Increasing Complexity in Rule-Based Clinical Decision Support: The Symptom Assessment and Management Intervention

Exploring the symptoms and psychological experiences among lung cancer convalescence patients after radical lobectomy: A qualitative study

OBJECTIVE

This study aims to explore the symptom experiences and psychological feelings of lung cancer patients after radical lobectomy in China.

METHODS

A qualitative study was conducted using face-to-face semistructured interviews with lung cancer patients who had a radical lobectomy for treatment of their cancer during the convalescence period. Participants (n = 18) were recruited from a general hospital in China, and patients were selected using purposive sampling from September 2021 to February 2022. Interviews were recorded and transcribed verbatim, and Colaizzi's seven-step method of phenomenology was used. The Consolidated Criteria for Reporting Qualitative Research (COREQ) checklist was conducted to report the study.

RESULTS

Four themes were extracted from the interview data: physiological dimensions (fatigue, cough or sputum, chest tightness and shortness of breath, daily activities affected, sleep disturbance, lack of appetite); psychological dimensions (negative emotion, fear of cancer recurrence, learning to accept reality, strengthened faith and hope); family dimensions (heavy economic burden, perceived family care, improved health management behavior); and social dimensions (perceived support of medical staff, decreased sense of social value and self-identity, changes in social and working style).

CONCLUSION

Lung cancer patients are still troubled by many problems during the postoperative recovery period. Medical staff should design and implement effective evaluations and targeted interventions for patients' physical and mental health as soon as possible to improve patients' physical and mental health, as well as their quality of life.

A qualitative analysis of algorithm-based decision support usability testing for symptom management across the trajectory of cancer care: one size does not fit all

BACKGROUND

Adults with cancer experience symptoms that change across the disease trajectory. Due to the distress and cost associated with uncontrolled symptoms, improving symptom management is an important component of quality cancer care. Clinical decision support (CDS) is a promising strategy to integrate clinical practice guideline (CPG)-based symptom management recommendations at the point of care.

METHODS

The objectives of this project were to develop and evaluate the usability of two symptom management algorithms (constipation and fatigue) across the trajectory of cancer care in patients with active disease treated in comprehensive or community cancer care settings to surveillance of cancer survivors in primary care practices. A modified ADAPTE process was used to develop algorithms based on national CPGs. Usability testing involved semi-structured interviews with clinicians from varied care settings, including comprehensive and community cancer centers, and primary care. The transcripts were analyzed with MAXQDA using Braun and Clarke's thematic analysis method. A cross tabs analysis was also performed to assess the prevalence of themes and subthemes by cancer care setting.

RESULTS

A total of 17 clinicians (physicians, nurse practitioners, and physician assistants) were interviewed for usability testing. Three main themes emerged: (1) Algorithms as useful, (2) Symptom management differences, and (3) Different target end-users. The cross-tabs analysis demonstrated differences among care trajectories and settings that originated in the Symptom management differences theme. The sub-themes of "Differences between diseases" and "Differences between care trajectories" originated from participants working in a comprehensive cancer center, which tends to be disease-specific locations for patients on active treatment. Meanwhile, participants from primary care identified the sub-theme of "Differences in settings," indicating that symptom management strategies are care setting specific.

CONCLUSIONS

While CDS can help promote evidence-based symptom management, systems providing care recommendations need to be specifically developed to fit patient characteristics and clinical context. Findings suggest that one set of algorithms will not be applicable throughout the entire cancer trajectory. Unique CDS for symptom management will be needed for patients who are cancer survivors being followed in primary care settings.

Patient-reported symptom monitoring: using (big) data to improve supportive care at the macro-, meso-, and micro-levels

PURPOSE

This paper aims to provide a comprehensive understanding of the need for continued development of symptom monitoring (SM) implementation, utilization, and data usage at the macro-, meso-, and micro-levels.

METHODS

Discussions from a patient-reported SM workshop at the MASCC/ISSO 2022 annual meeting were analyzed using a macro-meso-micro analytical framework of cancer care delivery. The workshop categories "initiation and implementation, barriers to adoption and utilization, and data usage" were integrated for each level.

RESULTS

At the macro-level, policy development could encourage data sharing and international collaboration, including the exchange of SM methods, supportive care models, and self-management modules. At the meso-level, institutions should adjust clinical workflow and service delivery and promote a thorough technical and clinical integration of SM. At the micro-level, SM should be individualized, with timely feedback for patients, and should foster trust and understanding of AI decision support tools amongst clinicians to improve supportive care.

CONCLUSIONS

The workshop reached a consensus among international experts on providing guidance on SM implementation, utilization, and (big) data usage pathways in cancer survivors across the cancer continuum and on macro-meso-micro levels.

Combined Expert and User-Driven Usability Assessment of Trauma Decision Support Systems Improves User-Centered Design

BACKGROUND

Trauma clinical decision support systems improve adherence with evidence-based practice but suffer from poor usability and the lack of a user-centered design. The objective of this study was to compare the effectiveness of user and expert-driven usability testing methods to detect usability issues in a rib fracture clinical decision support system and identify guiding principles for trauma clinical decision support systems.

METHODS

A user-driven and expert-driven usability investigation was conducted using a clinical decision support system developed for patients with rib fractures. The user-driven usability evaluation was as follows: 10 clinicians were selected for simulation-based usability testing using snowball sampling, and each clinician completed 3 simulations using a video-conferencing platform. End-users participated in a novel team-based approach that simulated realistic clinical workflows. The expert-driven heuristic evaluation was as follows: 2 usability experts conducted a heuristic evaluation of the clinical decision support system using 10 common usability heuristics. Usability issues were identified, cataloged, and ranked for severity using a 4-level ordinal scale. Thematic analysis was utilized to categorize the identified usability issues.

RESULTS

Seventy-nine usability issues were identified; 63% were identified by experts and 48% by end-users. Notably, 58% of severe usability issues were identified by experts alone. Only 11% of issues were identified by both methods. Five themes were identified that could guide the design of clinical decision support systems-transparency, functionality and integration into workflow, automated and noninterruptive, flexibility, and layout and appearance. Themes were preferentially identified by different methods.

CONCLUSION

We found that a dual-method usability evaluation involving usability experts and end-users drastically improved detection of usability issues over single-method alone. We identified 5 themes to guide trauma clinical decision support system design. Performing usability testing via a remote video-conferencing platform facilitated multi-site involvement despite a global pandemic.

A systematic review of technologies and standards used in the development of rule-based clinical decision support systems

A Clinical Decision Support System (CDSS) is a technology platform that uses medical knowledge with clinical data to provide customised advice for an individual patient's care. CDSSs use rules to encapsulate expert knowledge and rules engines to infer logic by evaluating rules according to a patient's specific information and related medical facts. However, CDSSs are by nature complex with a plethora of different technologies, standards and methods used to implement them and it can be difficult for practitioners to determine an appropriate solution for a specific scenario. This study's main goal is to provide a better understanding of different technical aspects of a CDSS, identify gaps in CDSS development and ultimately provide some guidelines to assist their translation into practice. We focus on issues related to knowledge representation including use of clinical ontologies, interoperability with EHRs, technology standards, CDSS architecture and mobile/cloud access.

This study performs a systematic literature review of rule-based CDSSs that discuss the underlying technologies used and have evaluated clinical outcomes. From a search that yielded an initial set of 1731 papers, only 15 included an evaluation of clinical outcomes. This study has found that a large majority of papers did not include any form of evaluation and, for many that did include an evaluation, the methodology was not sufficiently rigorous to provide statistically significant results. From the 15 papers shortlisted, there were no RCT or quasi-experimental studies, only 6 used ontologies to represent domain knowledge, only 2 integrated with an EHR system, only 5 supported mobile use and only 3 used recognised healthcare technology standards (and all these were HL7 standards). Based on these findings, the paper provides some recommendations for future CDSS development.

Clinical Decision Support for Symptom Management in Lung Cancer Patients: A Group RCT

CONTEXT

Clinical guidelines are available to enhance symptom management during cancer treatment but often are not used in the practice setting. Clinical decision support can facilitate the implementation and adherence to clinical guidelines. and improve the quality of cancer care.

OBJECTIVES

Clinical decision support offers an innovative approach to integrate guideline-based symptom management into oncology care. This study evaluated the effect of clinical decision support-based recommendations on clinical management of symptoms and health-related quality of life (HR-QOL) among outpatients with lung cancer.

METHODS

Twenty providers and 179 patients were allotted in group randomization to attention control (AC) or Symptom Assessment and Management Intervention (SAMI) arms. SAMI entailed patient-report of symptoms and delivery of recommendations to manage pain, fatigue, dyspnea, depression, and anxiety; AC entailed symptom reporting prior to the visit. Outcomes were collected at baseline, two, four and six-months. Adherence to recommendations was assessed through masked chart review. HR-QOL was measured by the Functional Assessment of Cancer Therapy-Lung questionnaire. Descriptive statistics with linear and logistic regression accounting for the clustering structure of the design and a modified chi-square test were used for analyses.

RESULTS

Median age of patients was 63 years, 58% female, 88% white, and 32% ≤high school education. Significant differences in clinical management were evident in SAMI vs. AC for all target symptoms that passed threshold. Patients in SAMI were more likely to receive sustained-release opioids for constant pain, adjuvant medications for neuropathic pain, opioids for dyspnea, stimulants for fatigue and mental health referrals for anxiety. However, there were no statistically significant differences in HR-QOL at any time point.

CONCLUSION

SAMI improved clinical management for all target symptoms but did not improve patient outcomes. A larger study is warranted to evaluate effectiveness.

Clinical trial cohort selection based on multi-level rule-based natural language processing system

OBJECTIVE

Identifying patients who meet selection criteria for clinical trials is typically challenging and time-consuming. In this article, we describe our clinical natural language processing (NLP) system to automatically assess patients' eligibility based on their longitudinal medical records. This work was part of the 2018 National NLP Clinical Challenges (n2c2) Shared-Task and Workshop on Cohort Selection for Clinical Trials.

MATERIALS AND METHODS

The authors developed an integrated rule-based clinical NLP system which employs a generic rule-based framework plugged in with lexical-, syntactic- and meta-level, task-specific knowledge inputs. In addition, the authors also implemented and evaluated a general clinical NLP (cNLP) system which is built with the Unified Medical Language System and Unstructured Information Management Architecture.

RESULTS AND DISCUSSION

The systems were evaluated as part of the 2018 n2c2-1 challenge, and authors' rule-based system obtained an F-measure of 0.9028, ranking fourth at the challenge and had less than 1% difference from the best system. While the general cNLP system didn't achieve performance as good as the rule-based system, it did establish its own advantages and potential in extracting clinical concepts.

CONCLUSION

Our results indicate that a well-designed rule-based clinical NLP system is capable of achieving good performance on cohort selection even with a small training data set. In addition, the investigation of a Unified Medical Language System-based general cNLP system suggests that a hybrid system combining these 2 approaches is promising to surpass the state-of-the-art performance.

Self-reported activities of daily living, health and quality of life among older adults in South Africa and Uganda: a cross sectional study

BACKGROUND

Difficulties in performing the activities of daily living (ADL) are common among middle-aged and older adults. Inability to perform the basic tasks as well as increased healthcare expenditure and dependence on care can have debilitating effects on health and quality of life. The objective of this study was to examine the relationship between self-reported difficulty in activities of daily living (ADL), health and quality of life among community-dwelling, older population in South Africa and Uganda.

METHODS

We analyzed cross-sectional data on 1495 men and women from South Africa (n = 514) and Uganda (n = 981) which were extracted from the SAGE Well-Being of Older People Study (WOPS 2011-13). Outcome variables were self-reported health and quality of life (QoL). Difficulty in ADL was assessed by self-reported answers on 12 different questions covering various physical and cognitive aspects. The association between self-reported health and quality of life with ADL difficulties was calculated by using multivariable logistic regression models.

RESULTS

Overall percentage of good health and good quality of life was 40.4% and 20%, respectively. The percentage of respondents who had 1-3, 3-6, > 6 ADL difficulties were 42.4%7, 30.97% and 14.85%, respectively. In South Africa, having > 6 ADL difficulties was associated with lower odds of good health among men [Odds ratio = 0.331, 95%CI = 0.245,0.448] and quality of life among men [Odds ratio = 0.609, 95%CI = 0.424,0.874] and women [Odds ratio = 0.129, 95%CI = 0.0697,0.240]. In Uganda, having > 6 ADL difficulties was associated lower odds of good health [Odds ratio = 0.364, 95%CI = 0.159,0.835] and quality of life [Odds ratio = 0.584, 95%CI = 0.357,0.954].

CONCLUSION

This study concludes that difficulty in ADL has a significant negative association with health and quality of life among community-dwelling older population (> 50 years) in South Africa and Uganda. The sex differences support previous findings on differential health outcomes among men and women, and underline the importance of designing sex-specific health intervention programs.

Palliative Care Skills and New Resources for Oncology Practices: Meeting the Palliative Care Needs of Patients With Cancer and Their Families

In its 2017 guideline, ASCO challenged members to integrate palliative care into their standard oncology practices for all patients, throughout their cancer trajectory. However, partnering with palliative care experts alone will not be enough to achieve that goal; there are too few experts now, and there will not be enough in the future to meet the needs of patients with cancer and their families. Other strategies are required. Oncologists can develop new communication skills that were not included in their fellowship curricula, skills that integrate into their visits the subjects that palliative care clinicians discuss routinely with patients referred to them. In this review, Dr. Back offers three questions matched to communication skills that can help oncologists explore key areas: (1) What is happening? (2) How do you (and I) feel? and (3) What is important? and discusses the "REMAP" strategy for making urgent medical decisions. Dr. Friedman reviews the impact of community-based palliative care resources and telehealth on care quality, patient centeredness, and reducing costs. Community-based palliative care services and telehealth are available to patients and families at home, during active treatment. Dr. Abrahm reviews how patient-reported outcomes (PROs) completed at home can enhance patients' symptom control, quality of life, and toleration of treatment and decrease unplanned emergency visits by alerting clinicians to patients' severe symptoms, making appropriate referrals, or suggesting patients contact their oncology team. She also provides an update on using PROs and natural language processing with clinical decision support to create sophisticated palliative care assessments and treatment options in the electronic health record during patients' office visits.

Identifying Lung Cancer Risk Factors in the Elderly Using Deep Neural Networks: Quantitative Analysis of Web-Based Survey Data

BACKGROUND

Lung cancer is one of the most dangerous malignant tumors, with the fastest-growing morbidity and mortality, especially in the elderly. With a rapid growth of the elderly population in recent years, lung cancer prevention and control are increasingly of fundamental importance, but are complicated by the fact that the pathogenesis of lung cancer is a complex process involving a variety of risk factors.

OBJECTIVE

This study aimed at identifying key risk factors of lung cancer incidence in the elderly and quantitatively analyzing these risk factors' degree of influence using a deep learning method.

METHODS

Based on Web-based survey data, we integrated multidisciplinary risk factors, including behavioral risk factors, disease history factors, environmental factors, and demographic factors, and then preprocessed these integrated data. We trained deep neural network models in a stratified elderly population. We then extracted risk factors of lung cancer in the elderly and conducted quantitative analyses of the degree of influence using the deep neural network models.

RESULTS

The proposed model quantitatively identified risk factors based on 235,673 adults. The proposed deep neural network models of 4 groups (age ≥65 years, women ≥65 years old, men ≥65 years old, and the whole population) achieved good performance in identifying lung cancer risk factors, with accuracy ranging from 0.927 (95% CI 0.223-0.525; P=.002) to 0.962 (95% CI 0.530-0.751; P=.002) and the area under curve ranging from 0.913 (95% CI 0.564-0.803) to 0.931(95% CI 0.499-0.593). Smoking frequency was the leading risk factor for lung cancer in men 65 years and older. Time since quitting and smoking at least 100 cigarettes in their lifetime were the main risk factors for lung cancer in women 65 years and older. Men 65 years and older had the highest lung cancer incidence among the stratified groups, particularly non-small cell lung cancer incidence. Lung cancer incidence decreased more obviously in men than in women with smoking rate decline.

CONCLUSIONS

This study demonstrated a quantitative method to identify risk factors of lung cancer in the elderly. The proposed models provided intervention indicators to prevent lung cancer, especially in older men. This approach might be used as a risk factor identification tool to apply in other cancers and help physicians make decisions on cancer prevention.

Medical knowledge infused convolutional neural networks for cohort selection in clinical trials

OBJECTIVE

In this era of digitized health records, there has been a marked interest in using de-identified patient records for conducting various health related surveys. To assist in this research effort, we developed a novel clinical data representation model entitled medical knowledge-infused convolutional neural network (MKCNN), which is used for learning the clinical trial criteria eligibility status of patients to participate in cohort studies.

MATERIALS AND METHODS

In this study, we propose a clinical text representation infused with medical knowledge (MK). First, we isolate the noise from the relevant data using a medically relevant description extractor; then we utilize log-likelihood ratio based weights from selected sentences to highlight "met" and "not-met" knowledge-infused representations in bichannel setting for each instance. The combined medical knowledge-infused representation (MK) from these modules helps identify significant clinical criteria semantics, which in turn renders effective learning when used with a convolutional neural network architecture.

RESULTS

MKCNN outperforms other Medical Knowledge (MK) relevant learning architectures by approximately 3%; notably SVM and XGBoost implementations developed in this study. MKCNN scored 86.1% on F1metric, a gain of 6% above the average performance assessed from the submissions for n2c2 task. Although pattern/rule-based methods show a higher average performance for the n2c2 clinical data set, MKCNN significantly improves performance of machine learning implementations for clinical datasets.

CONCLUSION

MKCNN scored 86.1% on the F1 score metric. In contrast to many of the rule-based systems introduced during the n2c2 challenge workshop, our system presents a model that heavily draws on machine-based learning. In addition, the MK representations add more value to clinical comprehension and interpretation of natural texts.

Changing functional status within 6 months posttreatment is prognostic of overall survival in patients with head and neck cancer: NRG Oncology Study

BACKGROUND

Is posttreatment functional status prognostic of overall survival in patients with head and neck cancer (HNC).

METHODS

In an HNC clinical trial, 495 patients had two posttreatment functional assessments measuring diet, public eating, and speech within 6 months. Patients were grouped by impairment (highly, moderately, modestly, or not impaired) and determined if they improved, declined, or did not change from the first assessment to the second. Multivariable Cox models estimated overall mortality.

RESULTS

Across all three scales, the change in posttreatment patient function strongly predicted overall survival. In diet, patients who declined to highly impaired had three times the mortality of patients who were not impaired at both assessments (hazard ratio [HR] = 3.60; 95% confidence interval, 2.02-6.42). For patients improving from highly impaired, mortality was statistically similar to patients with no impairment (HR = 1.38; 95% CI, 0.82-2.31).

CONCLUSIONS

Posttreatment functional status is a strong prognostic marker of survival in patients with HNC.

Nurse-Delivered Symptom Assessment for Individuals With Advanced Lung Cancer

OBJECTIVES

To assess an intervention derived from self-regulation theory (SRT) to promote well-being for individuals with advanced lung cancer.

SAMPLE & SETTING

45 adults with advanced lung cancer who were receiving chemotherapy at an ambulatory cancer center.

METHODS & VARIABLES

Participants were randomized to the intervention group or usual care control group. Feasibility assessment focused on recruitment, retention, design, methods, and fidelity. Outcome measures of quality of life, symptoms, and distress were collected at four time points. The main research variables were symptoms, quality of life, and distress.

RESULTS

The participation rate was 79%, and the retention rate was 62%. Participant loss was most often because of progressive disease and occurred early in the study. High fidelity was noted for delivery of the intervention as planned and outcome data collection by telephone. The mean number of interventions delivered was 5.5 of a planned 8. A high level of acceptability was reported for participants completing the intervention.

IMPLICATIONS FOR NURSING

Although delivering the SRT-derived intervention with fidelity was possible, feasibility findings do not warrant intervention replication in this population.

Algorithm-based decision support for symptom self-management among adults with Cancer: results of usability testing

BACKGROUND

It is essential that cancer patients understand anticipated symptoms, how to self-manage these symptoms, and when to call their clinicians. However, patients are often ill-prepared to manage symptoms at home. Clinical decision support (CDS) is a potentially innovative way to provide information to patients where and when they need it. The purpose of this project was to design and evaluate a simulated model of an algorithm-based CDS program for self-management of cancer symptoms.

METHODS

This study consisted of three phases; development of computable algorithms for self-management of cancer symptoms using a modified ADAPTE process, evaluation of a simulated model of the CDS program, and identification of design objectives and lessons learned from the evaluation of patient-centered CDS. In phase 1, algorithms for pain, constipation and nausea/vomiting were developed by an expert panel. In phase 2, we conducted usability testing of a simulated symptom assessment and management intervention for self-care (SAMI-Self-Care) CDS program involving focus groups, interviews and surveys with cancer patients, their caregivers and clinicians. The Acceptability E-scale measured acceptability of the program. In phase 3, we developed design objectives and identified barriers to uptake of patient-centered CDS based on the data gathered from stakeholders.

RESULTS

In phase 1, algorithms were reviewed and approved through a consensus meeting and majority vote. In phase 2, 24 patients & caregivers and 13 clinicians participated in the formative evaluation. Iterative changes were made in a simulated SAMI-Self-Care CDS program. Acceptability scores were high among patients, caregivers and clinicians. In phase 3, we formulated CDS design objectives, which included: 1) ensure patient safety, 2) communicate clinical concepts effectively, 3) promote communication with clinicians, 4) support patient activation, and 5) facilitate navigation and use. We identified patient barriers and clinician concerns to using CDS for symptom self-management, which were consistent with the chronic care model, a theoretical framework used to enhance patient-clinician communication and patient self-management.

CONCLUSION

Patient safety and tool navigation were critical features of CDS for patient self-management. Insights gleaned from this study may be used to inform the development of CDS resources for symptom self-management in patients with other chronic conditions.

Agile Acceptance Test-Driven Development of Clinical Decision Support Advisories: Feasibility of Using Open Source Software

Background

Moving to electronic health records (EHRs) confers substantial benefits but risks unintended consequences. Modern EHRs consist of complex software code with extensive local configurability options, which can introduce defects. Defects in clinical decision support (CDS) tools are surprisingly common. Feasible approaches to prevent and detect defects in EHR configuration, including CDS tools, are needed. In complex software systems, use of test–driven development and automated regression testing promotes reliability. Test–driven development encourages modular, testable design and expanding regression test coverage. Automated regression test suites improve software quality, providing a “safety net” for future software modifications. Each automated acceptance test serves multiple purposes, as requirements (prior to build), acceptance testing (on completion of build), regression testing (once live), and “living” design documentation. Rapid-cycle development or “agile” methods are being successfully applied to CDS development. The agile practice of automated test–driven development is not widely adopted, perhaps because most EHR software code is vendor-developed. However, key CDS advisory configuration design decisions and rules stored in the EHR may prove amenable to automated testing as “executable requirements.”

Objective

We aimed to establish feasibility of acceptance test–driven development of clinical decision support advisories in a commonly used EHR, using an open source automated acceptance testing framework (FitNesse).

Methods

Acceptance tests were initially constructed as spreadsheet tables to facilitate clinical review. Each table specified one aspect of the CDS advisory’s expected behavior. Table contents were then imported into a test suite in FitNesse, which queried the EHR database to automate testing. Tests and corresponding CDS configuration were migrated together from the development environment to production, with tests becoming part of the production regression test suite.

Results

We used test–driven development to construct a new CDS tool advising Emergency Department nurses to perform a swallowing assessment prior to administering oral medication to a patient with suspected stroke. Test tables specified desired behavior for (1) applicable clinical settings, (2) triggering action, (3) rule logic, (4) user interface, and (5) system actions in response to user input. Automated test suite results for the “executable requirements” are shown prior to building the CDS alert, during build, and after successful build.

Conclusions

Automated acceptance test–driven development and continuous regression testing of CDS configuration in a commercial EHR proves feasible with open source software. Automated test–driven development offers one potential contribution to achieving high-reliability EHR configuration. Vetting acceptance tests with clinicians elicits their input on crucial configuration details early during initial CDS design and iteratively during rapid-cycle optimization.

Identifying Future Drinkers: Behavioral Analysis of Monkeys Initiating Drinking to Intoxication is Predictive of Future Drinking Classification

BACKGROUND

The Monkey Alcohol Tissue Research Resource (MATRR) is a repository and analytics platform for detailed data derived from well-documented nonhuman primate (NHP) alcohol self-administration studies. This macaque model has demonstrated categorical drinking norms reflective of human drinking populations, resulting in consumption pattern classifications of very heavy drinking (VHD), heavy drinking (HD), binge drinking (BD), and low drinking (LD) individuals. Here, we expand on previous findings that suggest ethanol drinking patterns during initial drinking to intoxication can reliably predict future drinking category assignment.

METHODS

The classification strategy uses a machine-learning approach to examine an extensive set of daily drinking attributes during 90 sessions of induction across 7 cohorts of 5 to 8 monkeys for a total of 50 animals. A Random Forest classifier is employed to accurately predict categorical drinking after 12 months of self-administration.

RESULTS

Predictive outcome accuracy is approximately 78% when classes are aggregated into 2 groups, "LD and BD" and "HD and VHD." A subsequent 2-step classification model distinguishes individual LD and BD categories with 90% accuracy and between HD and VHD categories with 95% accuracy. Average 4-category classification accuracy is 74%, and provides putative distinguishing behavioral characteristics between groupings.

CONCLUSIONS

We demonstrate that data derived from the induction phase of this ethanol self-administration protocol have significant predictive power for future ethanol consumption patterns. Importantly, numerous predictive factors are longitudinal, measuring the change of drinking patterns through 3 stages of induction. Factors during induction that predict future heavy drinkers include being younger at the time of first intoxication and developing a shorter latency to first ethanol drink. Overall, this analysis identifies predictive characteristics in future very heavy drinkers that optimize intoxication, such as having increasingly fewer bouts with more drinks. This analysis also identifies characteristic avoidance of intoxicating topographies in future low drinkers, such as increasing number of bouts and waiting longer before the first ethanol drink.