Objective: Medication dosing in pediatrics is complex and prone to errors that may lead to patient harm. To improve computer-assisted dosing, a mathematical model and algorithm were developed to optimize clinical decision support dosing rules and reduce spurious alerts. The objective was to evaluate the feasibility of using this algorithm to adjust dosing rules. Materials and methods: Incorporating historical ordering data, a mathematical model and algorithm were developed to automatically determine optimal dosing rule parameters. The algorithm optimizes the dosing rules by balancing the number of alerts generated for a medication with a minimal length dose interval. In all, 5 candidate medications were tested. An analysis was performed to compare the number of alerts generated by the new model with the current dosing rules. Results: For the 5 medications, the algorithm generated multiple clinically relevant rule possibilities and the rules returned performed as well as current dosing rule or matched historical prescriber behavior. The rules were comparable to or better than the existing system rules in reducing the total alert burden. Discussion: The mathematical model and algorithm are an accurate and scalable solution to adjusting medication dosing rules. They can be implemented to change suboptimal rules more quickly than current manual methods and can be used to help identify and correct poor quality rules. Conclusions: Mathematical modeling using historic prescribing data can generate clinically appropriate electronic dosing rule parameters. This approach represents an automatable and scalable solution that could help reduce alert fatigue and decrease medication dosing errors.
Studies on autism spectrum disorder (ASD) have amassed substantial evidence for the role of genetics in the disease's phenotypic manifestation. A large number of coding and non-coding variants with low penetrance likely act in a combinatorial manner to explain the variable forms of ASD. However, many of these combined interactions, both additive and epistatic, remain undefined. Coalitional game theory (CGT) is an approach that seeks to identify players (individual genetic variants or genes) who tend to improve the performance-association to a disease phenotype of interest-of any coalition (subset of co-occurring genetic variants) they join. This method has been previously applied to boost biologically informative signal from gene expression data and exome sequencing data but remains to be explored in the context of cooperativity among non-coding genomic regions. We describe our extension of previous work, highlighting non-coding chromosomal regions relevant to ASD using CGT on alteration data of 4595 fully sequenced genomes from 756 multiplex families. Genomes were encoded into binary matrices for three types of non-coding regions previously implicated in ASD and separated into ASD (case) and unaffected (control) samples. A player metric, the Shapley value, enabled determination of individual variant contributions in both sets of cohorts. A total of 30 non-coding positions were found to have significantly elevated player scores and likely represent significant contributors to the genetic coordination underlying ASD. Cross-study analyses revealed that a subset of mutated non-coding regions (all of which are in human accelerated regions (HARs)) and related genes are involved in biological pathways or behavioral outcomes known to be affected in autism, suggesting the importance of single nucleotide polymorphisms (SNPs) within HARs in ASD. These findings support the use of CGT in identifying hidden yet influential non-coding players from large-scale genomic data, to better understand the precise underpinnings of complex neurodevelopmental disorders such as autism.
To demonstrate the usefulness of applying supervised machine-learning analyses to identify specific groups of patients that experience high levels of mortality post-interhospital transfer. This was a cross-sectional analysis of data from the Health Care Utilization Project 2013 National Inpatient Sample, that applied supervised machine-learning approaches that included (1) classification and regression tree to identify mutually exclusive groups of patients and their associated characteristics of those experiencing the highest levels of mortality and (2) random forest to identify the relative importance of each characteristic's contribution to post-transfer mortality. A total of 21 independent groups of patients were identified, with 13 of those groups exhibiting at least double the national average rate of mortality post-transfer. Patient characteristics identified as influencing post-transfer mortality the most included: diagnosis of a circulatory disorder, comorbidity of coagulopathy, diagnosis of cancer, and age. Employing supervised machine-learning analyses enabled the computational feasibility to assess all potential combinations of available patient characteristics to identify groups of patients experiencing the highest rates of mortality post-interhospital transfer, providing potentially useful data to support developing clinical decision support systems in future work.
Over the last decade, there has been an explosion of digital interventions that aim to either supplement or replace face-to-face mental health services. More recently, a number of automated conversational agents have also been made available, which respond to users in ways that mirror a real-life interaction. What are the social and ethical concerns that arise from these advances? In this article, we discuss, from a young person’s perspective, the strengths and limitations of using chatbots in mental health support. We also outline what we consider to be minimum ethical standards for these platforms, including issues surrounding privacy and confidentiality, efficacy, and safety, and review three existing platforms (Woebot, Joy, and Wysa) according to our proposed framework. It is our hope that this article will stimulate ethical debate among app developers, practitioners, young people, and other stakeholders, and inspire ethically responsible practice in digital mental health.
Medication dosing in pediatrics is complex and prone to errors that may lead to patient harm. To improve computer-assisted dosing, a mathematical model and algorithm were developed to optimize clinical decision support dosing rules and reduce spurious alerts. The objective was to evaluate the feasibility of using this algorithm to adjust dosing rules. Incorporating historical ordering data, a mathematical model and algorithm were developed to automatically determine optimal dosing rule parameters. The algorithm optimizes the dosing rules by balancing the number of alerts generated for a medication with a minimal length dose interval. In all, 5 candidate medications were tested. An analysis was performed to compare the number of alerts generated by the new model with the current dosing rules. For the 5 medications, the algorithm generated multiple clinically relevant rule possibilities and the rules returned performed as well as current dosing rule or matched historical prescriber behavior. The rules were comparable to or better than the existing system rules in reducing the total alert burden. The mathematical model and algorithm are an accurate and scalable solution to adjusting medication dosing rules. They can be implemented to change suboptimal rules more quickly than current manual methods and can be used to help identify and correct poor quality rules. Mathematical modeling using historic prescribing data can generate clinically appropriate electronic dosing rule parameters. This approach represents an automatable and scalable solution that could help reduce alert fatigue and decrease medication dosing errors.
Over the last decade, there has been an explosion of digital interventions that aim to either supplement or replace face-to-face mental health services. More recently, a number of automated conversational agents have also been made available, which respond to users in ways that mirror a real-life interaction. What are the social and ethical concerns that arise from these advances? In this article, we discuss, from a young person's perspective, the strengths and limitations of using chatbots in mental health support. We also outline what we consider to be minimum ethical standards for these platforms, including issues surrounding privacy and confidentiality, efficacy, and safety, and review three existing platforms (Woebot, Joy, and Wysa) according to our proposed framework. It is our hope that this article will stimulate ethical debate among app developers, practitioners, young people, and other stakeholders, and inspire ethically responsible practice in digital mental health.
Bedside monitors are intended as a safety net in patient care, but their management in the inpatient setting is a significant patient safety concern. The low precision of vital sign alarm systems leads to clinical staff becoming desensitized to the sound of the alarm, a phenomenon known as alarm fatigue. Alarm fatigue has been shown to increase response time to alarms or result in alarms being ignored altogether and has negative consequences for patient safety. We present methods to establish personalized thresholds for heart rate and respiratory rate alarms. These thresholds are first chosen based on patient characteristics available at the time of admission and are then adapted to incorporate vital signs observed in the first 2 hours of monitoring. We demonstrate that the adapted thresholds are similar to those chosen by clinicians for individual patients and would result in fewer alarms than the currently used age-based thresholds. Personalized vital sign alarm thresholds can help to alleviate the problem of alarm fatigue in an inpatient setting while ensuring that all critical vital signs are detected.
Homeless people experience a unique set of challenges leading to pervasive health and social problems. An increasing number of researchers have harnessed photographic data to gain a unique perspective of marginalised groups. The aim of the study is to explore the feasibility of using photographs in research to understand the complex environment experienced by homeless people, with a special interest in mental health. Individuals who frequently attend homeless facilities in London were sensitively approached and asked if they would be interested in taking part in the ‘Views From the Street’ pilot study. Once agreement was confirmed through a formal consenting procedure, participants were asked to visually capture and upload their own digital photos, along with a brief description. The collection of data highlighted a number of barriers to engagement and acceptability, including issues around the level of familiarity with the recruiter, practicalities of participation, public perception of phone use, poor technical literacy, anonymity, and disassociation with the ‘homeless’ label. Recommendations are made for future research utilising photographic participatory designs with the homeless population.
Convolutional neural networks (CNNs) have gained steady popularity as a tool to perform automatic classification of whole slide histology images. While CNNs have proven to be powerful classifiers in this context, they fail to explain this classification, as the network engineered features used for modeling and classification are ONLY interpretable by the CNNs themselves. This work aims at enhancing a traditional neural network model to perform histology image modeling, patient classification, and interpretation of the distinctive features identified by the network within the histology whole slide images (WSIs). We synthesize a workflow which (a) intelligently samples the training data by automatically selecting only image areas that display visible disease-relevant tissue state and (b) isolates regions most pertinent to the trained CNN prediction and translates them to observable and qualitative features such as color, intensity, cell and tissue morphology and texture. We use the Cancer Genome Atlas’s Breast Invasive Carcinoma (TCGA-BRCA) histology dataset to build a model predicting patient attributes (disease stage and node status) and the tumor proliferation challenge (TUPAC 2016) breast cancer histology image repository to help identify disease-relevant tissue state (mitotic activity). We find that our enhanced CNN based workflow both increased patient attribute predictive accuracy (~2% increase for disease stage and ~10% increase for node status) and experimentally proved that a data-driven CNN histology model predicting breast invasive carcinoma stages is highly sensitive to features such as color, cell size, and shape, granularity, and uniformity. This work summarizes the need for understanding the widely trusted models built using deep learning and adds a layer of biological context to a technique that functioned as a classification only approach till now.
Non-adherence with pharmacologic treatment is associated with increased rates of relapse and rehospitalisation among patients with schizophrenia and bipolar disorder. To improve treatment response, remission, and recovery, research efforts are still needed to elucidate how to effectively map patient’s response to medication treatment including both therapeutic and adverse effects, compliance, and satisfaction in the prodromal phase of illness (ie, the time period in between direct clinical consultation and relapse). The Actionable Intime Insights (AI2) application draws information from Australian Medicare administrative claims records in real time when compliance with treatment does not meet best practice guidelines for managing chronic severe mental illness. Subsequently, the AI2 application alerts clinicians and patients when patients do not adhere to guidelines for treatment. The aim of this study was to evaluate the impact of the AI2 application on the risk of hospitalisation among simulated patients with schizophrenia and bipolar disorder. Monte Carlo simulation methodology was used to estimate the impact of the AI2 intervention on the probability of hospitalisation over a 2-year period. Results indicated that when the AI2 algorithmic intervention had an efficacy level of (>0.6), over 80% of actioned alerts were contributing to reduced hospitalisation risk among the simulated patients. Such findings indicate the potential utility of the AI2 application should replication studies validate its methodologic and ecological rigour in real-world settings.
We evaluated quasi-healthy cohorts (model cohorts), derived from clinical data, to determine how well they simulated control cohorts. Control cohorts comprised individuals extracted from a public checkup database in Japan, under the condition that their values for 3 basic laboratory tests fall within specific reference ranges (3Ts condition). Model cohorts comprised outpatients, extracted from a clinical database at a hospital, under the 3Ts condition or under the condition that their values for 4 laboratory tests fall within specific reference ranges (4Ts condition). Because even a patient with a serious illness, such as cancer, may present with normal values on basic laboratory tests, one additional condition was added: the duration (1 or 3 months; 1M or 3M) during which patients were not hospitalized after their first laboratory test. For evaluations, cohorts were specified by age and sex. The 4Ts + 3M condition was the most effective condition, under which model cohorts were used to successfully simulate age-dependent changes and sex differences in laboratory test values for control cohorts. Therefore, by properly setting the conditions for extracting quasi-healthy individuals, we can derive cohorts from clinical data to simulate various types of cohorts. Although some issues with the proposed method remain to be solved, this approach presents new possibilities for using clinical data for cohort studies.
There is a dearth of research investigating youths’ experience of grief and mourning after the death of close friends or family. Even less research has explored the question of how youth use social media sites to engage in the grieving process. This study employs qualitative analysis and natural language processing to examine tweets that follow 2 deaths. First, we conducted a close textual read on a sample of tweets by Gakirah Barnes, a gang-involved teenaged girl in Chicago, and members of her Twitter network, over a 19-day period in 2014 during which 2 significant deaths occurred: that of Raason “Lil B” Shaw and Gakirah’s own death. We leverage the grief literature to understand the way Gakirah and her peers express thoughts, feelings, and behaviors at the time of these deaths. We also present and explain the rich and complex style of online communication among gang-involved youth, one that has been overlooked in prior research. Next, we overview the natural language processing output for expressions of loss and grief in our data set based on qualitative findings and present an error analysis on its output for grief. We conclude with a call for interdisciplinary research that analyzes online and offline behaviors to help understand physical and emotional violence and other problematic behaviors prevalent among marginalized communities.
Aims and Scope: The conference aims were two-fold: (1) to explore how digital technology is implemented into personalized and/or group mental health interventions and (2) to promote digital equality through developing culturally sensitive ways of bringing technological innovation to disadvantaged groups. A broad scope of perspectives were welcomed and encouraged, from lived experience, academic, clinical, media, the arts, policy-making, tech innovation, and other perspectives.
The use of precordial Doppler monitoring to prevent decompression sickness (DS) is well known by the scientific community as an important instrument for early diagnosis of DS. However, the timely and correct diagnosis of DS without assistance from diving medical specialists is unreliable. Thus, a common protocol for the manual annotation of echo Doppler signals and a tool for their automated recording and annotation are necessary. We have implemented original software for efficient bubble appearance annotation and proposed a unified annotation protocol. The tool auto-sets the response time of human “bubble examiners,” performs playback of the Doppler file by rendering it independent of the specific audio player, and enables the annotation of individual bubbles or multiple bubbles known as “showers.” The tool provides a report with an optimized data structure and estimates the embolic risk level according to the Extended Spencer Scale. The tool is built in accordance with ISO/IEC 9126 on software quality and has been projected and tested with assistance from the Divers Alert Network (DAN) Europe Foundation, which employs this tool for its diving data acquisition campaigns.
Algorithm–based clinical decision support (CDS) systems associate patient-derived health data with outcomes of interest, such as in-hospital mortality. However, the quality of such associations often depends on the availability of site-specific training data. Without sufficient quantities of data, the underlying statistical apparatus cannot differentiate useful patterns from noise and, as a result, may underperform. This initial training data burden limits the widespread, out-of-the-box, use of machine learning–based risk scoring systems. In this study, we implement a statistical transfer learning technique, which uses a large “source” data set to drastically reduce the amount of data needed to perform well on a “target” site for which training data are scarce. We test this transfer technique with AutoTriage, a mortality prediction algorithm, on patient charts from the Beth Israel Deaconess Medical Center (the source) and a population of 48 249 adult inpatients from University of California San Francisco Medical Center (the target institution). We find that the amount of training data required to surpass 0.80 area under the receiver operating characteristic (AUROC) on the target set decreases from more than 4000 patients to fewer than 220. This performance is superior to the Modified Early Warning Score (AUROC: 0.76) and corresponds to a decrease in clinical data collection time from approximately 6 months to less than 10 days. Our results highlight the usefulness of transfer learning in the specialization of CDS systems to new hospital sites, without requiring expensive and time-consuming data collection efforts.
The objective of this study was to determine whether the Food and Drug Administration’s Adverse Event Reporting System (FAERS) data set could serve as the basis of automated electronic health record (EHR) monitoring for the adverse drug reaction (ADR) subset of adverse drug events. We retrospectively collected EHR entries for 71 909 pediatric inpatient visits at Cincinnati Children’s Hospital Medical Center. Natural language processing (NLP) techniques were used to identify positive diseases/disorders and signs/symptoms (DDSSs) from the patients’ clinical narratives. We downloaded all FAERS reports submitted by medical providers and extracted the reported drug-DDSS pairs. For each patient, we aligned the drug-DDSS pairs extracted from their clinical notes with the corresponding drug-DDSS pairs from the FAERS data set to identify Drug-Reaction Pair Sentences (DRPSs). The DRPSs were processed by NLP techniques to identify ADR-related DRPSs. We used clinician annotated, real-world EHR data as reference standard to evaluate the proposed algorithm. During evaluation, the algorithm achieved promising performance and showed great potential in identifying ADRs accurately for pediatric patients.
Personalized and precision vaccination requires consideration of an individual’s sex and age. This article proposed systematic methods to study individual differences in adverse reactions following vaccination and chose trivalent influenza vaccine as a use case. Data were extracted from the Vaccine Adverse Event Reporting System from years 1990 to 2014. We first grouped symptoms into the Medical Dictionary for Regulatory Activities System Organ Classes (SOCs). We then applied zero-truncated Poisson regression and logistic regression to identify reporting differences among different individual groups over the SOCs. After that, we further studied detailed symptoms of 4 selected SOCs. In all, 19 of the 26 SOCs and 17 of the 434 symptoms under the 4 selected SOCs show significant reporting differences based on sex and/or age. In addition to detecting previously reported associations among sex, age group, and symptoms, our approach also enabled the detection of new associations.