Preterm births occur at an alarming rate of 10-15%. Preemies have a higher risk of infant mortali... more Preterm births occur at an alarming rate of 10-15%. Preemies have a higher risk of infant mortality, developmental retardation and long-term disabilities. Predicting preterm birth is difficult, even for the most experienced clinicians. The most well-designed clinical study thus far reaches a modest sensitivity of 18.2-24.2% at specificity of 28.6-33.3%. We take a different approach by exploiting databases of normal hospital operations. We aims are twofold: (i) to derive an easy-to-use, interpretable prediction rule with quantified uncertainties, and (ii) to construct accurate classifiers for preterm birth prediction. Our approach is to automatically generate and select from hundreds (if not thousands) of possible predictors using stability-aware techniques. Derived from a large database of 15,814 women, our simplified prediction rule with only 10 items has sensitivity of 62.3% at specificity of 81.5%.
Facial Expression Recognition (FER) can be widely applied to various research areas, such as ment... more Facial Expression Recognition (FER) can be widely applied to various research areas, such as mental diseases diagnosis and human social/physiological interaction detection. With the emerging advanced technologies in hardware and sensors, FER systems have been developed to support real-world application scenes, instead of laboratory environments. Although the laboratory-controlled FER systems achieve very high accuracy, around 97%, the technical transferring from the laboratory to real-world applications faces a great barrier of very low accuracy, approximately 50%. In this survey, we comprehensively discuss three significant challenges in the unconstrained real-world environments, such as illumination variation, head pose, and subject-dependence, which may not be resolved by only analysing images/videos in the FER system. We focus on those sensors that may provide extra information and help the FER systems to detect emotion in both static images and video sequences. We introduce thr...
Preterm birth is a clinical event significant but difficult to predict. Biomarkers such as fetal ... more Preterm birth is a clinical event significant but difficult to predict. Biomarkers such as fetal fibronectin and cervical length are effective, but the often are used only for women with clinically suspected preterm risk. It is unknown whether routinely collected data can be used in early pregnancy to stratify preterm birth risk by identifying asymptomatic women. This paper tries to determine the value of the Victorian Perinatal Data Collection (VPDC) dataset in predicting preterm birth and screening for invasive tests. De-identified VPDC report data from 2009 to 2013 were extracted for patients from Barwon Health in Victoria. Logistic regression models with elastic-net regularization were fitted to predict 37-week preterm, with the VPDC antenatal variables as predictors. The models were also extended with two additional variables not routinely noted in the VPDC: previous preterm birth and partner smoking status, testing the hypothesis that these two factors add prediction accuracy....
The Health of the Nation Outcome Scales (HoNOS) are mandated outcome-measures in many mental-heal... more The Health of the Nation Outcome Scales (HoNOS) are mandated outcome-measures in many mental-health jurisdictions. When HoNOS are used in different care settings, it is important to assess if setting specific bias exists. This article examines the consistency of HoNOS in a sample of psychiatric patients transitioned from acute inpatient care and community centres. A regional mental health service with both acute and community facilities. 111 psychiatric patients were transferred from inpatient care to community care from 2012 to 2014. Their HoNOS scores were extracted from a clinical database; Each inpatient-discharge assessment was followed by a community-intake assessment, with the median period between assessments being 4 days (range 0-14). Assessor experience and professional background were recorded. The difference of HoNOS at inpatient-discharge and community-intake were assessed with Pearson correlation, Cohen's κ and effect size. Inpatient-discharge HoNOS was on average ...
For years, opinion polls rely on data collected through telephone or person-to-person surveys. Th... more For years, opinion polls rely on data collected through telephone or person-to-person surveys. The process is costly, inconvenient, and slow. Recently online search data has emerged as potential proxies for the survey data. However considerable human involvement is still needed for the selection of search indices, a task that requires knowledge of both the target issue and how search terms are used by the online community. The robustness of such manually selected search indices can be questionable. In this paper, we propose an automatic polling system through a novel application of machine learning. In this system, the needs for examining, comparing, and selecting search indices have been eliminated through automatic generation of candidate search indices and intelligent combination of the indices. The results include a publicly accessible web application that provides real-time, robust, and accurate measurements of public opinions on several subjects of general interest.
Journal of medical Internet research, Dec 16, 2016
As more and more researchers are turning to big data for new opportunities of biomedical discover... more As more and more researchers are turning to big data for new opportunities of biomedical discoveries, machine learning models, as the backbone of big data analysis, are mentioned more often in biomedical journals. However, owing to the inherent complexity of machine learning methods, they are prone to misuse. Because of the flexibility in specifying machine learning models, the results are often insufficiently reported in research articles, hindering reliable assessment of model validity and consistent interpretation of model outputs. To attain a set of guidelines on the use of machine learning predictive models within clinical settings to make sure the models are correctly applied and sufficiently reported so that true discoveries can be distinguished from random coincidence. A multidisciplinary panel of machine learning experts, clinicians, and traditional statisticians were interviewed, using an iterative process in accordance with the Delphi method. The process produced a set of...
Using the prediction of cancer outcome as a model, we have tested the hypothesis that through ana... more Using the prediction of cancer outcome as a model, we have tested the hypothesis that through analysing routinely collected digital data contained in an electronic administrative record (EAR), using machine-learning techniques, we could enhance conventional methods in predicting clinical outcomes. A regional cancer centre in Australia. Disease-specific data from a purpose-built cancer registry (Evaluation of Cancer Outcomes (ECO)) from 869 patients were used to predict survival at 6, 12 and 24 months. The model was validated with data from a further 94 patients, and results compared to the assessment of five specialist oncologists. Machine-learning prediction using ECO data was compared with that using EAR and a model combining ECO and EAR data. Survival prediction accuracy in terms of the area under the receiver operating characteristic curve (AUC). The ECO model yielded AUCs of 0.87 (95% CI 0.848 to 0.890) at 6 months, 0.796 (95% CI 0.774 to 0.823) at 12 months and 0.764 (95% CI 0...
BackgroundFeature engineering is a time consuming component of predictive modelling. We propose a... more BackgroundFeature engineering is a time consuming component of predictive modelling. We propose a versatile platform to automatically extract features for risk prediction, based on a pre-defined and extensible entity schema. The extraction is independent of disease type or risk prediction task. We contrast auto-extracted features to baselines generated from the Elixhauser comorbidities.ResultsHospital medical records was transformed to event sequences, to which filters were applied to extract feature sets capturing diversity in temporal scales and data types. The features were evaluated on a readmission prediction task, comparing with baseline feature sets generated from the Elixhauser comorbidities. The prediction model was through logistic regression with elastic net regularization. Predictions horizons of 1, 2, 3, 6, 12Â months were considered for four diverse diseases: diabetes, COPD, mental disorders and pneumonia, with derivation and validation cohorts defined on non-overlappin...
Journal of epidemiology and community health, Jan 24, 2015
The WHO framework for non-communicable disease (NCD) describes risks and outcomes comprising the ... more The WHO framework for non-communicable disease (NCD) describes risks and outcomes comprising the majority of the global burden of disease. These factors are complex and interact at biological, behavioural, environmental and policy levels presenting challenges for population monitoring and intervention evaluation. This paper explores the utility of machine learning methods applied to population-level web search activity behaviour as a proxy for chronic disease risk factors. Web activity output for each element of the WHO's Causes of NCD framework was used as a basis for identifying relevant web search activity from 2004 to 2013 for the USA. Multiple linear regression models with regularisation were used to generate predictive algorithms, mapping web search activity to Centers for Disease Control and Prevention (CDC) measured risk factor/disease prevalence. Predictions for subsequent target years not included in the model derivation were tested against CDC data from population sur...
Using the prediction of cancer outcome as a model, we have tested the hypothesis that through ana... more Using the prediction of cancer outcome as a model, we have tested the hypothesis that through analysing routinely collected digital data contained in an electronic administrative record (EAR), using machine-learning techniques, we could enhance conventional methods in predicting clinical outcomes. A regional cancer centre in Australia. Disease-specific data from a purpose-built cancer registry (Evaluation of Cancer Outcomes (ECO)) from 869 patients were used to predict survival at 6, 12 and 24 months. The model was validated with data from a further 94 patients, and results compared to the assessment of five specialist oncologists. Machine-learning prediction using ECO data was compared with that using EAR and a model combining ECO and EAR data. Survival prediction accuracy in terms of the area under the receiver operating characteristic curve (AUC). The ECO model yielded AUCs of 0.87 (95% CI 0.848 to 0.890) at 6 months, 0.796 (95% CI 0.774 to 0.823) at 12 months and 0.764 (95% CI 0...
Preterm births occur at an alarming rate of 10-15%. Preemies have a higher risk of infant mortali... more Preterm births occur at an alarming rate of 10-15%. Preemies have a higher risk of infant mortality, developmental retardation and long-term disabilities. Predicting preterm birth is difficult, even for the most experienced clinicians. The most well-designed clinical study thus far reaches a modest sensitivity of 18.2-24.2% at specificity of 28.6-33.3%. We take a different approach by exploiting databases of normal hospital operations. We aims are twofold: (i) to derive an easy-to-use, interpretable prediction rule with quantified uncertainties, and (ii) to construct accurate classifiers for preterm birth prediction. Our approach is to automatically generate and select from hundreds (if not thousands) of possible predictors using stability-aware techniques. Derived from a large database of 15,814 women, our simplified prediction rule with only 10 items has sensitivity of 62.3% at specificity of 81.5%.
Facial Expression Recognition (FER) can be widely applied to various research areas, such as ment... more Facial Expression Recognition (FER) can be widely applied to various research areas, such as mental diseases diagnosis and human social/physiological interaction detection. With the emerging advanced technologies in hardware and sensors, FER systems have been developed to support real-world application scenes, instead of laboratory environments. Although the laboratory-controlled FER systems achieve very high accuracy, around 97%, the technical transferring from the laboratory to real-world applications faces a great barrier of very low accuracy, approximately 50%. In this survey, we comprehensively discuss three significant challenges in the unconstrained real-world environments, such as illumination variation, head pose, and subject-dependence, which may not be resolved by only analysing images/videos in the FER system. We focus on those sensors that may provide extra information and help the FER systems to detect emotion in both static images and video sequences. We introduce thr...
Preterm birth is a clinical event significant but difficult to predict. Biomarkers such as fetal ... more Preterm birth is a clinical event significant but difficult to predict. Biomarkers such as fetal fibronectin and cervical length are effective, but the often are used only for women with clinically suspected preterm risk. It is unknown whether routinely collected data can be used in early pregnancy to stratify preterm birth risk by identifying asymptomatic women. This paper tries to determine the value of the Victorian Perinatal Data Collection (VPDC) dataset in predicting preterm birth and screening for invasive tests. De-identified VPDC report data from 2009 to 2013 were extracted for patients from Barwon Health in Victoria. Logistic regression models with elastic-net regularization were fitted to predict 37-week preterm, with the VPDC antenatal variables as predictors. The models were also extended with two additional variables not routinely noted in the VPDC: previous preterm birth and partner smoking status, testing the hypothesis that these two factors add prediction accuracy....
The Health of the Nation Outcome Scales (HoNOS) are mandated outcome-measures in many mental-heal... more The Health of the Nation Outcome Scales (HoNOS) are mandated outcome-measures in many mental-health jurisdictions. When HoNOS are used in different care settings, it is important to assess if setting specific bias exists. This article examines the consistency of HoNOS in a sample of psychiatric patients transitioned from acute inpatient care and community centres. A regional mental health service with both acute and community facilities. 111 psychiatric patients were transferred from inpatient care to community care from 2012 to 2014. Their HoNOS scores were extracted from a clinical database; Each inpatient-discharge assessment was followed by a community-intake assessment, with the median period between assessments being 4 days (range 0-14). Assessor experience and professional background were recorded. The difference of HoNOS at inpatient-discharge and community-intake were assessed with Pearson correlation, Cohen's κ and effect size. Inpatient-discharge HoNOS was on average ...
For years, opinion polls rely on data collected through telephone or person-to-person surveys. Th... more For years, opinion polls rely on data collected through telephone or person-to-person surveys. The process is costly, inconvenient, and slow. Recently online search data has emerged as potential proxies for the survey data. However considerable human involvement is still needed for the selection of search indices, a task that requires knowledge of both the target issue and how search terms are used by the online community. The robustness of such manually selected search indices can be questionable. In this paper, we propose an automatic polling system through a novel application of machine learning. In this system, the needs for examining, comparing, and selecting search indices have been eliminated through automatic generation of candidate search indices and intelligent combination of the indices. The results include a publicly accessible web application that provides real-time, robust, and accurate measurements of public opinions on several subjects of general interest.
Journal of medical Internet research, Dec 16, 2016
As more and more researchers are turning to big data for new opportunities of biomedical discover... more As more and more researchers are turning to big data for new opportunities of biomedical discoveries, machine learning models, as the backbone of big data analysis, are mentioned more often in biomedical journals. However, owing to the inherent complexity of machine learning methods, they are prone to misuse. Because of the flexibility in specifying machine learning models, the results are often insufficiently reported in research articles, hindering reliable assessment of model validity and consistent interpretation of model outputs. To attain a set of guidelines on the use of machine learning predictive models within clinical settings to make sure the models are correctly applied and sufficiently reported so that true discoveries can be distinguished from random coincidence. A multidisciplinary panel of machine learning experts, clinicians, and traditional statisticians were interviewed, using an iterative process in accordance with the Delphi method. The process produced a set of...
Using the prediction of cancer outcome as a model, we have tested the hypothesis that through ana... more Using the prediction of cancer outcome as a model, we have tested the hypothesis that through analysing routinely collected digital data contained in an electronic administrative record (EAR), using machine-learning techniques, we could enhance conventional methods in predicting clinical outcomes. A regional cancer centre in Australia. Disease-specific data from a purpose-built cancer registry (Evaluation of Cancer Outcomes (ECO)) from 869 patients were used to predict survival at 6, 12 and 24 months. The model was validated with data from a further 94 patients, and results compared to the assessment of five specialist oncologists. Machine-learning prediction using ECO data was compared with that using EAR and a model combining ECO and EAR data. Survival prediction accuracy in terms of the area under the receiver operating characteristic curve (AUC). The ECO model yielded AUCs of 0.87 (95% CI 0.848 to 0.890) at 6 months, 0.796 (95% CI 0.774 to 0.823) at 12 months and 0.764 (95% CI 0...
BackgroundFeature engineering is a time consuming component of predictive modelling. We propose a... more BackgroundFeature engineering is a time consuming component of predictive modelling. We propose a versatile platform to automatically extract features for risk prediction, based on a pre-defined and extensible entity schema. The extraction is independent of disease type or risk prediction task. We contrast auto-extracted features to baselines generated from the Elixhauser comorbidities.ResultsHospital medical records was transformed to event sequences, to which filters were applied to extract feature sets capturing diversity in temporal scales and data types. The features were evaluated on a readmission prediction task, comparing with baseline feature sets generated from the Elixhauser comorbidities. The prediction model was through logistic regression with elastic net regularization. Predictions horizons of 1, 2, 3, 6, 12Â months were considered for four diverse diseases: diabetes, COPD, mental disorders and pneumonia, with derivation and validation cohorts defined on non-overlappin...
Journal of epidemiology and community health, Jan 24, 2015
The WHO framework for non-communicable disease (NCD) describes risks and outcomes comprising the ... more The WHO framework for non-communicable disease (NCD) describes risks and outcomes comprising the majority of the global burden of disease. These factors are complex and interact at biological, behavioural, environmental and policy levels presenting challenges for population monitoring and intervention evaluation. This paper explores the utility of machine learning methods applied to population-level web search activity behaviour as a proxy for chronic disease risk factors. Web activity output for each element of the WHO's Causes of NCD framework was used as a basis for identifying relevant web search activity from 2004 to 2013 for the USA. Multiple linear regression models with regularisation were used to generate predictive algorithms, mapping web search activity to Centers for Disease Control and Prevention (CDC) measured risk factor/disease prevalence. Predictions for subsequent target years not included in the model derivation were tested against CDC data from population sur...
Using the prediction of cancer outcome as a model, we have tested the hypothesis that through ana... more Using the prediction of cancer outcome as a model, we have tested the hypothesis that through analysing routinely collected digital data contained in an electronic administrative record (EAR), using machine-learning techniques, we could enhance conventional methods in predicting clinical outcomes. A regional cancer centre in Australia. Disease-specific data from a purpose-built cancer registry (Evaluation of Cancer Outcomes (ECO)) from 869 patients were used to predict survival at 6, 12 and 24 months. The model was validated with data from a further 94 patients, and results compared to the assessment of five specialist oncologists. Machine-learning prediction using ECO data was compared with that using EAR and a model combining ECO and EAR data. Survival prediction accuracy in terms of the area under the receiver operating characteristic curve (AUC). The ECO model yielded AUCs of 0.87 (95% CI 0.848 to 0.890) at 6 months, 0.796 (95% CI 0.774 to 0.823) at 12 months and 0.764 (95% CI 0...
Uploads