivity: 76%, specificity: 59%, Youden’s Index: 0.35) were found to have higher sensitivity and specificity compared to other anthropometric indices. Furthermore, anthropometric indices demonstrated statistically significant correlations with various hepatic and cardiometabolic indices. Among these, the strongest positive correlations were observed between WC, BMI, BAI, BRI, and AVI with the Hepatic Steatosis Index (HSI), TyG-BMI, and TyG-WC, as well as between VAI and the Atherogenic Index of Plasma (AIP), Lipid Accumulation Product (LAP), Cardiometabolic Index (CMI), and the Triglyceride and Glucose (TyG) Index.ConclusionAnthropometric indices are effective in predicting MAFLD risk among Iranian adults, with WWI, VAI, and RFM identified as the strongest predictors. The proposed cutoff values could serve as a straightforward and non-invasive methods for the early diagnosis of MAFLD.

The association between parental body mass index and the risk of adolescent obesity

This study aimed to examine the prevalence of adolescent obesity in urban areas and the potential association with parental body mass index (BMI). A cross-sectional design was used and participants were selected from institutions of higher education in Jakarta City. Anthropometric data were obtained by trained volunteers while other variables were acquired through a self-administered questionnaire completed using a Google online form. Among the 420 questionnaires distributed, 370 (88%) were retrieved and completed. Data were analyzed by bivariate and multivariate analysis using chi-square and logistic regression adjusted for lifestyle covariates. The results showed that 59.65% and 63.16% of participants had a father or mother who was overweight and obese. The tendency to acquire obesity was higher when the father was obese compared to the mother (OR=1.42; 95% CI=0.92-2.19). A correlation was found between parental BMI and overweight/obesity in adolescents, with the father being a stronger predictor than the mother. Although there was no significant association, this study underscored the significance of adolescent obesity and overweight as a public health issue, suggesting the need for urgent preventive measures.

Exploring Socio-Economic and Socio-Psychological Factors as A Predictor of Self-Help Groups Dynamics Effectiveness in Debre Birhan, Ethiopia

The study intended to address a knowledge gap by examining the group dynamics effectiveness of Self Help Groups in the Ethiopian context. A correlational design was applied and 372 Self Help Groups members were selected from 60 SHGs through simple random sampling. The main data analysis methods used were Pearson's product-moment correlation and multiple regression. The result indicated that the attitude (r=.667, p<001), extension contact (r=.534, p<001), socioeconomic profile (r=.593, p<001), and social participation (r=.400, p<001) of SHG members had a statistically significant positive relationship with the group’s performance. The model (attitude, social participation, socioeconomic profile, and extension contact) significantly predicted and explained 59.3% of the variance in self-help group dynamics effectiveness. Attitude was the strongest predictor (β = .512, p < .001) & uniquely explained 18.5% of the variance in group dynamics effectiveness, while the socioeconomic profile of self-help group members was the least predictor (β = .106, P < .005) with 0.5% of unique contribution in the explanation of group dynamics. The findings further revealed striking similarities with studies in Asia, suggesting that the potential universalities and the function of self-help group dynamics may transcend regional boundaries.

Individual differences in goal adjustment: convergence and divergence among three theoretical models.

Individual differences in dealing with unattainable goals or resource-consumptive goal pursuit are conceptualized as goal adjustment processes in three theoretical approaches: accommodative coping (two-process model of developmental regulation), compensatory secondary coping (motivational theory of life-span development), and goal disengagement and goal reengagement (goal adjustment theory). The aim of this paper is to conceptually and empirically analyze convergences and divergences between the three approaches as well as their relationship with indicators of well-being and their intersections with cognitive emotion regulation. The empirical study is based on a cross-sectional online survey (N = 433; M = 28.9 years, SD = 8.4 years; 50% female). The conceptual analysis yields clear convergences, but also differences. Empirically, clear but partially non-redundant relationships between the concepts are found in structural equation models. Accommodative coping showed the strongest correlations with measures of well-being and cognitive emotion regulation. When all goal adjustment measures are included simultaneously as predictors of well-being, accommodation remains as the strongest predictor (and partly goal reengagement as well), while goal disengagement shows opposing relationships with most measures of well-being. We discuss the lessons learnt from these findings and conclude by proposing future avenues to examine goal adjustment processes.

A nationally representative survey of ICD-11 PTSD among Danish adolescents and young adults aged 15-29.

Posttraumatic stress disorder (PTSD) is recognized as a debilitating psychiatric disorder affecting populations worldwide. This has inspired many countries to estimate the national prevalence rates of PTSD in Europe and beyond. At present, there are no published representative studies that have assessed the occurrence of trauma exposure and PTSD in Denmark using a valid measurement based on ICD-11 criteria. A national sample of the general population of young Danish residents, ranging in age between 15 to 29 years (n = 2,434), was surveyed cross-sectionally from April to October 2022. Data weights were applied to ensure representativity of the sample. Multiple regression was used to study the relationship between trauma exposure, sex, age, and PTSD. Accidents and violence were the most common types of trauma exposure with females being more likely to experience sexual violence. A total of 7.7% endorsed probable PTSD with women reporting higher rates of clinical and subclinical PTSD (12.3% and 12.7%, respectively) than men (3.5% and 7.3%, respectively). Findings from the multiple regression showed that female gender was associated with higher PTSD-severity, although the strongest predictor was trauma-type with other types of traumas, and sexual violence displaying the strongest relationship to PTSD-severity overall. A dose-response relationship between the number of trauma types and PTSD symptomatology was found. This is the first study of PTSD in a nationally representative Danish sample using a valid measure of ICD-11 PTSD. The identified PTSD rates were higher than Danish official estimates in a representative sample of the Danish adolescent and young adult population (7.7% weighted compared to 1%). The study replicated international findings of sex differences in probable PTSD endorsement.

Factors Determining Black Carbon Exposures among Pregnant Women Enrolled in the HAPIN Trial.

Residential biomass burning is an important source of black carbon (BC) exposure among rural communities in low- and middle-income countries. We collected 7165 personal BC samples and individual/household level information from 3103 pregnant women enrolled in the Household Air Pollution Intervention Network trial. Women in the intervention arm received free liquefied petroleum gas stoves and fuel throughout pregnancy; women in the control arm continued the use of biomass stoves. Median (IQR) postintervention BC exposures were 9.6 μg/m3 (5.2-14.0) for controls and 2.8 μg/m3 (1.6-4.8) for the intervention group. Using mixed models, we characterized predictors of BC exposure and assessed how exposure contrasts differed between arms by select predictors. Primary stove type was the strongest predictor (R2 = 0.42); the models including kerosene use, kitchen location, education, occupation, or stove use hours also provided additional explanatory power from the base model adjusted only for the study site. Our full, trial-wide, model explained 48% of the variation in BC exposures. We found evidence that the BC exposure contrast between arms differed by study site, adherence to the assigned study stove, and whether the participant cooked. Our findings highlight factors that may be addressed before and during studies to implement more impactful cookstove intervention trials.

An Empirical Study on the Turnover Intention among the SME Service Sectors Employees in Beijing, China: A Theory of Planned Behaviour Approach

This empirical study investigates the turnover intention among employees in the SME service sector in Beijing, China, using the Theory of Planned Behavior (TPB) as a theoretical framework. The research aims to understand the key psychological and social factors influencing employees' intentions to leave their current positions. Data were collected through a structured questionnaire administered to 400 employees across various SMEs in Beijing's service industry. The questionnaire measured attitudes towards turnover, subjective norms, perceived behavioral control, and turnover intention. The findings indicate that all three components of TPB significantly predict turnover intention. Attitudes towards turnover, shaped by job satisfaction and perceived job alternatives, emerged as the strongest predictor. Subjective norms, influenced by peer and family expectations, also play a critical role in shaping turnover intentions. Perceived behavioral control, which includes employees' confidence in securing new employment and perceived ease of leaving their current job, further contributes to the prediction model. The study highlights the importance of addressing both individual and contextual factors in managing turnover intentions. For SME managers, fostering a supportive work environment and enhancing job satisfaction can mitigate turnover risks. Moreover, understanding the influence of external social pressures and enhancing employees' perceived control over their career decisions can provide additional strategies to retain talent. This research contributes to the limited literature on employee turnover in China's SME service sector and offers practical insights for improving employee retention strategies. Future studies could explore longitudinal data to understand the dynamics of turnover intention over time and examine the role of additional variables such as organizational commitment and job stress.

Acute clinical outcomes predict both generic and specific health-related quality of life six and 12 months after stroke: A one-year prospective study developed in a middle-income country

ObjectiveTo identify acute predictors of generic and specific health-related quality of life (HRQoL) six and 12 months after stroke in individuals from a middle-income country. Material and methodsThis was a prospective study. The dependent outcomes assessed during six and 12 months after stroke included both generic and specific HRQoL (Short Form Health Survey-36 [SF-36] and stroke-specific quality of life [SSQOL]). The predictors were age, sex, education level, length of hospital stay, current living arrangement, stroke severity, functional independence, and motor impairment. Results122 (59.9±14 years) and 103 (59.8±14.71 years) individuals were evaluated six and 12 months after stroke, respectively. Functional independence and sex were significant acute predictors of both generic and specific HRQoL. Functional independence was the strongest predictor (0.149≤R2≤0.262; 20.01≤F≤43.96, p<0.001), except for generic HRQoL at 12 months, where sex was the strongest predictor (R2=0.14; F=17.97, p<0.001). ConclusionGeneric and specific HRQoL in chronic individuals six and 12 months after stroke, from a middle-income country, can be predicted based on functional independence, the strongest predictor, assessed in the acute phase, except for generic HRQoL at 12 months. Functional independence can be modified by rehabilitation strategies and thus should be considered for HRQoL prognoses at chronic phase.

Genetic and clinical risk factors for stroke recurrence with different impact by assessment age: data from the UK Biobank

Abstract Background The predictive utility of genetic risk factors added to clinical risk factors for stroke recurrence is unclear. Furthermore, whether those predictive utility change in different age groups is uncertain. This study aimed to compare the association of genetic and clinical risk factors with recurrent stroke. Methods Data were collected from 5,378 patients with a history of stroke from the UK Biobank. Cox proportional hazards regression models were used to assess the associations of genetic, demographic, lifestyle, and comorbidity risk factors with stroke recurrence, both in overall and three age-based groups. Results Over a median follow-up of 11.5 (interquartile range [IQR] 10.6–12.3) years, 417 patients had recurrent stroke. The hazard ratio (HR) for recurrent stroke was most pronounced for diabetes mellitus (HR 2.28, 95% confidence interval [CI] 1.83-2.86). Additionally, current smoking, hypertension, age, and polygenic risk score for ischemic stroke (stroke PRS) were also significantly associated with recurrent stroke. Based on concordance index (C-index, 95% CI), the strongest predictors were diabetes mellitus (0.578, 0.556-0.599) followed by age, hypertension and stroke PRS. However, the stroke PRS (0.577, 0.527-0.627) was the strongest predictor in the younger 1/3 patient group (median age 54, IQR 50-57). In addition to demographic, lifestyle, and comorbidity risk factors, genetic risk factor improved C-index of the prediction model from 0.640 (0.592-0.688) to 0.652 (0.602-0.703) in the younger group. Conclusions Recurrent stroke is significantly associated with genetic and clinical risk factors. Genetic risk factor enhances the predictive model`s accuracy, particularly in younger patients.Prediction of stroke recurrence

The role of serum chloride ion in the prognosis of COPD

BackgroundAs exacerbations of chronic obstructive pulmonary disease (COPD) are one of the leading causes of hospitalization and are associated with significant mortality, it is particularly important to accurately assess the risk of exacerbations in COPD. Most of the current clinical biomarkers are related to inflammation and few consider how ion levels affect COPD. Chloride ion, the second most abundant serum electrolyte, has been shown to be associated with poor prognoses in several diseases, but their relationship with COPD remains unclear. MethodsIn total, 105 patients with acute exacerbations of COPD were recruited. Data on clinical characteristics, lung function, blood count, blood biochemistry, relevant scales including the Clinical COPD Questionnaire (CCQ), BODE (BMI, airflow obstruction, dyspnea, exercise capacity) index and the St. George's Respiratory Questionnaire (SGRQ) were collected from all patients for statistical analysis. ResultThere were significant differences in lung function indicators and disease severity in the low chloride ion subgroup compared with the high chloride ion subgroup. On multiple logistic regression analysis, chloride ion was an independent factor affecting lung function in COPD patients (OR=0.808, 95% CI: 0.708 - 0.922, p=0.002). The sensitivity of chloride ion in predicting COPD severity was 78%, the specificity was 63%, and the area under the curve was 0.734 (p<0.001). Subgroup analysis showed that chloride ion was a stronger predictor in male and smoking patients. ConclusionsChloride ion was a novel prognostic biomarker for COPD, and low levels of chloride ion were independently associated with exacerbations in COPD patients.

Effects of spruce budworm defoliation on in-stream algal production and carbon use by food webs

Insect defoliation is a widespread cause of forest disturbance in Canada, and it has the potential to alter terrestrial carbon contributions to stream consumers and thus affect stream ecosystems. Although defoliation by spruce budworms ( Choristoneura fumiferana) is considered a natural disturbance with importance to forest succession, the magnitude and duration of outbreaks are increasing, and there is a growing need to understand their downstream consequences. To examine this, algal productivity and autochthonous (in-stream) energy supporting macroinvertebrate and fish consumers (using δ13C, δ15N) were examined in 12 streams in the Gaspé Peninsula, Québec, Canada, that ranged in watershed defoliation from spruce budworm. Hierarchical partitioning models were used to assess the contributions of watershed and stream variables to these endpoints. Total seasonal algal production ranged fourfold among sites, and cumulative defoliation was the strongest predictor. Consumers from streams with greater defoliation (cumulative or annual) had lower reliance on autochthonous carbon, despite increased algal production, and this effect was greater for brook trout than macroinvertebrates. These findings demonstrate for the first time that insect outbreaks—which alter forest structure and function—also similarly affect downstream aquatic ecosystems by causing changes in the production and contributions of carbon sources. This suggests that insect control strategies and forest management decisions should also consider implications for downstream aquatic ecosystems.

Machine Learning Model for Mild Cognitive Impairment Stage Based on Gait and MRI Images.

In patients with mild cognitive impairment (MCI), a lower level of cognitive function is associated with a higher likelihood of progression to dementia. In addition, gait disturbances and structural changes on brain MRI scans reflect cognitive levels. Therefore, we aimed to classify MCI based on cognitive level using gait parameters and brain MRI data. Eighty patients diagnosed with MCI from three dementia centres in Gangwon-do, Korea, were recruited for this study. We defined MCI as a Clinical Dementia Rating global score of ≥0.5, with a memory domain score of ≥0.5. Patients were classified as early-stage or late-stage MCI based on their mini-mental status examination (MMSE) z-scores. We trained a machine learning model using gait and MRI data parameters. The convolutional neural network (CNN) resulted in the best classifier performance in separating late-stage MCI from early-stage MCI; its performance was maximised when feature patterns that included multimodal features (GAIT + white matter dataset) were used. The single support time was the strongest predictor. Machine learning that incorporated gait and white matter parameters achieved the highest accuracy in distinguishing between late-stage MCI and early-stage MCI.

Ovarian response to controlled stimulation and its predictors in a limited-resource setting

BackgroundInfertility remains a serious health concern for Ethiopian women. Most of its treatment approaches entail controlled ovarian stimulation, the responses of which vary. However, there are no data on ovarian response to stimulation or its predictors in our situation. Thus, the current study aimed to assess the ovarian response to controlled stimulation and identify predictors.MethodsA retrospective follow-up study was undertaken from April 1, 2021, to March 31, 2022, among patients who had first-cycle controlled ovarian stimulation at St.Paul’s Hospital Fertility Center in Addis Ababa, Ethiopia. Clinical data were extracted using a checklist. SPSS-26 for data analysis and Epidata-4.2 for data entry were employed. The binary logistic regression model was fitted. A p-value < 0.05 indicated a significant association. The ROC curve was used to determine cutoff values and identify accurate predictors.ResultsA total of 412 study participants were included in the final analysis. The patients had a mean age of 32.3 ± 5.1 years (range: 20 − 4). The good ovarian response rate was 67% (95% CI: 62.2–71.5). An anti-Mullerian hormone (AMH) concentration < 1.2ng/ml (AOR = 0.19, 95% CI (0.06–0.57)), an antral follicle count (AFC) < 5 (AOR = 0.16, 95% CI (0.05–0.56)), and an induction length < 10 days (AOR = 0.23, 95% CI (0.06–0.93)) were significantly associated with ovarian response. The prediction accuracies for the AFC and AMH concentrations were 0.844 and 0.719, respectively. The optimal cutoff point for prediction was 5.5 AFC, which had a sensitivity of 77.2% and a specificity of 72.8%. However, its positive and negative predictive values were 85.2% and 61.1%, respectively. For AMH, the optimal cutoff value was 0.71ng/mL, with a corresponding sensitivity and specificity of 65.2% and 66%. At this value, the positive and negative predictive values were 63.8% and 67.3%, respectively.ConclusionOnly two-thirds of our patients achieved a good ovarian response. Induction duration, AMH concentration, and AFC were found to be predictors, with the AFC being the strongest predictor. Therefore, the AFC should be performed on all of our patients, and the AMH is selectively employed. Future research must verify the best cutoff points and investigate additional factors affecting ovarian response.