MétaCan
Menu
Back to cohort

A Spatial Scan Approach to Detecting Focused‐Global Clustering in Case‐Control Data

2012· article· en· W2153140731 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
aboutThe title or abstract carries a Canadian signal from the geographic lexicon.

Bibliographic record

VenueGeographical Analysis · 2012
Typearticle
Languageen
FieldMedicine
TopicData-Driven Disease Surveillance
Canadian institutionsMcMaster University
Fundersnot available
KeywordsCluster analysisEvent (particle physics)Computer scienceGeographyCluster (spacecraft)Focus (optics)Data miningCartographyArtificial intelligencePhysics

Abstract

fetched live from OpenAlex

Clustering of spatial event data around points of interest (such as point‐emitting sources of pollution) can indicate a relationship between the probability of the event's occurrence and the distance from those points of interest. Several focused cluster detection methods have been developed to identify such clustering when it occurs. We present a focused spatial scan cluster detection method for detecting clustering of cases around points of interest in case‐control data. This method has more power to detect clustering than the traditional focused spatial scan method and requires less parameterization than many other alternatives. We test this method with synthetic hot spot and clinal cluster data, and then with real‐world data for motor vehicle collisions involving child pedestrians in T oronto, C anada. The method performs reasonably well in comparison with other methods, provides descriptive information about the range of clustering around points of interest, and does not require corrections for multiple testing. Future work will incorporate this approach with methods that search for clusters in non‐circular shapes—such as along water drainage basins and road networks. La aglomeración de eventos espaciales alrededor de puntos de interés (como fuentes de contaminación de emisión de tipo puntual), puede indicar una relación entre la probabilidad de ocurrencia del evento y la distancia de los puntos de interés. Varios métodos de detección de aglomeración enfocada (focus cluster) han sido desarrollados para identificar este tipo de aglomeración cuando esta se produce. Los autores presentan un método de barrido espacial para detección de focus clusters para identificar la concentración de casos alrededor de los puntos de interés en datos de tipo caso‐control ( case‐control data ). Este método es más potente para la detección de aglomeraciones que el método tradicional basado en exploración espacial y requiere de menos parámetros que otras técnicas alternativas. El método propuesto es puesto a prueba vía hot spots y datos de aglomeraciones en gradiente ( clinal,cluster data ) sintéticos y luego con datos reales de accidentes de tráfico de peatones infantiles en Toronto, Canadá. El método funciona razonablemente bien en comparación a otros métodos, proporciona información descriptiva sobre el alcance de la aglomeración alrededor de los puntos de interés, y no requiere correcciones para el problema de pruebas múltiples (multiple testing) . En el futuro, los autores planean incorporar este enfoque a métodos que identifican aglomeraciones en formas no circulares‐tal como las áreas a lo largo de las cuencas de drenaje de agua y redes de carreteras. 围绕兴趣点的空间事件数据聚类(如点源污染)可表征事件发生概率和与兴趣点距离间的关系。目前已有几种集聚点聚类探测方法用来识别此类事件发生的集聚情况。本文提出了一种聚焦空间扫描聚类方法来探测个例对照数据的兴趣点事件聚类。该方法比传统空间扫描方法具有更强的探测空间聚类的性能,并且所需参数较少。通过综合热点与渐变聚类数据对该方法进行测试,然后将其应用于加拿大多伦多市涉及儿童行人的车辆碰撞数据中。对比实验表明,该方法结果更为合理,并提供了兴趣点周围聚类范围的描述性信息,且不需要对多重检验结果进行修正。下一步研究将与寻找非圆形区域(如排水防水区与道路网络)聚类的分析方法集成。

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.112
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.005
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.026
GPT teacher head0.291
Teacher spread0.265 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it