Pub Date : 2019-05-20DOI: 10.4172/2155-6180.1000430
C. B. Bagwell, C. Bray, D. Herbert, Beth L. Hill, M. Inokuma, Gregory T. Stelzer, B. Hunsberger
SNE methods are a set of 9 to 10 interconnected algorithms that map high-dimensional data into low-dimensional space while minimizing loss of information. Each step in this process is important for producing high-quality maps. Cense′™ mapping not only enhances many of the steps in this process but also fundamentally changes the underlying mathematics to produce high-quality maps. The key mathematical enhancement is to leverage the Cauchy distribution for creating both high-dimensional and lowdimensional similarity matrices. This simple change eliminates the necessity of using perplexity and entropy and results in maps that optimally separate clusters defined in high-dimensional space. It also eliminates the loss of cluster resolution commonly seen with t-SNE with higher numbers of events. There is just one free parameter for Cen-se′ mapping, and that parameter rarely needs to change. Other enhancements include a relatively low memory footprint, highly threaded implementation, and a final classification step that can process millions of events in seconds. When the Cen-se′ mapping system is integrated with probability state modeling, the clusters of events are positioned in a reproducible manner and are colored, labeled, and enumerated automatically. We provide a step-by-step, simple example that describes how the Cen-se′ method works and differs from the t-SNE method. We present data from several experiments to compare the two mapping strategies on high-dimensional mass cytometry data. We provide a section on information theory to explain how the steepest gradient equations were formulated and how they control the movement of the low-dimensional points as the system renders the map Since existing implementations of the t-SNE algorithm can easily be modified with many of these enhancements, this work should result in more effective use of this very exciting and far-reaching new technology.
{"title":"Improving the t-SNE Algorithms for Cytometry and Other Technologies: Cen-Se' Mapping","authors":"C. B. Bagwell, C. Bray, D. Herbert, Beth L. Hill, M. Inokuma, Gregory T. Stelzer, B. Hunsberger","doi":"10.4172/2155-6180.1000430","DOIUrl":"https://doi.org/10.4172/2155-6180.1000430","url":null,"abstract":"SNE methods are a set of 9 to 10 interconnected algorithms that map high-dimensional data into low-dimensional space while minimizing loss of information. Each step in this process is important for producing high-quality maps. Cense′™ mapping not only enhances many of the steps in this process but also fundamentally changes the underlying mathematics to produce high-quality maps. The key mathematical enhancement is to leverage the Cauchy distribution for creating both high-dimensional and lowdimensional similarity matrices. This simple change eliminates the necessity of using perplexity and entropy and results in maps that optimally separate clusters defined in high-dimensional space. It also eliminates the loss of cluster resolution commonly seen with t-SNE with higher numbers of events. There is just one free parameter for Cen-se′ mapping, and that parameter rarely needs to change. Other enhancements include a relatively low memory footprint, highly threaded implementation, and a final classification step that can process millions of events in seconds. When the Cen-se′ mapping system is integrated with probability state modeling, the clusters of events are positioned in a reproducible manner and are colored, labeled, and enumerated automatically. We provide a step-by-step, simple example that describes how the Cen-se′ method works and differs from the t-SNE method. We present data from several experiments to compare the two mapping strategies on high-dimensional mass cytometry data. We provide a section on information theory to explain how the steepest gradient equations were formulated and how they control the movement of the low-dimensional points as the system renders the map Since existing implementations of the t-SNE algorithm can easily be modified with many of these enhancements, this work should result in more effective use of this very exciting and far-reaching new technology.","PeriodicalId":87294,"journal":{"name":"Journal of biometrics & biostatistics","volume":"10 1","pages":"1-13"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42397992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-02-18DOI: 10.4172/2155-6180.1000422
D. Ajay, Gbolahan Akanji Fabiyi, S. Bello
Introduction: Social isolation is a global public health challenge. Social isolation may worsen the prognosis of diabetes. Assessment of social isolation among older diabetic adults is important, and the use of valid and reliable measure is necessary. Therefore, the aim of this study was to determine the prevalence of social isolation, and to investigate the factor structure and reliability of the abbreviated version of Lubben Social Network Scale (LSNS-6) among older diabetic patients in Abeokuta, Nigeria. Methods: A descriptive cross-sectional study was conducted, wherein type 2 diabetic patients aged 50 and above were consecutively recruited from Federal Medical Centre, Idi Aba, and General Hospital, Ijaye. A pre-tested, intervieweradministered, structured questionnaire was used to collect data. The factor structure of the LSNS-6 was investigated using exploratory factor analysis (EFA) with principal axis factoring method of estimation and varimax rotation. Estimates of the internal consistency reliability of the subscales and the overall scale were obtained from alpha coefficients. Results: A total of 160 respondents with the mean age of 63.2 ± 9.6 years and the mean duration of diabetes of 7.5 ± 6.8 years participated in the study. Sixty-six (41.3%) respondents were socially isolated (LSNS-6 score < 12). The EFA revealed 2 factors (i.e. Family and Friend) which explained 72.6% of the total variance. Cronbach’s alpha coefficients for Family and Friend subscales were 0.84 and 0.90, respectively. Stratified alpha for the scale was 0.90. Conclusion: The prevalence of social isolation among the older diabetic patients was high. Also, the LSNS-6 was found to be a reliable and valid instrument for assessing social isolation in this study population. Assessment and management of social isolation should be incorporated into diabetes treatment plan for older diabetic patients.
{"title":"Prevalence of Social Isolation and Psychometric Properties of Lubben Social Network Scale among Older Diabetic Patients in Abeokuta, Nigeria","authors":"D. Ajay, Gbolahan Akanji Fabiyi, S. Bello","doi":"10.4172/2155-6180.1000422","DOIUrl":"https://doi.org/10.4172/2155-6180.1000422","url":null,"abstract":"Introduction: Social isolation is a global public health challenge. Social isolation may worsen the prognosis of diabetes. Assessment of social isolation among older diabetic adults is important, and the use of valid and reliable measure is necessary. Therefore, the aim of this study was to determine the prevalence of social isolation, and to investigate the factor structure and reliability of the abbreviated version of Lubben Social Network Scale (LSNS-6) among older diabetic patients in Abeokuta, Nigeria. \u0000Methods: A descriptive cross-sectional study was conducted, wherein type 2 diabetic patients aged 50 and above were consecutively recruited from Federal Medical Centre, Idi Aba, and General Hospital, Ijaye. A pre-tested, intervieweradministered, structured questionnaire was used to collect data. The factor structure of the LSNS-6 was investigated using exploratory factor analysis (EFA) with principal axis factoring method of estimation and varimax rotation. Estimates of the internal consistency reliability of the subscales and the overall scale were obtained from alpha coefficients. \u0000 Results: A total of 160 respondents with the mean age of 63.2 ± 9.6 years and the mean duration of diabetes of 7.5 ± 6.8 years participated in the study. Sixty-six (41.3%) respondents were socially isolated (LSNS-6 score < 12). The EFA revealed 2 factors (i.e. Family and Friend) which explained 72.6% of the total variance. Cronbach’s alpha coefficients for Family and Friend subscales were 0.84 and 0.90, respectively. Stratified alpha for the scale was 0.90. \u0000Conclusion: The prevalence of social isolation among the older diabetic patients was high. Also, the LSNS-6 was found to be a reliable and valid instrument for assessing social isolation in this study population. Assessment and management of social isolation should be incorporated into diabetes treatment plan for older diabetic patients.","PeriodicalId":87294,"journal":{"name":"Journal of biometrics & biostatistics","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43598598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.37421/JBMBS.2019.10.434
M. Bashir, Humariya Heena, T. Wani
Background: Adequate biostatistics knowledge among healthcare professionals is imperative for understanding medical literature and practicing evidence-based medicine. This study assessed the basic and advanced knowledge in biostatistics and clinical research among healthcare workers at the King Fahad Medical City (KFMC), Riyadh, Saudi Arabia. Methods: In this cross-sectional survey, data was collected from healthcare providers using a self-administered questionnaire, having questions related to demographics, biostatistics and clinical research. Data analysis was performed using statistical package SPSS 22. Results: Of 194 participants (63 [32.5%] consultants, 52 [26.8%] residents, and 79 [40.7%] allied healthcare providers), 45.4% had positive attitude towards learning biostatistics. Only 35.1% correctly answered biostatistics and clinical research instrument-related questions. Half participants had low score, 33% had good score, and 18-19% had excellent score of basic and advanced knowledge of biostatistics and clinical research. The highest degree and number of years of experience in biostatistics after medical school graduation were significantly (χ2 (2)=16.589, p<0.001) associated with basic and advanced biostatistics knowledge scores. Conclusion: Timely and painstaking training courses in biostatistics and clinical research are needed to improve the research standards in Saudi Arabia. Interested candidates should collaborated with statisticians to improve quality of their work and enhance their statistical skills.
{"title":"Assessment of Basic and Advanced Knowledge in Biostatistics and Clinical Research among Health care Professionals at King Fahad Medical City, Riyadh, KSA: A cross-Sectional Survey","authors":"M. Bashir, Humariya Heena, T. Wani","doi":"10.37421/JBMBS.2019.10.434","DOIUrl":"https://doi.org/10.37421/JBMBS.2019.10.434","url":null,"abstract":"Background: Adequate biostatistics knowledge among healthcare professionals is imperative for understanding medical literature and practicing evidence-based medicine. This study assessed the basic and advanced knowledge in biostatistics and clinical research among healthcare workers at the King Fahad Medical City (KFMC), Riyadh, Saudi Arabia. Methods: In this cross-sectional survey, data was collected from healthcare providers using a self-administered questionnaire, having questions related to demographics, biostatistics and clinical research. Data analysis was performed using statistical package SPSS 22. Results: Of 194 participants (63 [32.5%] consultants, 52 [26.8%] residents, and 79 [40.7%] allied healthcare providers), 45.4% had positive attitude towards learning biostatistics. Only 35.1% correctly answered biostatistics and clinical research instrument-related questions. Half participants had low score, 33% had good score, and 18-19% had excellent score of basic and advanced knowledge of biostatistics and clinical research. The highest degree and number of years of experience in biostatistics after medical school graduation were significantly (χ2 (2)=16.589, p<0.001) associated with basic and advanced biostatistics knowledge scores. Conclusion: Timely and painstaking training courses in biostatistics and clinical research are needed to improve the research standards in Saudi Arabia. Interested candidates should collaborated with statisticians to improve quality of their work and enhance their statistical skills.","PeriodicalId":87294,"journal":{"name":"Journal of biometrics & biostatistics","volume":"190 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"70054254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-26DOI: 10.4172/2155-6180.1000415
Yirui Hu, D. Hoover
Intervention effects on continuous longitudinal normal outcomes are often estimated in two-arm pre-post interventional studies with b≥1 pre- and k≥1 post-intervention measures using “Difference-in-Differences” (DD) analysis. Although randomization is preferred, non-randomized designs are often necessary due to practical constraints. Power/sample size estimation methods for non-randomized DD designs that incorporate the correlation structure of repeated measures are needed. We derive Generalized Least Squares (GLS) variance estimate of the intervention effect. For the commonly assumed compound symmetry (CS) correlation structure (where the correlation between all repeated measures is a constantρ) this leads to simple power and sample size estimation formulas that can be implemented using pencil and paper. Given a constrained number of total timepoints (T), having as close to possible equal number of pre-and post-intervention timepoints (b=k) achieves greatest power. When planning a study with 7 or less timepoints, given large ρ(ρ≥0.6) in multiple baseline measures (b≥2) or ρ≥0.8 in a single baseline setting, the improvement in power from a randomized versus non-randomized DD design may be minor. Extensions to cluster study designs and incorporation of time invariant covariates are given. Applications to study planning are illustrated using three real examples with T=4 timepoints and ρ ranging from 0.55 to 0.75.
{"title":"Simple Power and Sample Size Estimation for Non-Randomized Longitudinal Difference in Differences Studies","authors":"Yirui Hu, D. Hoover","doi":"10.4172/2155-6180.1000415","DOIUrl":"https://doi.org/10.4172/2155-6180.1000415","url":null,"abstract":"Intervention effects on continuous longitudinal normal outcomes are often estimated in two-arm pre-post interventional studies with b≥1 pre- and k≥1 post-intervention measures using “Difference-in-Differences” (DD) analysis. Although randomization is preferred, non-randomized designs are often necessary due to practical constraints. Power/sample size estimation methods for non-randomized DD designs that incorporate the correlation structure of repeated measures are needed. We derive Generalized Least Squares (GLS) variance estimate of the intervention effect. For the commonly assumed compound symmetry (CS) correlation structure (where the correlation between all repeated measures is a constantρ) this leads to simple power and sample size estimation formulas that can be implemented using pencil and paper. Given a constrained number of total timepoints (T), having as close to possible equal number of pre-and post-intervention timepoints (b=k) achieves greatest power. When planning a study with 7 or less timepoints, given large ρ(ρ≥0.6) in multiple baseline measures (b≥2) or ρ≥0.8 in a single baseline setting, the improvement in power from a randomized versus non-randomized DD design may be minor. Extensions to cluster study designs and incorporation of time invariant covariates are given. Applications to study planning are illustrated using three real examples with T=4 timepoints and ρ ranging from 0.55 to 0.75.","PeriodicalId":87294,"journal":{"name":"Journal of biometrics & biostatistics","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41917199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-04DOI: 10.4172/2155-6180.1000394
C. Qualls, Peter Evans, A. Perciaccante, R. Bianucci, D. Lippi, O. Appenzeller
The structures of the human hands and feet are shaped by evolution and its effects on the brain, skeleton and other structures, and on behavior. We used measurements obtained of hands and feet from living humans in Europe, the Americas (South and North) and Australia and images of hands and feet in cave art, paintings, and photographs obtained from the Web including some from Africa. We used the ratios of the third finger/width of hand and second toe/width of foot. We hypothesized that hand ratios would not have changed over millennia whereas, because of the use of footwear and mechanical locomotion, the ratios obtained from feet could have changed significantly. Here we report that statistical analyses and modeling confirmed our initial hypothesis.
{"title":"The human hand and foot in evolution and art : the effects of wearing footwear","authors":"C. Qualls, Peter Evans, A. Perciaccante, R. Bianucci, D. Lippi, O. Appenzeller","doi":"10.4172/2155-6180.1000394","DOIUrl":"https://doi.org/10.4172/2155-6180.1000394","url":null,"abstract":"The structures of the human hands and feet are shaped by evolution and its effects on the brain, skeleton and other structures, and on behavior. We used measurements obtained of hands and feet from living humans in Europe, the Americas (South and North) and Australia and images of hands and feet in cave art, paintings, and photographs obtained from the Web including some from Africa. We used the ratios of the third finger/width of hand and second toe/width of foot. We hypothesized that hand ratios would not have changed over millennia whereas, because of the use of footwear and mechanical locomotion, the ratios obtained from feet could have changed significantly. Here we report that statistical analyses and modeling confirmed our initial hypothesis.","PeriodicalId":87294,"journal":{"name":"Journal of biometrics & biostatistics","volume":" ","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2018-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.4172/2155-6180.1000394","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46079974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-28DOI: 10.4172/2155-6180.1000390
Tsitsiashvili Gurami, Bulgakov Victor, Losev Alexandr
In this paper, an algorithm of directed graph replacement by acyclic directed graph is constructing and is applying for a study of the key players required for connecting ABA signaling and ABA-mediated drought and thermo tolerance.
{"title":"Replacement of Directed Graph by Acyclic Directed Graph and Its Application in Biostatistics","authors":"Tsitsiashvili Gurami, Bulgakov Victor, Losev Alexandr","doi":"10.4172/2155-6180.1000390","DOIUrl":"https://doi.org/10.4172/2155-6180.1000390","url":null,"abstract":"In this paper, an algorithm of directed graph replacement by acyclic directed graph is constructing and is applying for a study of the key players required for connecting ABA signaling and ABA-mediated drought and thermo tolerance.","PeriodicalId":87294,"journal":{"name":"Journal of biometrics & biostatistics","volume":"9 1","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2018-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.4172/2155-6180.1000390","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45497800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-02-27DOI: 10.4172/2155-6180.1000391
N. Demirkuş, Divin Alkan
In this study, first of all, a definition of sets will be explained. In addition to the definition of the set known in mathematics, new approaches will be presented. Ten rules about the set definition model will be proposed. 1. It is necessary to determine the title and descriptive identity of the set. 2. It is necessary to determine the address of the set. 3. Specifying the appropriate boundary of the set of creature. 4. Specifying the time of the cluster. 5. The status of the cluster action must be specified. 6. The type and group of the cluster should be specified. 7. The status of live or non-live clusters should be indicated. 8. The load of the cluster element must be specified. 9. If possible, the gender of the cluster element must be specified. 10. The scientific name of the cluster elements must be specified. Out of these ten rules: the cluster must be specified if there is a special case. Later, the definitions of these rules will be presented with examples. Also gender, load, location, action, group, live and inanimate etc., cluster properties will be defined. Examples of animate and inanimate creature sets will be presented. After all, we gain mathematical cluster consciousness of all animate and inanimate creatures and systems in the nature. In addition to this; Natural, artificial, virtual, objective, mental, light etc., examples of sets will be given.
{"title":"A Brand New Approach to Sets in Mathematics","authors":"N. Demirkuş, Divin Alkan","doi":"10.4172/2155-6180.1000391","DOIUrl":"https://doi.org/10.4172/2155-6180.1000391","url":null,"abstract":"In this study, first of all, a definition of sets will be explained. In addition to the definition of the set known in mathematics, new approaches will be presented. Ten rules about the set definition model will be proposed. 1. It is necessary to determine the title and descriptive identity of the set. 2. It is necessary to determine the address of the set. 3. Specifying the appropriate boundary of the set of creature. 4. Specifying the time of the cluster. 5. The status of the cluster action must be specified. 6. The type and group of the cluster should be specified. 7. The status of live or non-live clusters should be indicated. 8. The load of the cluster element must be specified. 9. If possible, the gender of the cluster element must be specified. 10. The scientific name of the cluster elements must be specified. Out of these ten rules: the cluster must be specified if there is a special case. Later, the definitions of these rules will be presented with examples. Also gender, load, location, action, group, live and inanimate etc., cluster properties will be defined. Examples of animate and inanimate creature sets will be presented. After all, we gain mathematical cluster consciousness of all animate and inanimate creatures and systems in the nature. In addition to this; Natural, artificial, virtual, objective, mental, light etc., examples of sets will be given.","PeriodicalId":87294,"journal":{"name":"Journal of biometrics & biostatistics","volume":"9 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2018-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.4172/2155-6180.1000391","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43994052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-01-30DOI: 10.4172/2155-6180.1000387
Uzuke Ca, O. Ica
A statistical model which can be used to estimate the loss of fertility due to delayed marriage after the age at menarche was proposed. This model made use of a cohort of women who had their menarche at age 13 years. The expected number of years of spinsterhood was also estimated as e(x). The result showed that a spinster who had her menarche at age 13 years and delayed her marriage on the average 12 years is going to lose on the average 2 children.
{"title":"Estimating and Testing the Effect of Delayed Marriage on Fertility","authors":"Uzuke Ca, O. Ica","doi":"10.4172/2155-6180.1000387","DOIUrl":"https://doi.org/10.4172/2155-6180.1000387","url":null,"abstract":"A statistical model which can be used to estimate the loss of fertility due to delayed marriage after the age at menarche was proposed. This model made use of a cohort of women who had their menarche at age 13 years. The expected number of years of spinsterhood was also estimated as e(x). The result showed that a spinster who had her menarche at age 13 years and delayed her marriage on the average 12 years is going to lose on the average 2 children.","PeriodicalId":87294,"journal":{"name":"Journal of biometrics & biostatistics","volume":"9 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2018-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.4172/2155-6180.1000387","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44819871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Qianfan Wu, Adel Boueiz, Alican Bozkurt, Arya Masoomi, Allan Wang, Dawn L DeMeo, Scott T Weiss, Weiliang Qiu
Predicting disease status for a complex human disease using genomic data is an important, yet challenging, step in personalized medicine. Among many challenges, the so-called curse of dimensionality problem results in unsatisfied performances of many state-of-art machine learning algorithms. A major recent advance in machine learning is the rapid development of deep learning algorithms that can efficiently extract meaningful features from high-dimensional and complex datasets through a stacked and hierarchical learning process. Deep learning has shown breakthrough performance in several areas including image recognition, natural language processing, and speech recognition. However, the performance of deep learning in predicting disease status using genomic datasets is still not well studied. In this article, we performed a review on the four relevant articles that we found through our thorough literature search. All four articles first used auto-encoders to project high-dimensional genomic data to a low dimensional space and then applied the state-of-the-art machine learning algorithms to predict disease status based on the low-dimensional representations. These deep learning approaches outperformed existing prediction methods, such as prediction based on transcript-wise screening and prediction based on principal component analysis. The limitations of the current deep learning approach and possible improvements were also discussed.
{"title":"Deep Learning Methods for Predicting Disease Status Using Genomic Data.","authors":"Qianfan Wu, Adel Boueiz, Alican Bozkurt, Arya Masoomi, Allan Wang, Dawn L DeMeo, Scott T Weiss, Weiliang Qiu","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Predicting disease status for a complex human disease using genomic data is an important, yet challenging, step in personalized medicine. Among many challenges, the so-called curse of dimensionality problem results in unsatisfied performances of many state-of-art machine learning algorithms. A major recent advance in machine learning is the rapid development of deep learning algorithms that can efficiently extract meaningful features from high-dimensional and complex datasets through a stacked and hierarchical learning process. Deep learning has shown breakthrough performance in several areas including image recognition, natural language processing, and speech recognition. However, the performance of deep learning in predicting disease status using genomic datasets is still not well studied. In this article, we performed a review on the four relevant articles that we found through our thorough literature search. All four articles first used auto-encoders to project high-dimensional genomic data to a low dimensional space and then applied the state-of-the-art machine learning algorithms to predict disease status based on the low-dimensional representations. These deep learning approaches outperformed existing prediction methods, such as prediction based on transcript-wise screening and prediction based on principal component analysis. The limitations of the current deep learning approach and possible improvements were also discussed.</p>","PeriodicalId":87294,"journal":{"name":"Journal of biometrics & biostatistics","volume":"9 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6530791/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"37274873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-01-01DOI: 10.4172/2155-6180.1000396
C. Qualls, S. Lucas, Ali Am, O. Appenzeller
We analyzed Conodonts and rocks using Inductively Coupled Plasma-Optical Emission Spectroscopy (ICP-OES) using statistical methods to compare the tipping points for arsenic (As) and lead (Pb) in conodonts and contemporaneous human tissues. We found that ancient seas contained high levels of As which also occurred in Conodont teeth and which was leached from rocks; a biogenic enrichment. We show that there is a significant decline in reaching the tipping point with time (P=0.01) implying that the sources of these neurotoxic metals in modern teeth have decreased such that Pb and As no longer accumulate in human apatite as it did in the apatite of Conodont teeth. The probability of exceeding the tipping point increases significantly with increasing As concentration (P=0.01) and increasing Pb concentration (P=0.04). This suggests that the toxic effects of these metals may be additive. Citation: Qualls C, Lucas SG, Ali AM, Appenzeller O (2018) Tipping Points: A Statistical Comparison between Humans and Conodonts. J Biom Biostat 9: 396. doi: 10.4172/2155-6180.1000396
我们使用电感耦合等离子体发射光谱(ICP-OES)对牙形刺和岩石进行了分析，并采用统计方法比较了牙形刺和同期人体组织中砷和铅的临界点。我们发现古代海洋中含有高浓度的砷，这些砷也出现在牙形石牙齿中，并且是从岩石中浸出的;生物富集。我们发现，随着时间的推移，达到临界点的时间显著下降(P=0.01)，这意味着现代牙齿中这些神经毒性金属的来源已经减少，以至于铅和砷不再像在牙形石牙齿的磷灰石中那样在人类磷灰石中积累。随着As浓度的增加(P=0.01)和Pb浓度的增加(P=0.04)，超过临界点的概率显著增加。这表明这些金属的毒性作用可能是加性的。引用本文:Qualls C, Lucas SG, Ali AM, Appenzeller O(2018)临界点:人类与牙形刺的统计比较。[J]中国生物医学工程学报，9:393。doi: 10.4172 / 2155 - 6180.1000396
{"title":"Tipping Points: A Statistical Comparison between Humans and Conodonts","authors":"C. Qualls, S. Lucas, Ali Am, O. Appenzeller","doi":"10.4172/2155-6180.1000396","DOIUrl":"https://doi.org/10.4172/2155-6180.1000396","url":null,"abstract":"We analyzed Conodonts and rocks using Inductively Coupled Plasma-Optical Emission Spectroscopy (ICP-OES) using statistical methods to compare the tipping points for arsenic (As) and lead (Pb) in conodonts and contemporaneous human tissues. We found that ancient seas contained high levels of As which also occurred in Conodont teeth and which was leached from rocks; a biogenic enrichment. We show that there is a significant decline in reaching the tipping point with time (P=0.01) implying that the sources of these neurotoxic metals in modern teeth have decreased such that Pb and As no longer accumulate in human apatite as it did in the apatite of Conodont teeth. The probability of exceeding the tipping point increases significantly with increasing As concentration (P=0.01) and increasing Pb concentration (P=0.04). This suggests that the toxic effects of these metals may be additive. Citation: Qualls C, Lucas SG, Ali AM, Appenzeller O (2018) Tipping Points: A Statistical Comparison between Humans and Conodonts. J Biom Biostat 9: 396. doi: 10.4172/2155-6180.1000396","PeriodicalId":87294,"journal":{"name":"Journal of biometrics & biostatistics","volume":"09 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2018-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.4172/2155-6180.1000396","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"70292309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：