Using data science to improve outcomes for persons with opioid use disorder

Exploring Algorithmic Explainability: Generating Explainable AI Insights for Personalized Clinical Decision Support Focused on Cannabis Intoxication in Young Adults

As an increasing number of states adopt more permissive cannabis regulations, the necessity of gaining a comprehensive understanding of cannabis's effects on young adults has grown exponentially, driven by its escalating prevalence of use. By leveraging popular eXplainable Artificial Intelligence (XAI) techniques such as SHAP (SHapley Additive exPlanations), rule-based explanations, intrinsically interpretable models, and counterfactual explanations, we undertake an exploratory but in-depth examination of the impact of cannabis use on individual behavioral patterns and physiological states. This study explores the possibility of facilitating algorithmic decision-making by combining interpretable artificial intelligence (XAI) techniques with sensor data, with the aim of providing researchers and clinicians with personalized analyses of cannabis intoxication behavior. SHAP analyzes the importance and quantifies the impact of specific factors such as environmental noise or heart rate, enabling clinicians to pinpoint influential behaviors and environmental conditions. SkopeRules simplify the understanding of cannabis use for a specific activity or environmental use. Decision trees provide a clear visualization of how factors interact to influence cannabis consumption. Counterfactual models help identify key changes in behaviors or conditions that may alter cannabis use outcomes, to guide effective individualized intervention strategies. This multidimensional analytical approach not only unveils changes in behavioral and physiological states after cannabis use, such as frequent fluctuations in activity states, nontraditional sleep patterns, and specific use habits at different times and places, but also highlights the significance of individual differences in responses to cannabis use. These insights carry profound implications for clinicians seeking to gain a deeper understanding of the diverse needs of their patients and for tailoring precisely targeted intervention strategies. Furthermore, our findings highlight the pivotal role that XAI technologies could play in enhancing the transparency and interpretability of Clinical Decision Support Systems (CDSS), with a particular focus on substance misuse treatment. This research significantly contributes to ongoing initiatives aimed at advancing clinical practices that aim to prevent and reduce cannabis-related harms to health, positioning XAI as a supportive tool for clinicians and researchers alike.

A Dynamic Model of Opioid Overdose Deaths in Canada during the Co-Occurring Opioid Overdose Crisis and COVID-19 Pandemic

With over 40,000 opioid-related overdose deaths between January 2016 and June 2023, the opioid-overdose crisis is a significant public health concern for Canada. The opioid crisis arose from a complex system involving prescription opioid use, the use of prescription opioids not as prescribed, and non-medical opioid use. The increasing presence of fentanyl and its analogues in the illegal drugs supply has been an important driver of the crisis. In response to the overdose crisis, governments at the municipal, provincial/territorial, and federal levels have increased actions to address opioid-related harms. At the onset of the COVID-19 pandemic, concerns emerged over how the pandemic context may impact the opioid overdose crisis. Using evidence from a number of sources, we developed a dynamic mathematical model of opioid overdose death to simulate possible trajectories of overdose deaths during the COVID-19 pandemic. This model incorporates information on prescription opioid use, opioid use not as prescribed, non-medical opioid use, the level of fentanyl in the drug supply, and a measure of the proportion deaths preventable by new interventions. The simulated scenarios provided decision makers with insight into possible trajectories of the opioid crisis in Canada during the COVID-19 pandemic, highlighting the potential of the crisis to take a turn for the worse under certain assumptions, and thus, informing planning during a period when surveillance data were not yet available. This model provides a starting point for future models, and through its development, we have identified important data and evidence gaps that need to be filled in order to inform future action.

Question-answering system extracts information on injection drug use from clinical notes

BACKGROUND

Injection drug use (IDU) can increase mortality and morbidity. Therefore, identifying IDU early and initiating harm reduction interventions can benefit individuals at risk. However, extracting IDU behaviors from patients' electronic health records (EHR) is difficult because there is no other structured data available, such as International Classification of Disease (ICD) codes, and IDU is most often documented in unstructured free-text clinical notes. Although natural language processing can efficiently extract this information from unstructured data, there are no validated tools.

METHODS

To address this gap in clinical information, we design a question-answering (QA) framework to extract information on IDU from clinical notes for use in clinical operations. Our framework involves two main steps: (1) generating a gold-standard QA dataset and (2) developing and testing the QA model. We use 2323 clinical notes of 1145 patients curated from the US Department of Veterans Affairs (VA) Corporate Data Warehouse to construct the gold-standard dataset for developing and evaluating the QA model. We also demonstrate the QA model's ability to extract IDU-related information from temporally out-of-distribution data.

RESULTS

Here, we show that for a strict match between gold-standard and predicted answers, the QA model achieves a 51.65% F1 score. For a relaxed match between the gold-standard and predicted answers, the QA model obtains a 78.03% F1 score, along with 85.38% Precision and 79.02% Recall scores. Moreover, the QA model demonstrates consistent performance when subjected to temporally out-of-distribution data.

CONCLUSIONS

Our study introduces a QA framework designed to extract IDU information from clinical notes, aiming to enhance the accurate and efficient detection of people who inject drugs, extract relevant information, and ultimately facilitate informed patient care.

The evolution of Big Data in neuroscience and neurology

Neurological diseases are on the rise worldwide, leading to increased healthcare costs and diminished quality of life in patients. In recent years, Big Data has started to transform the fields of Neuroscience and Neurology. Scientists and clinicians are collaborating in global alliances, combining diverse datasets on a massive scale, and solving complex computational problems that demand the utilization of increasingly powerful computational resources. This Big Data revolution is opening new avenues for developing innovative treatments for neurological diseases. Our paper surveys Big Data's impact on neurological patient care, as exemplified through work done in a comprehensive selection of areas, including Connectomics, Alzheimer's Disease, Stroke, Depression, Parkinson's Disease, Pain, and Addiction (e.g., Opioid Use Disorder). We present an overview of research and the methodologies utilizing Big Data in each area, as well as their current limitations and technical challenges. Despite the potential benefits, the full potential of Big Data in these fields currently remains unrealized. We close with recommendations for future research aimed at optimizing the use of Big Data in Neuroscience and Neurology for improved patient outcomes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40537-023-00751-2.

Data Science Implementation Trends in Nursing Practice: A Review of the 2021 Literature

OBJECTIVES

The goal of this work was to provide a review of the implementation of data science-driven applications focused on structural or outcome-related nurse-sensitive indicators in the literature in 2021. By conducting this review, we aim to inform readers of trends in the nursing indicators being addressed, the patient populations and settings of focus, and lessons and challenges identified during the implementation of these tools.

METHODS

We conducted a rigorous descriptive review of the literature to identify relevant research published in 2021. We extracted data on model development, implementation-related strategies and measures, lessons learned, and challenges and stakeholder involvement. We also assessed whether reports of data science application implementations currently follow the guidelines of the Developmental and Exploratory Clinical Investigations of DEcision support systems driven by AI (DECIDE-AI) framework.

RESULTS

Of 4,943 articles found in PubMed (NLM) and CINAHL (EBSCOhost), 11 were included in the final review and data extraction. Systems leveraging data science were developed for adult patient populations and were primarily deployed in hospital settings. The clinical domains targeted included mortality/deterioration, utilization/resource allocation, and hospital-acquired infections/COVID-19. The composition of development teams and types of stakeholders involved varied. Research teams more frequently reported on implementation methods than implementation results. Most studies provided lessons learned that could help inform future implementations of data science systems in health care.

CONCLUSION

In 2021, very few studies report on the implementation of data science-driven applications focused on structural- or outcome-related nurse-sensitive indicators. This gap in the sharing of implementation strategies needs to be addressed in order for these systems to be successfully adopted in health care settings.

Prospective acceptability of digital phenotyping among pregnant and parenting people with opioid use disorder: A multisite qualitative study

Background

While medications for opioid use disorder (MOUD) effectively treat OUD during pregnancy and the postpartum period, poor treatment retention is common. Digital phenotyping, or passive sensing data captured from personal mobile devices, namely smartphones, provides an opportunity to understand behaviors, psychological states, and social influences contributing to perinatal MOUD non-retention. Given this novel area of investigation, we conducted a qualitative study to determine the acceptability of digital phenotyping among pregnant and parenting people with opioid use disorder (PPP-OUD).

Methods

This study was guided by the Theoretical Framework of Acceptability (TFA). Within a clinical trial testing a behavioral health intervention for PPP-OUD, we used purposeful criterion sampling to recruit 11 participants who delivered a child in the past 12  months and received OUD treatment during pregnancy or the postpartum period. Data were collected through phone interviews using a structured interview guide based on four TFA constructs (affective attitude, burden, ethicality, self-efficacy). We used framework analysis to code, chart, and identify key patterns within the data.

Results

Participants generally expressed positive attitudes about digital phenotyping and high self-efficacy and low anticipated burden to participate in studies that collect smartphone-based passive sensing data. Nonetheless, concerns were noted related to data privacy/security and sharing location information. Differences in participant assessments of burden were related to length of time required and level of remuneration to participate in a study. Interviewees voiced broad support for participating in a digital phenotyping study with known/trusted individuals but expressed concerns about third-party data sharing and government monitoring.

Conclusion

Digital phenotyping methods were acceptable to PPP-OUD. Enhancements in acceptability include allowing participants to maintain control over which data are shared, limiting frequency of research contacts, aligning compensation with participant burden, and outlining data privacy/security protections on study materials.

Natural Language Processing and Machine Learning to Identify People Who Inject Drugs in Electronic Health Records

Background

Improving the identification of people who inject drugs (PWID) in electronic medical records can improve clinical decision making, risk assessment and mitigation, and health service research. Identification of PWID currently consists of heterogeneous, nonspecific International Classification of Diseases (ICD) codes as proxies. Natural language processing (NLP) and machine learning (ML) methods may have better diagnostic metrics than nonspecific ICD codes for identifying PWID.

Methods

We manually reviewed 1000 records of patients diagnosed with Staphylococcus aureus bacteremia admitted to Veterans Health Administration hospitals from 2003 through 2014. The manual review was the reference standard. We developed and trained NLP/ML algorithms with and without regular expression filters for negation (NegEx) and compared these with 11 proxy combinations of ICD codes to identify PWID. Data were split 70% for training and 30% for testing. We calculated diagnostic metrics and estimated 95% confidence intervals (CIs) by bootstrapping the hold-out test set. Best models were determined by best F-score, a summary of sensitivity and positive predictive value.

Results

Random forest with and without NegEx were the best-performing NLP/ML algorithms in the training set. Random forest with NegEx outperformed all ICD-based algorithms. F-score for the best NLP/ML algorithm was 0.905 (95% CI, .786-.967) and 0.592 (95% CI, .550-.632) for the best ICD-based algorithm. The NLP/ML algorithm had a sensitivity of 92.6% and specificity of 95.4%.

Conclusions

NLP/ML outperformed ICD-based coding algorithms at identifying PWID in electronic health records. NLP/ML models should be considered in identifying cohorts of PWID to improve clinical decision making, health services research, and administrative surveillance.