ABSTRACT
At the beginning of the COVID-19 pandemic, there was significant hype about the potential impact of artificial intelligence (AI) tools in combatting COVID-19 on diagnosis, prognosis, or surveillance. However, AI tools have not yet been widely successful. One of the key reason is the COVID-19 pandemic has demanded faster real-time development of AI-driven clinical and health support tools, including rapid data collection, algorithm development, validation, and deployment. However, there was not enough time for proper data quality control. Learning from the hard lessons in COVID-19, we summarize the important health data quality challenges during COVID-19 pandemic such as lack of data standardization, missing data, tabulation errors, and noise and artifact. Then we conduct a systematic investigation of computational methods that address these issues, including emerging novel advanced AI data quality control methods that achieve better data quality outcomes and, in some cases, simplify or automate the data cleaning process. We hope this article can assist healthcare community to improve health data quality going forward with novel AI development.
Subject(s)
Artificial Intelligence , COVID-19 , Humans , Data Accuracy , Pandemics , AlgorithmsABSTRACT
More than 5 million patients have admitted annually to intensive care units (ICUs) in the United States. The leading causes of mortality are cardiovascular failures, multi-organ failures, and sepsis. Data-driven techniques have been used in the analysis of patient data to predict adverse events, such as ICU mortality and ICU readmission. These models often make use of temporal or static features from a single ICU database to make predictions on subsequent adverse events. To explore the potential of domain adaptation, we propose a method of data analysis using gradient boosting and convolutional autoencoder (CAE) to predict significant adverse events in the ICU, such as ICU mortality and ICU readmission. We demonstrate our results from a retrospective data analysis using patient records from a publicly available database called Multi-parameter Intelligent Monitoring in Intensive Care-II (MIMIC-II) and a local database from Children's Healthcare of Atlanta (CHOA). We demonstrate that after adopting novel data imputation on patient ICU data, gradient boosting is effective in both the mortality prediction task and the ICU readmission prediction task. In addition, we use gradient boosting to identify top-ranking temporal and non-temporal features in both prediction tasks. We discuss the relationship between these features and the specific prediction task. Lastly, we indicate that CAE might not be effective in feature extraction on one dataset, but domain adaptation with CAE feature extraction across two datasets shows promising results.
ABSTRACT
Most current Alzheimer's disease (AD) and mild cognitive disorders (MCI) studies use single data modality to make predictions such as AD stages. The fusion of multiple data modalities can provide a holistic view of AD staging analysis. Thus, we use deep learning (DL) to integrally analyze imaging (magnetic resonance imaging (MRI)), genetic (single nucleotide polymorphisms (SNPs)), and clinical test data to classify patients into AD, MCI, and controls (CN). We use stacked denoising auto-encoders to extract features from clinical and genetic data, and use 3D-convolutional neural networks (CNNs) for imaging data. We also develop a novel data interpretation method to identify top-performing features learned by the deep-models with clustering and perturbation analysis. Using Alzheimer's disease neuroimaging initiative (ADNI) dataset, we demonstrate that deep models outperform shallow models, including support vector machines, decision trees, random forests, and k-nearest neighbors. In addition, we demonstrate that integrating multi-modality data outperforms single modality models in terms of accuracy, precision, recall, and meanF1 scores. Our models have identified hippocampus, amygdala brain areas, and the Rey Auditory Verbal Learning Test (RAVLT) as top distinguished features, which are consistent with the known AD literature.
Subject(s)
Alzheimer Disease/diagnosis , Data Mining , Deep Learning , Diagnosis, Computer-Assisted , Early Diagnosis , HumansABSTRACT
Patient and health provider interaction via text messaging (TM) has become an accepted form of communication, often favored by adolescents and young adults. While integration of TM in disease management has aided health interventions and behavior modifications, broader adoption is hindered by expense, fixed reporting schedules, and monotonic communication. A low-cost, flexible TM reporting system (REMOTES) was developed using inexpensive cloud-based services with features of two-way communication, personalized reporting scheduling, and scalable and secured data storage. REMOTES is a template-based reporting tool adaptable to a wide-range of complexity in response formats. In a pilot study, 27 adolescents with sickle cell disease participated to assess feasibility of REMOTES in both inpatient and outpatient settings. Subject compliance with at least one daily self-report pain query was 94.9% (112/118) during inpatient and 91.1% (327/359) during outpatient, with an overall accuracy of 99.2% (970/978). With use of a more complex 8-item questionnaire, 30% (7/21) inpatient and 66.6% (36/54) outpatient responses were reported with 98.1% (51/52) reporting accuracy. All participants expressed high pre-trial expectation (88%) and post-trial satisfaction (89%). The study suggests that cloud-based text messaging is feasible and an easy-of-use solution for low-cost and personalized patient engagement.
ABSTRACT
The diversity and number of parameters monitored in an intensive care unit (ICU) make the resulting databases highly susceptible to quality issues, such as missing information and erroneous data entry, which adversely affect the downstream processing and predictive modeling. Missing data interpolation and imputation techniques, such as multiple imputation, expectation maximization, and hot-deck imputation techniques do not account for the type of missing data, which can lead to bias. In our study, we first model the missing data as three types: "neglectable" also known as a.k.a "missing completely at random," "recoverable" a.k.a. "missing at random," and "not easily recoverable" a.k.a. "missing not at random." We then design imputation techniques for each type of missing data. We use a publicly available database (MIMIC II) to demonstrate how these imputations perform with random forests for prediction. Our results indicate that these novel imputation techniques outperformed standard mean filling techniques and expectation maximization with a statistical significance p ≤ 0.01 in predicting ICU mortality.
Subject(s)
Data Collection/standards , Electronic Health Records/standards , Intensive Care Units , Models, Statistical , Humans , Medical Informatics , Quality ControlABSTRACT
One pressing need in the area of public health is timely, accurate, and complete reporting of deaths and the diseases or conditions leading up to them. Fast Healthcare Interoperability Resources (FHIR) is a new HL7 interoperability standard for electronic health record, while Sustainable Medical Applications and Reusable Technologies (SMART)-on-FHIR enables third-party app development that can work "out of the box." This paper demonstrates the feasibility of developing SMART-on-FHIR applications that enables medical professionals to perform timely and accurate death reporting within multiple different USA State jurisdictions. We explored how the information on a standard certificate of death can be mapped to resources defined in the FHIR standard Draft Standard for Trial Use Version 2 and common profiles. We also demonstrated analytics for potentially improving the accuracy and completeness of mortality reporting data.
Subject(s)
Health Information Interoperability , Mortality , Public Health/methods , HumansABSTRACT
Accurate reporting of causes of death on death certificates is essential to formulate appropriate disease control, prevention and emergency response by national health-protection institutions such as Center for disease prevention and control (CDC). In this study, we utilize knowledge from publicly available expert-formulated rules for the cause of death to determine the extent of discordance in the death certificates in national mortality data with the expert knowledge base. We also report the most commonly occurring invalid causal pairs which physicians put in the death certificates. We use sequence rule mining to find patterns that are most frequent on death certificates and compare them with the rules from the expert knowledge based. Based on our results, 20.1% of the common patterns derived from entries into death certificates were discordant. The most probable causes of these discordance or invalid rules are missing steps and non-specific ICD-10 codes on the death certificates.
ABSTRACT
There are approximately 4 million intensive care unit (ICU) admissions each year in the United States with costs accounting for 4.1% of national health expenditures. Unforeseen adverse events contribute disproportionately to these costs. Thus, there has been substantial research in developing clinical decision support systems to predict and improve ICU outcomes such as ICU mortality, prolonged length of stay, and ICU readmission. However, the data in the ICU is collected at diverse time intervals and includes both static and temporal data. Common methods for static data mining such as Cox and logistic regression and methods for temporal data analysis such as temporal association rule mining do not model the combination of both static and temporal data. This work aims to overcome this challenge to combine static models such as logistic regression and feedforward neural networks with temporal models such as conditional random fields(CRF). We demonstrate the results using adult patient records from a publicly available database called Multi-parameter Intelligent Monitoring in Intensive Care - II (MIMIC-II). We show that the combination models outperformed individual models of logistic regression, feed-forward neural networks and conditional random fields in predicting ICU mortality. The combination models also outperform the static models of logistic regression and feed-forward neural networks for the prediction of 30 day ICU readmissions when tested using Matthews correlation coefficient and accuracy as the metrics.
Subject(s)
Patient Readmission , Critical Care , Humans , Intensive Care Units , Length of Stay , Logistic Models , Retrospective StudiesABSTRACT
Alzheimer's Disease (AD) is one of the leading causes of death and dementia worldwide. Early diagnosis confers many benefits, including improved care and access to effective treatment. However, it is still a medical challenge due to the lack of an efficient and inexpensive way to assess cognitive function [1]. Although research on data from Neuroimaging and Brain Initiative and the advancement in data analytics has greatly enhanced our understanding of the underlying disease process, there is still a lack of complete knowledge regarding the indicative biomarkers of Alzheimer's Disease. Recently, computer aided diagnosis of mild cognitive impairment and AD with functional brain images using machine learning methods has become popular. However, the prediction accuracy remains unoptimistic, with prediction accuracy ranging from 60% to 88% [2,3,6]. Among them, support vector machine is the most popular classifier. However, because of the relatively small sample size and the amount of noise in functional brain imaging data, a single classifier cannot achieve high classification performance. Instead of using a global classifier, in this work, we aim to improve AD prediction accuracy by combining three different classifiers using weighted and unweighted schemes. We rank image-derived features according to their importance to the classification performance and show that the top ranked features are localized in the brain areas which have been found to associate with the progression of AD. We test the proposed approach on 11C-PIB PET scans from The Alzheimer's Disease Neuroimaging Initiative (ADNI) database and demonstrated that the weighted ensemble models outperformed individual models of K-Nearest Neighbors, Random Forests, Neural Nets with overall cross validation accuracy of 86.1% ± 8.34%, specificity of 90.6% ± 12.9% and test accuracy of 80.9% and specificity 85.76% in classification of AD, mild cognitive impairment and healthy elder adults.
Subject(s)
Alzheimer Disease , Aniline Compounds , Benzothiazoles , Carbon Radioisotopes , Cognitive Dysfunction , Humans , Positron-Emission Tomography , ThiazolesABSTRACT
One pressing need in the area of public health is timely, accurate, and complete reporting of deaths and the conditions leading up to them. Fast Healthcare Interoperability Resources (FHIR) is a new HL7 interoperability standard for electronic health record (EHR), while Sustainable Medical Applications and Reusable Technologies (SMART)-on-FHIR enables third-party app development that can work "out of the box". This research demonstrates the feasibility of developing SMART-on-FHIR applications to enable medical professionals to perform timely and accurate death reporting within multiple different jurisdictions of US. We explored how the information on a standard certificate of death can be mapped to resources defined in the FHIR standard (DSTU2). We also demonstrated analytics for potentially improving the accuracy and completeness of mortality reporting data.
ABSTRACT
OBJECTIVE: Rapid advances of high-throughput technologies and wide adoption of electronic health records (EHRs) have led to fast accumulation of -omic and EHR data. These voluminous complex data contain abundant information for precision medicine, and big data analytics can extract such knowledge to improve the quality of healthcare. METHODS: In this paper, we present -omic and EHR data characteristics, associated challenges, and data analytics including data preprocessing, mining, and modeling. RESULTS: To demonstrate how big data analytics enables precision medicine, we provide two case studies, including identifying disease biomarkers from multi-omic data and incorporating -omic information into EHR. CONCLUSION: Big data analytics is able to address -omic and EHR data challenges for paradigm shift toward precision medicine. SIGNIFICANCE: Big data analytics makes sense of -omic and EHR data to improve healthcare outcome. It has long lasting societal impact.
Subject(s)
Databases, Factual , Electronic Health Records , Genomics , Medical Informatics , Precision Medicine , HumansABSTRACT
The Centers for Disease Control estimate that 1.6 to 3.8 million concussions occur in sports and recreational activities annually. Studies have shown that concussions increase the risk of future injuries and mild cognitive disorders. Despite extensive research on sports related concussion risk factors, the factors which are most predictive of concussion outcome and recovery time course remain unknown. In order to overcome the issue of physician bias and to identify the factors which can best predict concussion diagnosis, we propose a multi-variate logistic regression based analysis. We demonstrate our results on a dataset with 126 subjects (ages 12-31). Our results indicate that among 322 features, our model selected 27-29 features which included a history of playing sports, history of a previous concussion, drowsiness, nausea, trouble focusing as measured by a common symptom list, and oculomotor function. The features picked using our model were found to be highly predictive of concussions and gave a prediction performance accuracy greater than 90%, Matthews correlation coefficient greater than 0.8 and the area under the curve greater than 0.95.
ABSTRACT
Patient similarity measurement is an important tool for cohort identification in clinical decision support applications. A reliable similarity metric can be used for deriving diagnostic or prognostic information about a target patient using other patients with similar trajectories of health-care events. However, the measure of similar care trajectories is challenged by the irregularity of measurements, inherent in health care. To address this challenge, we propose a novel temporal similarity measure for patients based on irregularly measured laboratory test data from the Multiparameter Intelligent Monitoring in Intensive Care database and the pediatric Intensive Care Unit (ICU) database of Children's Healthcare of Atlanta. This similarity measure, which is modified from the Smith Waterman algorithm, identifies patients that share sequentially similar laboratory results separated by time intervals of similar length. We demonstrate the predictive power of our method; that is, patients with higher similarity in their previous histories will most likely have higher similarity in their later histories. In addition, compared with other non-temporal measures, our method is stronger at predicting mortality in ICU patients diagnosed with acute kidney injury and sepsis. CATEGORIES AND SUBJECT DESCRIPTORS: H.3.3 [Information Storage and Retrieval]: Retrieval models and rankings - similarity measures; J.3 [Applied Computing]: Life and medical sciences - health and medical information systems. GENERAL TERM: Algorithm.
ABSTRACT
Cancer is one of the most common and deadly diseases around the world. Amongst all the different treatments of cancer such as surgery, chemotherapy and radiation therapy, surgical resection is the most effective. Successful surgeries greatly rely on the detection of the accurate tumor size and location, which can be enhanced by contrast agents. Commercial endoscope light sources, however, offer only white light illumination. In this paper, we present the development of a LED endoscope light source that provides 2 light channels plus white light to help surgeons to detect a clear tumor margin during minimally invasive surgeries. By exciting indocyanine green (ICG) and 5-Aminolaevulinic acid (ALA)-induced protoporphyrin IX (PPIX), the light source is intended to give the user a visible image of the tumor margin. This light source is also portable, easy to use and costs less than $300 to build.
Subject(s)
Fluorescent Dyes/chemistry , Light , Minimally Invasive Surgical Procedures/instrumentation , Optical Imaging/instrumentation , Semiconductors , Aminolevulinic Acid/chemistry , Humans , Indocyanine Green/chemistry , Neoplasms/diagnosis , Neoplasms/surgery , Photosensitizing Agents/chemistry , Protoporphyrins/chemistryABSTRACT
Physical injury, stroke, trauma, traumatic brain injury and spinal cord injury rank among the top causes of disability. There are a total of 54 million people in the US requiring rehabilitative assistance of which 15.3 million people are in the age groups of 18-44. However, the compliance rate for patients performing rehabilitation exercises in the home environment is poor. In this paper, we design and prototype a personalized home rehabilitation system, MotionTalk, for the real time quantitative assessment of mobility. Performance of rehabilitation is designed to be assessed using the changes in mobility, reflected in the exercises performed by patients at home with respect to the same exercises performed in the clinic. Our system is capable of capturing motion using Microsoft Kinect and analyzing the position and rotation information to give scores for assessing rehabilitation progress. In comparison to conventional rehabilitation systems, MotionTalk is an inexpensive (<$150 compared to conventional systems costing >$1000), less intrusive and personalized home rehabilitation system, which was developed and tested using data from able-bodied volunteers at Georgia Institute of Technology.
ABSTRACT
Sickle cell disease (SCD) is the most common inherited disease, and SCD symptoms impact functioning and well-being. For example, adolescents with SCD have a higher tendency of psychological problems than the general population. Acceptance and Commitment Therapy (ACT), a cognitive-behavioral therapy, is an effective intervention to promote quality of life and functioning in adolescents with chronic illness. However, traditional visit-based therapy sessions are restrained by challenges, such as limited follow-up, insufficient data collection, low treatment adherence, and delayed intervention. In this paper, we present Instant Acceptance and Commitment Therapy (iACT), a system designed to enhance the quality of pediatric ACT. iACT utilizes text messaging technology, which is the most popular cell phone activity among adolescents, to conduct real-time psychotherapy interventions. The system is built on cloud computing technologies, which provides a convenient and cost-effective monitoring environment. To evaluate iACT, a trial with 60 adolescents with SCD is being conducted in conjunction with the Georgia Institute of Technology, Children's Healthcare of Atlanta, and Georgia State University.
Subject(s)
Acceptance and Commitment Therapy , Anemia, Sickle Cell/psychology , Anemia, Sickle Cell/therapy , Cell Phone , Psychotherapy , Telemedicine , Adolescent , Child , HumansABSTRACT
Rapid prototyping of medically assistive mobile devices promises to fuel innovation and provides opportunity for hands-on engineering training in biomedical engineering curricula. This paper presents the design and outcomes of a course offered during a 16-week semester in Fall 2011 with 11 students enrolled. The syllabus covered a mobile health design process from end-to-end, including storyboarding, non-functional prototypes, integrated circuit programming, 3D modeling, 3D printing, cloud computing database programming, and developing patient engagement through animated videos describing the benefits of a new device. Most technologies presented in this class are open source and thus provide unlimited "hackability". They are also cost-effective and easily transferrable to other departments.
Subject(s)
Pain Management/methods , Telemedicine , Asthma/pathology , Asthma/prevention & control , Biomedical Engineering/education , Child , Computer-Aided Design , Curriculum , Humans , Pain Management/instrumentation , Pilot Projects , Radio Frequency Identification DeviceABSTRACT
Traumatic brain injury (TBI) is one of the leading causes of death and disability in the age group of 0 - 44 years. Though physical exercises have proven benefits in the rehabilitation process, the compliance rate of patients in the home environment is poor. In this paper we propose a system, MotionTalk, which captures and analyses motion data acquired using Microsoft Kinect. It is designed to give a real time quantitative assessment of the exercises performed by TBI patients at home with respect to the same exercises performed in the clinic by utilizing relatively inexpensive contactless sensing and dynamic programming techniques. In comparison to previous reminder systems, wearable systems, and motion capture systems, MotionTalk is less intrusive in nature and inexpensive to deploy at home because it is based on readily available hardware. This was developed and tested on able bodied volunteers and in the future we hope to test it on patients with TBI, after IRB approval.
Subject(s)
Brain Injuries/rehabilitation , Adult , Algorithms , Humans , Image Processing, Computer-Assisted , Joints/physiology , Markov Chains , Movement , User-Computer Interface , Video Recording , Young AdultABSTRACT
The rapid development of biomedical monitoring technologies has enabled modern intensive care units (ICUs) to gather vast amounts of multimodal measurement data about their patients. However, processing large volumes of complex data in real-time has become a big challenge. Together with ICU physicians, we have designed and developed an ICU clinical decision support system icuARM based on associate rule mining (ARM), and a publicly available research database MIMIC-II (Multi-parameter Intelligent Monitoring in Intensive Care II) that contains more than 40,000 ICU records for 30,000+patients. icuARM is constructed with multiple association rules and an easy-to-use graphical user interface (GUI) for care providers to perform real-time data and information mining in the ICU setting. To validate icuARM, we have investigated the associations between patients' conditions such as comorbidities, demographics, and medications and their ICU outcomes such as ICU length of stay. Coagulopathy surfaced as the most dangerous co-morbidity that leads to the highest possibility (54.1%) of prolonged ICU stay. In addition, women who are older than 50 years have the highest possibility (38.8%) of prolonged ICU stay. For clinical conditions treatable with multiple drugs, icuARM suggests that medication choice can be optimized based on patient-specific characteristics. Overall, icuARM can provide valuable insights for ICU physicians to tailor a patient's treatment based on his or her clinical status in real time.
ABSTRACT
Sickle cell disease, the most common hemoglobin disorder, affects major organ systems with symptoms of pain, anemia and a multitude of chronic conditions. For adolescents, the disease adversely affects school attendance, academic progress and social activity. To effectively study the relationship among school attendance and other factors like demographics and academic performance, studies have relied on self-reporting and school records, all of which have some bias. In this study we design and prototype a system, called SickleSAM (Sickle cell School attendance and Activity Monitoring system), for automatically monitoring school attendance and daily activity of adolescents with sickle cell disease. SickleSAM intends to remove human bias and inaccuracies. The system uses built-in GPS to collect data which will be recorded into a cloud database using Short Messaging Service technology. SickleSAM is developed by Georgia Institute of Technology in conjunction with Children's Healthcare of Atlanta (CHOA). System effectiveness is being evaluated using a trial of 10 adolescents with the disease.