The Experts below are selected from a list of 99999 Experts worldwide ranked by ideXlab platform
Ingmar Weber - One of the best experts on this subject based on the ideXlab platform.
-
Lifestyle Disease Surveillance Using Population Search Behavior: Feasibility Study.
Journal of medical Internet research, 2020Co-Authors: Shahan Ali Memon, Saquib Razak, Ingmar WeberAbstract:Background: As the process of producing official health statistics for Lifestyle Diseases is slow, researchers have explored using Web search data as a proxy for Lifestyle Disease surveillance. Existing studies, however, are prone to at least one of the following issues: ad-hoc keyword selection, overfitting, insufficient predictive evaluation, lack of generalization, and failure to compare against trivial baselines.Objective: The aims of this study were to (1) employ a corrective approach improving previous methods; (2) study the key limitations in using Google Trends for Lifestyle Disease surveillance; and (3) test the generalizability of our methodology to other countries beyond the United States.Methods: For each of the target variables (diabetes, obesity, and exercise), prevalence rates were collected. After a rigorous keyword selection process, data from Google Trends were collected. These data were denormalized to form spatio-temporal indices. L1-regularized regression models were trained to predict prevalence rates from denormalized Google Trends indices. Models were tested on a held-out set and compared against baselines from the literature as well as a trivial last year equals this year baseline. A similar analysis was done using a multivariate spatio-temporal model where the previous year’s prevalence was included as a covariate. This model was modified to create a time-lagged regression analysis framework. Finally, a hierarchical time-lagged multivariate spatio-temporal model was created to account for subnational trends in the data. The model trained on US data was, then, applied in a transfer learning framework to Canada.Results: In the US context, our proposed models beat the performances of the prior work, as well as the trivial baselines. In terms of the mean absolute error (MAE), the best of our proposed models yields 24% improvement (0.72-0.55; P
-
Lifestyle Disease Surveillance Using Population Search Behavior: Feasibility Study (Preprint)
2019Co-Authors: Shahan Ali Memon, Saquib Razak, Ingmar WeberAbstract:BACKGROUND As the process of producing official health statistics for Lifestyle Diseases is slow, researchers have explored using Web search data as a proxy for Lifestyle Disease surveillance. Existing studies, however, are prone to at least one of the following issues: ad-hoc keyword selection, overfitting, insufficient predictive evaluation, lack of generalization, and failure to compare against trivial baselines. OBJECTIVE The aims of this study were to (1) employ a corrective approach improving previous methods; (2) study the key limitations in using Google Trends for Lifestyle Disease surveillance; and (3) test the generalizability of our methodology to other countries beyond the United States. METHODS For each of the target variables (diabetes, obesity, and exercise), prevalence rates were collected. After a rigorous keyword selection process, data from Google Trends were collected. These data were denormalized to form spatio-temporal indices. L1-regularized regression models were trained to predict prevalence rates from denormalized Google Trends indices. Models were tested on a held-out set and compared against baselines from the literature as well as a trivial last year equals this year baseline. A similar analysis was done using a multivariate spatio-temporal model where the previous year’s prevalence was included as a covariate. This model was modified to create a time-lagged regression analysis framework. Finally, a hierarchical time-lagged multivariate spatio-temporal model was created to account for subnational trends in the data. The model trained on US data was, then, applied in a transfer learning framework to Canada. RESULTS In the US context, our proposed models beat the performances of the prior work, as well as the trivial baselines. In terms of the mean absolute error (MAE), the best of our proposed models yields 24% improvement (0.72-0.55; <i>P</i><.001) for diabetes; 18% improvement (1.20-0.99; <i>P</i>=.001) for obesity, and 34% improvement (2.89-1.95; <i>P</i><.001) for exercise. Our proposed across-country transfer learning framework also shows promising results with an average Spearman and Pearson correlation of 0.70 for diabetes and 0.90 and 0.91 for obesity, respectively. CONCLUSIONS Although our proposed models beat the baselines, we find the modeling of Lifestyle Diseases to be a challenging problem, one that requires an abundance of data as well as creative modeling strategies. In doing so, this study shows a low-to-moderate validity of Google Trends in the context of Lifestyle Disease surveillance, even when applying novel corrective approaches, including a proposed denormalization scheme. We envision qualitative analyses to be a more practical use of Google Trends in the context of Lifestyle Disease surveillance. For the quantitative analyses, the highest utility of using Google Trends is in the context of transfer learning where low-resource countries could benefit from high-resource countries by using proxy models.
-
using facebook ads audiences for global Lifestyle Disease surveillance promises and limitations
arXiv: Computers and Society, 2017Co-Authors: Matheus Araujo, Ingmar Weber, Yelena Mejova, Fabricio BenevenutoAbstract:Every day, millions of users reveal their interests on Facebook, which are then monetized via targeted advertisement marketing campaigns. In this paper, we explore the use of demographically rich Facebook Ads audience estimates for tracking non-communicable Diseases around the world. Across 47 countries, we compute the audiences of marker interests, and evaluate their potential in tracking health conditions associated with tobacco use, obesity, and diabetes, compared to the performance of placebo interests. Despite its huge potential, we find that, for modeling prevalence of health conditions across countries, differences in these interest audiences are only weakly indicative of the corresponding prevalence rates. Within the countries, however, our approach provides interesting insights on trends of health awareness across demographic groups. Finally, we provide a temporal error analysis to expose the potential pitfalls of using Facebook's Marketing API as a black box.
Shahan Ali Memon - One of the best experts on this subject based on the ideXlab platform.
-
Lifestyle Disease Surveillance Using Population Search Behavior: Feasibility Study.
Journal of medical Internet research, 2020Co-Authors: Shahan Ali Memon, Saquib Razak, Ingmar WeberAbstract:Background: As the process of producing official health statistics for Lifestyle Diseases is slow, researchers have explored using Web search data as a proxy for Lifestyle Disease surveillance. Existing studies, however, are prone to at least one of the following issues: ad-hoc keyword selection, overfitting, insufficient predictive evaluation, lack of generalization, and failure to compare against trivial baselines.Objective: The aims of this study were to (1) employ a corrective approach improving previous methods; (2) study the key limitations in using Google Trends for Lifestyle Disease surveillance; and (3) test the generalizability of our methodology to other countries beyond the United States.Methods: For each of the target variables (diabetes, obesity, and exercise), prevalence rates were collected. After a rigorous keyword selection process, data from Google Trends were collected. These data were denormalized to form spatio-temporal indices. L1-regularized regression models were trained to predict prevalence rates from denormalized Google Trends indices. Models were tested on a held-out set and compared against baselines from the literature as well as a trivial last year equals this year baseline. A similar analysis was done using a multivariate spatio-temporal model where the previous year’s prevalence was included as a covariate. This model was modified to create a time-lagged regression analysis framework. Finally, a hierarchical time-lagged multivariate spatio-temporal model was created to account for subnational trends in the data. The model trained on US data was, then, applied in a transfer learning framework to Canada.Results: In the US context, our proposed models beat the performances of the prior work, as well as the trivial baselines. In terms of the mean absolute error (MAE), the best of our proposed models yields 24% improvement (0.72-0.55; P
-
Lifestyle Disease Surveillance Using Population Search Behavior: Feasibility Study (Preprint)
2019Co-Authors: Shahan Ali Memon, Saquib Razak, Ingmar WeberAbstract:BACKGROUND As the process of producing official health statistics for Lifestyle Diseases is slow, researchers have explored using Web search data as a proxy for Lifestyle Disease surveillance. Existing studies, however, are prone to at least one of the following issues: ad-hoc keyword selection, overfitting, insufficient predictive evaluation, lack of generalization, and failure to compare against trivial baselines. OBJECTIVE The aims of this study were to (1) employ a corrective approach improving previous methods; (2) study the key limitations in using Google Trends for Lifestyle Disease surveillance; and (3) test the generalizability of our methodology to other countries beyond the United States. METHODS For each of the target variables (diabetes, obesity, and exercise), prevalence rates were collected. After a rigorous keyword selection process, data from Google Trends were collected. These data were denormalized to form spatio-temporal indices. L1-regularized regression models were trained to predict prevalence rates from denormalized Google Trends indices. Models were tested on a held-out set and compared against baselines from the literature as well as a trivial last year equals this year baseline. A similar analysis was done using a multivariate spatio-temporal model where the previous year’s prevalence was included as a covariate. This model was modified to create a time-lagged regression analysis framework. Finally, a hierarchical time-lagged multivariate spatio-temporal model was created to account for subnational trends in the data. The model trained on US data was, then, applied in a transfer learning framework to Canada. RESULTS In the US context, our proposed models beat the performances of the prior work, as well as the trivial baselines. In terms of the mean absolute error (MAE), the best of our proposed models yields 24% improvement (0.72-0.55; <i>P</i><.001) for diabetes; 18% improvement (1.20-0.99; <i>P</i>=.001) for obesity, and 34% improvement (2.89-1.95; <i>P</i><.001) for exercise. Our proposed across-country transfer learning framework also shows promising results with an average Spearman and Pearson correlation of 0.70 for diabetes and 0.90 and 0.91 for obesity, respectively. CONCLUSIONS Although our proposed models beat the baselines, we find the modeling of Lifestyle Diseases to be a challenging problem, one that requires an abundance of data as well as creative modeling strategies. In doing so, this study shows a low-to-moderate validity of Google Trends in the context of Lifestyle Disease surveillance, even when applying novel corrective approaches, including a proposed denormalization scheme. We envision qualitative analyses to be a more practical use of Google Trends in the context of Lifestyle Disease surveillance. For the quantitative analyses, the highest utility of using Google Trends is in the context of transfer learning where low-resource countries could benefit from high-resource countries by using proxy models.
Saquib Razak - One of the best experts on this subject based on the ideXlab platform.
-
Lifestyle Disease Surveillance Using Population Search Behavior: Feasibility Study.
Journal of medical Internet research, 2020Co-Authors: Shahan Ali Memon, Saquib Razak, Ingmar WeberAbstract:Background: As the process of producing official health statistics for Lifestyle Diseases is slow, researchers have explored using Web search data as a proxy for Lifestyle Disease surveillance. Existing studies, however, are prone to at least one of the following issues: ad-hoc keyword selection, overfitting, insufficient predictive evaluation, lack of generalization, and failure to compare against trivial baselines.Objective: The aims of this study were to (1) employ a corrective approach improving previous methods; (2) study the key limitations in using Google Trends for Lifestyle Disease surveillance; and (3) test the generalizability of our methodology to other countries beyond the United States.Methods: For each of the target variables (diabetes, obesity, and exercise), prevalence rates were collected. After a rigorous keyword selection process, data from Google Trends were collected. These data were denormalized to form spatio-temporal indices. L1-regularized regression models were trained to predict prevalence rates from denormalized Google Trends indices. Models were tested on a held-out set and compared against baselines from the literature as well as a trivial last year equals this year baseline. A similar analysis was done using a multivariate spatio-temporal model where the previous year’s prevalence was included as a covariate. This model was modified to create a time-lagged regression analysis framework. Finally, a hierarchical time-lagged multivariate spatio-temporal model was created to account for subnational trends in the data. The model trained on US data was, then, applied in a transfer learning framework to Canada.Results: In the US context, our proposed models beat the performances of the prior work, as well as the trivial baselines. In terms of the mean absolute error (MAE), the best of our proposed models yields 24% improvement (0.72-0.55; P
-
Lifestyle Disease Surveillance Using Population Search Behavior: Feasibility Study (Preprint)
2019Co-Authors: Shahan Ali Memon, Saquib Razak, Ingmar WeberAbstract:BACKGROUND As the process of producing official health statistics for Lifestyle Diseases is slow, researchers have explored using Web search data as a proxy for Lifestyle Disease surveillance. Existing studies, however, are prone to at least one of the following issues: ad-hoc keyword selection, overfitting, insufficient predictive evaluation, lack of generalization, and failure to compare against trivial baselines. OBJECTIVE The aims of this study were to (1) employ a corrective approach improving previous methods; (2) study the key limitations in using Google Trends for Lifestyle Disease surveillance; and (3) test the generalizability of our methodology to other countries beyond the United States. METHODS For each of the target variables (diabetes, obesity, and exercise), prevalence rates were collected. After a rigorous keyword selection process, data from Google Trends were collected. These data were denormalized to form spatio-temporal indices. L1-regularized regression models were trained to predict prevalence rates from denormalized Google Trends indices. Models were tested on a held-out set and compared against baselines from the literature as well as a trivial last year equals this year baseline. A similar analysis was done using a multivariate spatio-temporal model where the previous year’s prevalence was included as a covariate. This model was modified to create a time-lagged regression analysis framework. Finally, a hierarchical time-lagged multivariate spatio-temporal model was created to account for subnational trends in the data. The model trained on US data was, then, applied in a transfer learning framework to Canada. RESULTS In the US context, our proposed models beat the performances of the prior work, as well as the trivial baselines. In terms of the mean absolute error (MAE), the best of our proposed models yields 24% improvement (0.72-0.55; <i>P</i><.001) for diabetes; 18% improvement (1.20-0.99; <i>P</i>=.001) for obesity, and 34% improvement (2.89-1.95; <i>P</i><.001) for exercise. Our proposed across-country transfer learning framework also shows promising results with an average Spearman and Pearson correlation of 0.70 for diabetes and 0.90 and 0.91 for obesity, respectively. CONCLUSIONS Although our proposed models beat the baselines, we find the modeling of Lifestyle Diseases to be a challenging problem, one that requires an abundance of data as well as creative modeling strategies. In doing so, this study shows a low-to-moderate validity of Google Trends in the context of Lifestyle Disease surveillance, even when applying novel corrective approaches, including a proposed denormalization scheme. We envision qualitative analyses to be a more practical use of Google Trends in the context of Lifestyle Disease surveillance. For the quantitative analyses, the highest utility of using Google Trends is in the context of transfer learning where low-resource countries could benefit from high-resource countries by using proxy models.
Takeshi Sato - One of the best experts on this subject based on the ideXlab platform.
-
Studies on the psychosomatic functioning of ill-health according to eastern and Western medicine. 3. Two treatment methods using kampo medication for stress-related and Lifestyle Disease.
The American journal of Chinese medicine, 1999Co-Authors: Masashi Takeichi, Takeshi SatoAbstract:In this study, we examine the modality of improvement in psychosomatic function to verify the suitability of two treatment methods previously described. The subjects were nine medical students with no history of blood stasis-related illness (average age, 24.8; SD, 1.4 years) and 21 patients of our outpatient clinic (average age, 54.3; SD, 10.4 years). For purposes of our research, Kampo medication was selected based on the diagnosis and treatment of unbalanced qi, blood, and body fluid developed by the authors in their previous report. As a result, the therapeutic features of the preventive treatment group of nine medical students and the final treatment group of 21 patients of the outpatient clinic were essentially identical. There were two such features: 1. At the psychological level, this consisted of an improvement in stress- related emotional reaction, centered on anxiety and depression, and at the physiological level, this consisted of an improvement in peripheral blood circulation (an increase of the fractal dimension of the plethysmogram, p = 0.0357). 2. The improvement of the foregoing psychosomatic function is related to the improvement of blood stasis (strictly speaking, vital energy stagnation and blood stasis) in Oriental medicine, and the improvement of blood rheological abnormalities in Western medicine. Therefore, this research confirmed the significance of two treatment methods proposed by the authors for stress-related illness and Lifestyle Disease in individuals with an anxiety-affinitive constitution.
Jean Woo - One of the best experts on this subject based on the ideXlab platform.
-
Relationships among diet, physical activity and other Lifestyle factors and debilitating Diseases in the elderly.
European Journal of Clinical Nutrition, 2000Co-Authors: Jean WooAbstract:Diet and physical activity are two major Lifestyle factors that play a role in the prevention or management of debilitating conditions affecting older people. Both under- and overnutrition predispose to Diseases. Low sodium and high potassium intakes, as well as the consumption of fruits and vegetables are associated with a reduction of hypertension and Diseases arising from hypertension such as stroke and dementia. Dietary patterns (consumption of quantity and types of fats, cholesterol, vegetable oils, fish) are important in the prevention of coronary heart Disease. Calcium and vitamin D intakes are important factors in the development of osteoporosis, while various dietary factors have been linked to the development of cancer. Physical activity is important in the prevention of functional decline and increased survival, reduced incidence of falls and fractures, and has various cardiovascular health benefits. Apart from prevention of Diseases, exercise also has an important role in improving function in some chronic Diseases such as heart failure or chronic obstructive pulmonary Disease. Both diet and exercise interact, so that public health recommendations often take the form of Lifestyle modification advice in the prevention of Disease and disability. Descriptors: aging; dietary intake; physical activity; Lifestyle; Disease European Journal of Clinical Nutrition (2000) 54, Suppl 3, S143‐S147