Toward personalized care for insomnia in the US Army: a machine learning model to predict response to cognitive behavioral therapy for insomnia.

STUDY OBJECTIVES: The standard of care for military personnel with insomnia is cognitive behavioral therapy for insomnia (CBT-I). However, only a minority seeking insomnia treatment receive CBT-I, and little reliable guidance exists to identify those most likely to respond. As a step toward personalized care, we present results of a machine learning (ML) model to predict CBT-I response. METHODS: Administrative data were examined for n=1,449 nondeployed US Army soldiers treated for insomnia with CBT-I who had moderate-severe baseline Insomnia Severity Index (ISI) scores and completed one or more follow-up ISIs 6-12 weeks after baseline. An ensemble ML model was developed in a 70% training sample to predict clinically significant ISI improvement (reduction of at least two standard deviations on the baseline ISI distribution). Predictors included a wide range of military administrative and baseline clinical variables. Model accuracy was evaluated in the remaining 30% test sample. RESULTS: 19.8% of patients had clinically significant ISI improvement. Model AU-ROC (SE) was 0.60 (0.03). The 20% of test sample patients with highest probabilities of improvement were twice as likely to have clinically significant improvement as the remaining 80% (36.5% versus 15.7%; χ21=9.2, p=.002). Nearly 85% of prediction accuracy was due to ten variables, the most important of which were baseline insomnia severity and baseline suicidal ideation. CONCLUSIONS: Pending replication, the model could be used as part of a patient-centered decision-making process for insomnia treatment. Parallel models will be needed for alternative treatments before such a system is of optimal value.

Predicting Homelessness Among Transitioning U.S. Army Soldiers.

INTRODUCTION: This study develops a practical method to triage Army transitioning service members (TSMs) at highest risk of homelessness to target a preventive intervention. METHODS: The sample included 4,790 soldiers from the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS) who participated in 1 of 3 Army STARRS 2011-2014 baseline surveys followed by the third wave of the STARRS-LS online panel surveys (2020-2022). Two machine learning models were trained: a Stage-1 model that used administrative predictors and geospatial data available for all TSMs at discharge to identify high-risk TSMs for initial outreach; and a Stage-2 model estimated in the high-risk subsample that used self-reported survey data to help determine highest risk based on additional information collected from high-risk TSMs once they are contacted. The outcome in both models was homelessness within 12 months after leaving active service. RESULTS: Twelve-month prevalence of post-transition homelessness was 5.0% (SE=0.5). The Stage-1 model identified 30% of high-risk TSMs who accounted for 52% of homelessness. The Stage-2 model identified 10% of all TSMs (i.e., 33% of high-risk TSMs) who accounted for 35% of all homelessness (i.e., 63% of the homeless among high-risk TSMs). CONCLUSIONS: Machine learning can help target outreach and assessment of TSMs for homeless prevention interventions.

The impact of COVID-19 vaccine reactions on secondary vaccine hesitancy.

BACKGROUND: Primary and booster vaccinations are critical for mitigating COVID-19 transmission, morbidity, and mortality. Future booster vaccine campaigns rely on an increased understanding of vaccine hesitancy. OBJECTIVE: To evaluate self-reported allergic and skin vaccine reactions as factors potentially associated with vaccine hesitancy in a nationwide vaccine allergy registry. METHODS: Responses to survey questions concerning COVID-19 vaccine perceptions, coded from free text by 2 independent reviewers. Multivariable logistic regression models were used to determine the association between changed negative perception and respondent demographics, vaccination history, and reaction characteristics. RESULTS: A total of 993 individuals (median of 46 years [IQR, 36-59], 88% female, 82% White) self-reported reactions to COVID-19 vaccination. Reactions included the following: delayed large local skin reaction (40%), hives/urticaria (32%), immediate large local skin reaction (3%), swelling (3%), anaphylaxis (2%), and other or unspecified (20%). Most respondents were initially unconcerned about the safety of COVID-19 vaccines (56%). After reactions, 401 of 993 (40%) report negative change in perception of vaccination, with more than half of these respondents (n = 211, 53%) citing their reasoning as a negative experience with adverse effects. Of 102 individuals asked about future vaccination, 79 (77%) indicated that they were unlikely or very unlikely to receive future COVID-19 vaccinations. Increased negative perception after reaction was associated with younger age, later COVID-19 vaccination dose number, and reaction type. CONCLUSION: Our findings reveal that an individual's experience with allergic or cutaneous adverse effects after COVID-19 vaccination affects attitudes and decision-making regarding future vaccination, even in initially non-hesitant individuals. Further investigation of secondary vaccine hesitancy is necessary for adapting public health messaging to this important population.

NHE3 inhibitor tenapanor maintains intestinal barrier function, decreases visceral hypersensitivity, and attenuates TRPV1 signaling in colonic sensory neurons.

The pathogenesis of irritable bowel syndrome (IBS) is multifactorial, characterized in part by increased intestinal permeability, and visceral hypersensitivity. Increased permeability is associated with IBS severity and abdominal pain. Tenapanor is FDA-approved for the treatment of IBS with constipation (IBS-C) and has demonstrated improvements in bowel motility and a reduction in IBS-related pain; however, the mechanism by which tenapanor mediates these functions remains unclear. Here, the effects of tenapanor on colonic pain signaling and intestinal permeability were assessed through behavioral, electrophysiological, and cell culture experiments. Intestinal motility studies in rats and humans demonstrated that tenapanor increased luminal sodium and water retention and gastrointestinal transit versus placebo. A significantly reduced visceral motor reflex (VMR) to colonic distension was observed with tenapanor treatment versus vehicle in two rat models of visceral hypersensitivity (neonatal acetic acid sensitization and partial restraint stress; both P < 0.05), returning VMR responses to that of nonsensitized controls. Whole cell voltage patch-clamp recordings of retrogradely labeled colonic dorsal root ganglia (DRG) neurons from sensitized rats found that tenapanor significantly reduced DRG neuron hyperexcitability to capsaicin versus vehicle (P < 0.05), an effect not mediated by epithelial cell secretions. Tenapanor also attenuated increases in intestinal permeability in human colon monolayer cultures caused by incubation with proinflammatory cytokines (P < 0.001) or fecal supernatants from patients with IBS-C (P < 0.005). These results support a model in which tenapanor reduces IBS-related pain by strengthening the intestinal barrier, thereby decreasing permeability to macromolecules and antigens and reducing DRG-mediated pain signaling.NEW & NOTEWORTHY A series of nonclinical experiments support the theory that tenapanor inhibits IBS-C-related pain by strengthening the intestinal barrier. Tenapanor treatment reduced visceral motor responses to nonsensitized levels in two rat models of hypersensitivity and reduced responses to capsaicin in sensitized colonic nociceptive dorsal root ganglia neurons. Intestinal permeability experiments in human colon monolayer cultures found that tenapanor attenuates increases in permeability induced by either inflammatory cytokines or fecal supernatants from patients with IBS-C.

Influence of Metal Identity and Complex Nuclearity in Kumada Cross-Coupling Polymerizations with a Pyridine Diimine-Based Ligand Scaffold.

Cross-coupling polymerizations have fundamentally changed the field of conjugated polymers (CPs) by expanding the scope of accessible materials. Despite the prevalence of cross-coupling in CP synthesis, almost all polymerizations rely on mononuclear Ni or Pd catalysts. Here, we report a systematic exploration of mono- and dinuclear Fe and Ni precatalysts with a pyridine diimine ligand scaffold for Kumada cross-coupling polymerization of a donor thiophene and an acceptor benzotriazole monomers. We observe that variation of the metal identity from Ni to Fe produces contrasting polymerization mechanisms, while complex nuclearity has a minimal impact on reactivity. Specifically, Fe complexes appear to catalyze step-growth Kumada polymerizations and can readily access both Csp2-Csp3 and Csp2-Csp2 cross-couplings, while Ni complexes catalyze chain-growth polymerizations and predominantly Csp2-Csp2 cross-couplings. Thus, our work sheds light on important design parameters for transition metal complexes used in cross-coupling polymerizations, demonstrates the viability of iron catalysis in Kumada polymerization, and opens the door to novel polymer compositions.

Machine learning-based prediction of low-value care for hospitalized patients.

Objective: Low-value care (i.e., costly health care treatments that provide little or no benefit) is an ongoing problem in United States hospitals. Traditional strategies for reducing low-value care are only moderately successful. Informed by behavioral science principles, we sought to use machine learning to inform a targeted prompting system that suggests preferred alternative treatments at the point of care but before clinicians have made a decision. Methods: We used intravenous administration of albumin for fluid resuscitation in intensive care unit (ICU) patients as an exemplar of low-value care practice, identified using the electronic health record of a multi-hospital health system. We divided all ICU episodes into 4-h periods and defined a set of relevant clinical features at the period level. We then developed two machine learning models: a single-stage model that directly predicts if a patient will receive albumin in the next period; and a two-stage model that first predicts if any resuscitation fluid will be administered and then predicts albumin only among the patients with a high probability of fluid use. Results: We examined 87,489 ICU episodes divided into approximately 1.5 million 4-h periods. The area under the receiver operating characteristic curve was 0.86 for both prediction models. The positive predictive value was 0.21 (95% confidence interval: 0.20, 0.23) for the single-stage model and 0.22 (0.20, 0.23) for the two-stage model. Applying either model in a targeted prompting system could prevent 10% of albumin administrations, with an attending physician receiving one prompt every 4.2 days of ICU service. Conclusion: Prediction of low-value care is feasible and could enable a point-of-care, targeted prompting system that offers suggestions ahead of the moment of need before clinicians have already decided. A two-stage approach does not improve performance but does interject new levers for the calibration of such a system.

Smoking status among cancer patients by specialty: A U.S. nationwide representative analysis.

BACKGROUND: Persistence in tobacco use among cancer survivors has been associated with a multitude of clinicodemographic factors. However, there is a paucity of understanding regarding the role the healthcare professional's specialty plays in tobacco cessation in tobacco-related cancer survivors. METHODS: We conducted a cross-sectional analysis of data from cancer survivors with a smoking history using the Behavioral Risk Factor Surveillance System (BRFSS) database to examine differences in the proportion of patients continuing tobacco use among patients with a diagnosis of cancer segregated by cancer site specialty over the 2016-2020 period. We accounted for complex survey design and used sampling weights to obtain a nationwide representative sample. We employed modified Poisson regression adjusting for age, gender, education, income, race, marital status, and medical specialty. RESULTS: We analyzed 19,855 cancer survivors with a current or past history of tobacco use, of whom 5222 (26,3%) self-reported to be current smokers. Patients with urological and gynecological tobacco-related malignancies had a higher relative risk (RR) of being current smokers with a RR of 1.30 (95% confidence interval, 1.12-1.51) and 1.25 (95% confidence interval, 1.12-1.39) respectively. Malignant Hematology had the lowest RR of smoking status among all other specialties RR 0.85 (95% confidence interval, 0.59-1.21). CONCLUSIONS: Continuing smoking rates among tobacco-related cancer survivors were different between specialties. One in four cancer survivors were current smokers; this emphasizes health professionals' paramount role in tobacco cessation counseling.

Hierarchical temporal prediction captures motion processing along the visual pathway.

Visual neurons respond selectively to features that become increasingly complex from the eyes to the cortex. Retinal neurons prefer flashing spots of light, primary visual cortical (V1) neurons prefer moving bars, and those in higher cortical areas favor complex features like moving textures. Previously, we showed that V1 simple cell tuning can be accounted for by a basic model implementing temporal prediction - representing features that predict future sensory input from past input (Singer et al., 2018). Here, we show that hierarchical application of temporal prediction can capture how tuning properties change across at least two levels of the visual system. This suggests that the brain does not efficiently represent all incoming information; instead, it selectively represents sensory inputs that help in predicting the future. When applied hierarchically, temporal prediction extracts time-varying features that depend on increasingly high-level statistics of the sensory input.

Evidence of personality-dependent plasticity in dairy calf movement behaviours derived from automated data collection.

Individual consistency in behaviour, known as animal personality, and behavioural plasticity in response to environmental changes are important factors shaping individual behaviour. Correlations between them, called personality-dependent plasticity, indicate that personality can affect individual reactions to the environment. In farm animals this could impact the response to management changes or stressors but has not yet been investigated. Here we use ultra-wideband location sensors to measure personality and plasticity in the movement of 90 dairy calves for up to 56 days starting in small pair-housing enclosures, and subsequently moved to larger social housings. For the first time calves were shown to differ in personality and plasticity of movement when changing housing. There were significant correlations between personality and plasticity for distance travelled (0.57), meaning that individuals that travelled the furthest in the pair housing increased their movement more in the social groups, and for residence time (- 0.65) as those that stayed in the same area more decreased more with the change in housing, demonstrating personality-dependent plasticity. Additionally, calves conformed to their pen-mate's behaviour in pairs, but this did not continue in the groups. Therefore, personality, plasticity and social effects impact how farm animals respond to changes and can inform management decisions.

A practical risk calculator for suicidal behavior among transitioning U.S. Army soldiers: results from the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS).

BACKGROUND: Risk of suicide-related behaviors is elevated among military personnel transitioning to civilian life. An earlier report showed that high-risk U.S. Army soldiers could be identified shortly before this transition with a machine learning model that included predictors from administrative systems, self-report surveys, and geospatial data. Based on this result, a Veterans Affairs and Army initiative was launched to evaluate a suicide-prevention intervention for high-risk transitioning soldiers. To make targeting practical, though, a streamlined model and risk calculator were needed that used only a short series of self-report survey questions. METHODS: We revised the original model in a sample of n = 8335 observations from the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS) who participated in one of three Army STARRS 2011-2014 baseline surveys while in service and in one or more subsequent panel surveys (LS1: 2016-2018, LS2: 2018-2019) after leaving service. We trained ensemble machine learning models with constrained numbers of item-level survey predictors in a 70% training sample. The outcome was self-reported post-transition suicide attempts (SA). The models were validated in the 30% test sample. RESULTS: Twelve-month post-transition SA prevalence was 1.0% (s.e. = 0.1). The best constrained model, with only 17 predictors, had a test sample ROC-AUC of 0.85 (s.e. = 0.03). The 10-30% of respondents with the highest predicted risk included 44.9-92.5% of 12-month SAs. CONCLUSIONS: An accurate SA risk calculator based on a short self-report survey can target transitioning soldiers shortly before leaving service for intervention to prevent post-transition SA.

The Role of Data Science in Closing the Implementation Gap.

Data science has the potential to greatly enhance efforts to translate evidence into practice in critical care. The intensive care unit is a data-rich environment enabling insight into both patient-level care patterns and clinician-level treatment patterns. By applying artificial intelligence to these novel data sources, implementation strategies can be tailored to individual patients, individual clinicians, and individual situations, revealing when evidence-based practices are missed and facilitating context-sensitive clinical decision support. To achieve these goals, technology developers should work closely with clinicians to create unbiased applications that are integrated into the clinical workflow.

Designing and Implementing "Living and Breathing" Clinical Trials: An Overview and Lessons Learned from the COVID-19 Pandemic.

The practice of medicine is characterized by uncertainty, and the findings of randomized clinical trials (RCTs) are meant to help curb that uncertainty. Traditional RCTs, however, have many limitations. To overcome some of these limitations, new trial paradigms rooted in the origins of evidence-based medicine are beginning to disrupt the traditional mold. These new designs recognize uncertainty permeates medical decision making and aim to capitalize on modern health system infrastructure to integrate investigation as a component of care delivery. This article provides an overview of "living, breathing" trials, including current state, anticipated developments, and areas of controversy.

A voice-based digital assistant for intelligent prompting of evidence-based practices during ICU rounds.

OBJECTIVE: To evaluate the technical feasibility and potential value of a digital assistant that prompts intensive care unit (ICU) rounding teams to use evidence-based practices based on analysis of their real-time discussions. METHODS: We evaluated a novel voice-based digital assistant which audio records and processes the ICU care team's rounding discussions to determine which evidence-based practices are applicable to the patient but have yet to be addressed by the team. The system would then prompt the team to consider indicated but not yet delivered practices, thereby reducing cognitive burden compared to traditional rigid rounding checklists. In a retrospective analysis, we applied automatic transcription, natural language processing, and a rule-based expert system to generate personalized prompts for each patient in 106 audio-recorded ICU rounding discussions. To assess technical feasibility, we compared the system's prompts to those created by experienced critical care nurses who directly observed rounds. To assess potential value, we also compared the system's prompts to a hypothetical paper checklist containing all evidence-based practices. RESULTS: The positive predictive value, negative predictive value, true positive rate, and true negative rate of the system's prompts were 0.45 ± 0.06, 0.83 ± 0.04, 0.68 ± 0.07, and 0.66 ± 0.04, respectively. If implemented in lieu of a paper checklist, the system would generate 56% fewer prompts per patient, with 50%±17% greater precision. CONCLUSION: A voice-based digital assistant can reduce prompts per patient compared to traditional approaches for improving evidence uptake on ICU rounds. Additional work is needed to evaluate field performance and team acceptance.

Editing of polymer backbones.

Polymers are at the epicentre of modern technological progress and the associated environmental pollution. Considerations of both polymer functionality and lifecycle are crucial in these contexts, and the polymer backbone - the core of a polymer - is at the root of these considerations. Just as the meaning of a sentence can be altered by editing its words, the function and sustainability of a polymer can also be transformed via the chemical modification of its backbone. Yet, polymer modification has primarily been focused on the polymer periphery. In this Review, we focus on the transformations of the polymer backbone by defining some concepts fundamental to this topic (for example, 'polymer backbone' and 'backbone editing') and by collecting and categorizing examples of backbone editing scattered throughout a century's worth of chemical literature, and outline critical directions for further research. In so doing, we lay the foundation for the field of polymer backbone editing and hope to accelerate its development.

Postpartum cessation of urban space use by a female baboon living at the edge of the City of Cape Town.

Species with slow life history strategies that invest in few offspring with extended parental care need to adapt their behavior to cope with anthropogenic changes that occur within their lifetime. Here we show that a female chacma baboon (Papio ursinus) that commonly ranges within urban space in the City of Cape Town, South Africa, stops using urban space after giving birth. This change of space use occurs without any significant change in daily distance traveled or social interactions that would be expected with general risk-sensitive behavior after birth. Instead, we suggest this change occurs because of the specific and greater risks the baboons experience within the urban space compared to natural space, and because leaving the troop (to enter urban space) may increase infanticide risk. This case study can inform methods used to manage the baboons' urban space use in Cape Town and provides insight into how life history events alter individuals' use of anthropogenic environments.

Effects of accelerometry-derived physical activity energy expenditure on urinary C-peptide levels in a wild primate (Papio ursinus).

Animals have finite energy reserves for growth, survival, and reproduction and must maintain a stable energy balance. Measuring energy balance in the wild, however, is beset with methodological challenges. Quantification of urinary C-peptide (uCP), a proxy for insulin secretion, has enabled researchers to non-invasively estimate energy balance, and positive relationships between uCP levels and energy intake have been documented in numerous non-human primates. Comparatively few studies show that, consistent with insulin physiology, energy expenditure also alters levels of uCP. The timescale and extent of this relationship, however, remains unclear given the reliance on crude measures of activity and inferred energy expenditure. Here, for the first time, we test for effects of accelerometer-derived Vectorial Dynamic Body Acceleration (VeDBA) - a continuous measure of physical activity energy expenditure - on urinary C-peptide (uCP) levels in n = 12 wild chacma baboons (Papio ursinus). Applying a model selection approach, we show that VeDBA summed over short timescales (30 min to 1 h) prior to urine collection was negatively associated with uCP levels. Using the acceleration-based time individuals spent 'non-stationary' (i.e. locomoting) prior to urine collection as a predictor - instead of summed VeDBA - revealed similar but less clear results. Overall, the negative relationship between VeDBA and uCP levels highlights the importance of quantifying physical activity energy expenditure when using uCP measures to estimate energy balance and has potential implications for the field of energetics accelerometry.

Toward personalized care for insomnia in the US Army: development of a machine-learning model to predict response to pharmacotherapy.

STUDY OBJECTIVES: Although many military personnel with insomnia are treated with prescription medication, little reliable guidance exists to identify patients most likely to respond. As a first step toward personalized care for insomnia, we present results of a machine-learning model to predict response to insomnia medication. METHODS: The sample comprised n = 4,738 nondeployed US Army soldiers treated with insomnia medication and followed 6-12 weeks after initiating treatment. All patients had moderate-severe baseline scores on the Insomnia Severity Index (ISI) and completed 1 or more follow-up ISIs 6-12 weeks after baseline. An ensemble machine-learning model was developed in a 70% training sample to predict clinically significant ISI improvement, defined as reduction of at least 2 standard deviations on the baseline ISI distribution. Predictors included a wide range of military administrative and baseline clinical variables. Model accuracy was evaluated in the remaining 30% test sample. RESULTS: 21.3% of patients had clinically significant ISI improvement. Model test sample area under the receiver operating characteristic curve (standard error) was 0.63 (0.02). Among the 30% of patients with the highest predicted probabilities of improvement, 32.5.% had clinically significant symptom improvement vs 16.6% in the 70% sample predicted to be least likely to improve (χ21 = 37.1, P < .001). More than 75% of prediction accuracy was due to 10 variables, the most important of which was baseline insomnia severity. CONCLUSIONS: Pending replication, the model could be used as part of a patient-centered decision-making process for insomnia treatment, but parallel models will be needed for alternative treatments before such a system is of optimal value. CITATION: Gabbay FH, Wynn GH, Georg MW, et al. Toward personalized care for insomnia in the US Army: development of a machine-learning model to predict response to pharmacotherapy. J Clin Sleep Med. 2023;19(8):1399-1410.

Quantifying allo-grooming in wild chacma baboons (Papio ursinus) using tri-axial acceleration data and machine learning.

Quantification of activity budgets is pivotal for understanding how animals respond to changes in their environment. Social grooming is a key activity that underpins various social processes with consequences for health and fitness. Traditional methods use direct (focal) observations to calculate grooming rates, providing systematic but sparse data. Accelerometers, in contrast, can quantify activity budgets continuously but have not been used to quantify social grooming. We test whether grooming can be accurately identified using machine learning (random forest model) trained on labelled acceleration data from wild chacma baboons (Papio ursinus). We successfully identified giving and receiving grooming with high precision (81% and 91%) and recall (87% and 79%). Giving grooming was associated with a distinct rhythmical signal along the surge axis. Receiving grooming had similar acceleration signals to resting, and thus was more difficult to assign. We applied our machine learning model to n = 680 collar data days from n = 12 baboons and found that grooming rates obtained from accelerometers were significantly and positively correlated with direct observation rates for giving but not receiving grooming. The ability to collect continuous grooming data in wild populations will allow researchers to re-examine and expand upon long-standing questions regarding the formation and function of grooming bonds.