Discriminant Function Analysis of Foramen Magnum Variables in South Indian Population | Chapter 05 | Issues and Developments in Medicine and Medical Research Vol. 4

 Introduction: The foramen magnum is an important component of the craniovertebral junction's interplay of bony, ligamentous, and muscular tissues. Multivariate discriminant function analysis was used to analyse all of the variables. This multivariate analysis is concerned with the challenge of allocating individual values to a specific group, which is based on the sum of a number of variable characteristics of an individual, with all characters given equal weightage.

Methods: The study sample consisted of 200 south Indian skull bones (105 males and 95 females). The sex differences between the skull bones were investigated using multivariate discriminant function analysis. The multivariate linear discriminant function works on the idea that sex is a dependent variable and measured variables are independent variables.

The results showed that 95 male skull bones were accurately sexed and 84 female skull bones were correctly sexed out of 105. Only 179 skull bones out of 200 were correctly sexed. So 90 percent of male skull bones were accurately sexed, whereas 88 percent of female skull bones were correctly sexed. With all of the variables taken into account, 90 percent of skull bones were correctly sexed.

Conclusion: When normal statistical methods and multivariate analysis results were compared, it was evident that multivariate analysis was far superior in terms of both reliability and accuracy. As a result, with limited resources, multivariate analysis is the best way for determining the sex of skull bones.

Author(S) Details

S. P. Vinutha
JSS Medical College, JSSAHER, Mysuru, Karnataka, India.

R. Shubha
Kempegowda Institute of Medical Sciences, Bengaluru, Karnataka, India.

View Book:- https://stm.bookpi.org/IDMMR-V4/article/view/5542

A Review of Multivariate Analysis and Machine Learning in Pediatric Epilepsy Research | Chapter 8 | New Frontiers in Medicine and Medical Research Vol. 10

 Because of the development of the brain, paediatric epilepsy poses some unique challenges and opportunities in seizure control. In childhood epilepsy, multivariate analysis and machine learning methods are rapidly being used in seizure detection and prediction, epileptogenic lesion identification, and clinical outcome prediction. These methods have made it feasible to detect seizures on an electroencephalogram (EEG) and detect lesions on imaging automatically, according to this publication, which examined such studies to provide an overview of the subject. Furthermore, despite the fact that seizures have long been assumed to occur at random or without warning, it has been revealed that seizures can occur non-randomly in complex patient-specific conditions. Preictal variations on EEG can be detected and distinguished from interictal activities using machine learning techniques, allowing seizure occurrence to be predicted. Seizure prediction, on the other hand, has substantial obstacles, such as the need for appropriate clinical data and good machine learning algorithms to recognise complicated seizure occurrence patterns. Seizure outcome factors have also been discovered using multivariate analysis and machine learning techniques in outcome studies. More research is needed to improve these relatively new techniques and confirmatory studies are needed to make them accurate and dependable. Multivariate analysis and machine learning are expected to contribute more to identifying complex seizure patterns, epileptogenic lesions, and outcome predictors to improve seizure detection/prediction, lesion detection, and seizure outcome prediction, resulting in better seizure control, lower mortality rates, and improved quality of life in children with epilepsy.

Author (S) Details

Jing Zhang
Department of Neurology, Washington University in St. Louis, St. Louis, MO 63110, USA.

View Book :- https://stm.bookpi.org/NFMMR-V10/article/view/3507

Multivariate Analysis in Pediatric Brain Tumor Research | Chapter 21 | New Frontiers in Medicine and Medical Research Vol. 6

 Brain tumours in children are fatal, and more research is needed to enhance patient care. In children with brain tumours, multivariate analysis has become more common in recent years for tumour categorization (segmentation) and survival (outcome) assessment. In order to provide an overview of the topic, this publication analysed studies that used multivariate analysis in paediatric brain tumour research. Large variations in tumour categorization outcomes were identified during tumour classification examinations. Furthermore, the multivariate survival analysis model had a moderate error rate, which could lead to erroneous survival estimates and misidentification of prognostic factors. To address these issues, this paper looked at the data processing chains in these multivariate analyses in detail, suggesting that optimising and standardising them could improve tumour classification and survival analysis, as well as reduce variations and errors in classification and survival estimates. As multivariate analytic tools, data processing technology, and imaging techniques evolve in the twenty-first century's Big Data era, Complicated imaging data processing problems in tumour classification are predicted to be overcome, and complex data processing will be revolutionised. This will enable accurate automatic tumour categorization and segmentation, which will aid in early cancer identification and treatment, as well as therapy planning and monitoring of tumour progression and treatment effects. Furthermore, multivariate analytic methods and technologies will assist change patient treatment and actually benefit children with brain tumours, with breakthroughs in survival assessment to guide life-saving rescue and recovery plans.

Author (S) Details

Neha Agarwal
DNB Gynaecology and Obstetrics Department of Gynaecology and Obstetrics Central Hospital, South Eastern Railways Garden Reach, Kolkata - 700043, India.

Anupam Lahiri
DNB General Surgery Department of General Surgery Central Hospital, South Eastern Railways Garden Reach, Kolkata – 700043, India.

View Book :- https://stm.bookpi.org/NFMMR-V6/article/view/2779

Significance of Textural Parameters for Characterization of Clastic Sedimentary Processes: Case Study of Benin Formation, Niger Delta, Nigeria | Chapter 1 | Modern Advances in Geography, Environment and Earth Sciences Vol. 4

 The textural properties and depositional processes of 120 sand samples collected over a 47-kilometer transect from Ikot Abasi to Eket in southern Nigeria were determined using granulometric analysis. The varied size distributions for each sample were determined using standard sedimentological procedures such as sieve analysis. The fluidity factor of the depositing medium and the energy factor of the deposition environment are reflected in the sediment size distribution. This was also subjected to statistical analysis (mean grain size, median, sorting, kurtosis, skewness, bivariate and multivariate analyses). The samples range in size from extremely fine grain to pebbly (3.23 to -1.53) in diameter, and are sorted from very poorly to very well (2.069 to 0.294), with around 86 percent of the samples being badly sorted. The sediments are mostly leptokurtic (91%) with only a few (9 samples) platykurtic (range 8.148 to -1.082) and coarse to extremely fine skewed in character. Saltation and surface creep, mostly due to current and channel action, are the major modes of conveyance recorded by these sediments. Bivariate analysis revealed that the majority of the sediments are related to river deposition processes, with coastal processes taking a back seat. The sediments of this study area were generally characterised by a shallow marine disturbed environment, according to multivariate analysis. The sediments were deposited mostly via graded suspension to bottom suspension and rolling, according to the CM pattern. In a shallow marine depositional environment, these characteristics identify sediments deposited by fluvio-deltaic processes dominated by tractive current patterns. The sediments throughout the transect analysed reveal energy setting linked with a combination of high and relaxed energy at various points during the depositional process, as evidenced by their moderate sorting, which is generally positively skewed and leptokurtic.

Author(s) Details

E. E. Okon
Department of Geology, University of Calabar, Calabar, Nigeria.

N. U. Essien
Department of Geosciences, Akwa Ibom State University, Mkpat Enin, Nigeria.

A. O. Ilori
Department of Civil Engineering, University of Uyo, Uyo, Nigeria.

S. N. Njoku
Energy and Mineral Resources Ltd, Lagos, Nigeria.

View Book :- https://stm.bookpi.org/MAGEES-4/article/view/1045