Detailed accuracy (95% predicted intervals) of each models across subregions of countries for predictor configurations C1-C8 under the setting of PHS definition I.

Detailed accuracy (95% predicted intervals) of each models across subregions of countries for predictor configurations C1-C8 under the setting of PHS definition I.

<p>Detailed accuracy (95% predicted intervals) of each models across subregions of countries for predictor configurations C1-C8 under the setting of PHS definition I.</p>

Saved in:

Bibliographic Details
Main Author:	Yewen Chen (12013847) (author)
Other Authors:	Fangzhi Luo (21728888) (author), Leonardo Martinez (702635) (author), Susan Jiang (10776913) (author), Ye Shen (294552) (author)
Published:	2025
Subjects:	Medicine Biotechnology Infectious Diseases Computational Biology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> compared three key aspects pose extreme challenges incorporate neighboring information identifying key aspects enhance predictive modeling collecting secondary data 9 %, compared hotspot prediction accuracy xlink "> based xlink "> schistosomiasis baseline infection data 5 %- 37 hotspot imbalance distribution hotspot predictions based technique schistosomiasis prevention schistosomiasis consortium transmission areas timely intervention public sources predictor combinations operational research mitigate overfitting limited availability early identification
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Detailed accuracy (95% predicted intervals) of each models for predictor configurations C1-C8 under the setting of PHS definition II.
by: Yewen Chen (12013847)
Published: (2025)

Detailed accuracy (95% predicted intervals) of each models for predictor configurations C1-C8 under the setting of PHS definition I.
by: Yewen Chen (12013847)
Published: (2025)

Detailed accuracy (95% predicted intervals) of each models for predictor configurations under the setting of PHS definition I, where the previous non-baseline method used the infection data in years 1 and 3 [14], while the proposed data fusion method used the infection data only from year 1 (C2-C8).
by: Yewen Chen (12013847)
Published: (2025)

Based on two persistent hotspot (PHS) definitions, the proportion of hotspots (1) and non-hotspots (0) in Kenya and Tanzania.
by: Yewen Chen (12013847)
Published: (2025)

The relative improvements (RIs, %) for each scenario obtained using the spatially weighted data fusion method with different predictor configurations (C2–C8), compared to the method with configuration C1.
by: Yewen Chen (12013847)
Published: (2025)

Relative improvements (IRs, %) for each scenario obtained using the proposed spatially weighted data fusion methods with different predictor configurations (C2-C8), compared to the method with configuration C1.
by: Yewen Chen (12013847)
Published: (2025)

Under PHS definition I, the RIs, in prediction accuracy on unprocessed test sets, obtained from the models trained using pre-processed synthetic data based on the proposed different predictor configurations, compared to models using unprocessed original imbalanced training data, where the best model with the highest prediction accuracy was considered for each method (i.e., y-axis).
by: Yewen Chen (12013847)
Published: (2025)

Baseline infection prevalence across five subregions surrounding Lake Victoria, including two subregions in Tanzania (West and East) and three in Kenya (Northwest, Northeast, and South).
by: Yewen Chen (12013847)
Published: (2025)

Average relative improvements (ARIs, %) for each model in prediction accuracy on test sets from the proposed spatially weighted method using seven different predictor configurations C2–C8, compared to the method using the baseline infection data only (C1).
by: Yewen Chen (12013847)
Published: (2025)

The importance of predictors was assessed by examining the relative effects of each predictor, with the effect quantified as the percentage of variance contribution based on multiple Gradient Boosting Machine (GBM) with different hyperparameters.
by: Yewen Chen (12013847)
Published: (2025)

List of predictors used in this study for developing prediction models for early identification of schistosomiasis hotspots.
by: Yewen Chen (12013847)
Published: (2025)

Map of hotspot areas around Lake Victoria, highlighted in red points, in Tanzania (top) and Kenya (bottom) using persistent hotspot definitions I–II.
by: Yewen Chen (12013847)
Published: (2025)

Hotspot prediction accuracy (95% predicted intervals) on test sets obtained using models developed using synthetic sampling training sets, compared to those developed using imbalanced training sets.
by: Yewen Chen (12013847)
Published: (2025)

Relative improvements (RIs) in prediction accuracy on test sets for the three scenarios from the proposed spatially weighted data fusion method using different predictor categories, compared to the approach using only baseline infection data.
by: Yewen Chen (12013847)
Published: (2025)

Study framework for enhancing early identification of schistosomiasis hotspots (early identification refers to the use of infection data only from the first year to develop prediction models).
by: Yewen Chen (12013847)
Published: (2025)

Relative improvements in hotspot prediction accuracy on test sets obtained using models developed on synthetic sampling training sets, compared to those developed on imbalanced training sets.
by: Yewen Chen (12013847)
Published: (2025)

Overall performance of each model in each of the three scenarios for predicting PHSs for <i>S. mansoni</i>, where the horizontal lines in the boxplots represent the median of accuracy.
by: Yewen Chen (12013847)
Published: (2025)

Empirical variograms and fitted curves by exponential variogram models.
by: Yewen Chen (12013847)
Published: (2025)

Study arms of SCORE for schistosomiasis.
by: Yewen Chen (12013847)
Published: (2025)

Interventions in the hotspot implementation units (IUs). Interventions in the hotspot IUs of the SchistoBreak study in three intervention periods in Pemba, Tanzania, from 2021 to 2023.
by: Lydia Trippler (10136316)
Published: (2025)

Demographic information of study participants. Demographic information of participants in school-based and household-based cross-sectional surveys of the SchistoBreak study implemented in Pemba, Tanzania, from 2021 to 2024.
by: Lydia Trippler (10136316)
Published: (2025)

Chance of infection with <i>Schistosoma haematobium.</i>
by: Lydia Trippler (10136316)
Published: (2025)

Risk factors for <i>Schistosoma haematobium</i> infection.
by: Lydia Trippler (10136316)
Published: (2025)

Characteristics of households participating in the SchistoBreak study in Pemba, Tanzania.
by: Lydia Trippler (10136316)
Published: (2025)

<i>Schistosoma haematobium</i> prevalence in hotspot implementation units (IUs) in annual school-based surveys (A) and household-based surveys (B) of the SchistoBreak study in Pemba, Tanzania, from 2021 to 2024.
by: Lydia Trippler (10136316)
Published: (2025)

Annual change in low-prevalence (orange) and hotspot (red) implementation units (IUs).
by: Lydia Trippler (10136316)
Published: (2025)

<i>Schistosoma haematobium</i> and microhematuria prevalence.
by: Lydia Trippler (10136316)
Published: (2025)

Study participation.
by: Lydia Trippler (10136316)
Published: (2025)

S2 Data - Adaptive integrated intervention approaches for schistosomiasis elimination in Pemba: A 4-year intervention study and focus on hotspots
by: Lydia Trippler (10136316)
Published: (2025)

S1 Data - Adaptive integrated intervention approaches for schistosomiasis elimination in Pemba: A 4-year intervention study and focus on hotspots
by: Lydia Trippler (10136316)
Published: (2025)

Microhematuria prevalence in hotspot implementation units.
by: Lydia Trippler (10136316)
Published: (2025)

Comparison of the changes in WHO risk category compared to the baseline in the previous MDAs baseline category.
by: Takafira Mduluza (39754)
Published: (2025)

Results of different approaches to determine persistent hotspots of <i>S. haematobium</i> prevalence (PPHS).
by: Takafira Mduluza (39754)
Published: (2025)

Measures of praziquantel efficacy (PZQ) against <i>Schistosoma haematobium</i> after the treatment during a mass drug administration (MDA).
by: Takafira Mduluza (39754)
Published: (2025)

Coverage of the mass drug administration programs at the national and district level, for each detected persistent hotspots of <i>S. haematobium</i> prevalence (PPHS).
by: Takafira Mduluza (39754)
Published: (2025)

Linear regression of the relationship between the egg reduction rate and distance to the nearest waterway.
by: Takafira Mduluza (39754)
Published: (2025)

The relationship between pre-treatment intensity of <i>Schistosoma haematobium</i> infection and cure rate (CR) after praziquantel (PZQ) treatment during six years of annual mass drug administrations (MDAs) in Zimbabwe.
by: Takafira Mduluza (39754)
Published: (2025)

Box plots showing baseline prevalence and mean egg count at pre-MDA1 in districts that were responders compared to those that were persistent hotspots of decreasing praziquantel efficacy (EPHS).
by: Takafira Mduluza (39754)
Published: (2025)

Box plots showing baseline prevalence and mean egg count at pre-MDA1 in districts that were responders compared to persistent hotspots of <i>S. haematobium</i> prevalence (PPHS).
by: Takafira Mduluza (39754)
Published: (2025)

Map of Zimbabwe highlighting the districts detected as persistent hotspots of <i>S. haematobium</i> prevalence (PPHS), persistent hotspots of decreased praziquantel efficacy (EPHS), and districts of both PPHS and EPHS.
by: Takafira Mduluza (39754)
Published: (2025)

Cannot write session to /tmp/vufind_sessions/sess_r8noaq5vu0kfpq7mr66rvkogcn