Using machine learning techniques to characterize sleep-deprived driving behavior.

OBJECTIVE: Sleep deprivation is known to affect driving behavior and may lead to serious car accidents similar to the effects from e.g., alcohol. In a previous study, we have demonstrated that the use of machine learning techniques allows adequate characterization of abnormal driving behavior after alprazolam and/or alcohol intake. In the present study, we extend this approach to sleep deprivation and test the model for characterization of new interventions. We aimed to classify abnormal driving behavior after sleep deprivation, and, by using a machine learning model, we tested if this model could also pick up abnormal driving behavior resulting from other interventions. METHODS: Data were collected during a previous study, in which 24 subjects were tested after being sleep-deprived and after a well-rested night. Features were calculated from several driving parameters, such as the lateral position, speed of the car, and steering speed. In the present study, we used a gradient boosting model to classify sleep deprivation. The model was validated using a 5-fold cross validation technique. Next, probability scores were used to identify the overlap of driving behavior after sleep deprivation and driving behavior affected by other interventions. In the current study alprazolam, alcohol, and placebo are used to test/validate the approach. RESULTS: The sleep deprivation model detected abnormal driving behavior in the simulator with an accuracy of 77 ± 9%. Abnormal driving behavior after alprazolam, and to a lesser extent also after alcohol intake, showed remarkably similar characteristics to sleep deprivation. The average probability score for alprazolam and alcohol measurements was 0.79, for alcohol 0.63, and for placebo only 0.27 and 0.30, matching the expected relative drowsiness. CONCLUSION: We developed a model detecting abnormal driving induced by sleep deprivation. The model shows the similarities in driving characteristics between sleep deprivation and other interventions, i.e., alcohol and alprazolam. Consequently, our model for sleep deprivation may serve as a next reference point for a driving test battery of newly developed drugs.

Towards remote monitoring in pediatric care and clinical trials-Tolerability, repeatability and reference values of candidate digital endpoints derived from physical activity, heart rate and sleep in healthy children.

BACKGROUND: Digital devices and wearables allow for the measurement of a wide range of health-related parameters in a non-invasive manner, which may be particularly valuable in pediatrics. Incorporation of such parameters in clinical trials or care as digital endpoint could reduce the burden for children and their parents but requires clinical validation in the target population. This study aims to determine the tolerability, repeatability, and reference values of novel digital endpoints in healthy children. METHODS: Apparently healthy children (n = 175, 46% male) aged 2-16 were included. Subjects were monitored for 21 days using a home-monitoring platform with several devices (smartwatch, spirometer, thermometer, blood pressure monitor, scales). Endpoints were analyzed with a mixed effects model, assessing variables that explained within- and between-subject variability. Endpoints based on physical activity, heart rate, and sleep-related parameters were included in the analysis. For physical-activity-related endpoints, a sample size needed to detect a 15% increase was calculated. FINDINGS: Median compliance was 94%. Variability in each physical activity-related candidate endpoint was explained by age, sex, watch wear time, rain duration per day, average ambient temperature, and population density of the city of residence. Estimated sample sizes for candidate endpoints ranged from 33-110 per group. Daytime heart rate, nocturnal heart rate and sleep duration decreased as a function of age and were comparable to reference values published in the literature. CONCLUSIONS: Wearable- and portable devices are tolerable for pediatric subjects. The raw data, models and reference values presented here can be used to guide further validation and, in the future, clinical trial designs involving the included measures.

The use of machine learning improves the assessment of drug-induced driving behaviour.

RATIONALE: Car-driving performance is negatively affected by the intake of alcohol, tranquillizers, sedatives and sleep deprivation. Although several studies have shown that the standard deviation of the lateral position on the road (SDLP) is sensitive to drug-induced changes in simulated and real driving performance tests, this parameter alone might not fully assess and quantify deviant or unsafe driving. OBJECTIVE: Using machine learning we investigated if including multiple simulator-derived parameters, rather than the SDLP alone would provide a more accurate assessment of the effect of substances affecting driving performance. We specifically analysed the effects of alcohol and alprazolam. METHODS: The data used in the present study were collected during a previous study on driving effects of alcohol and alprazolam in 24 healthy subjects (12 M, 12 F, mean age 26 years, range 20-43 years). Various driving features, such as speed and steering variations, were quantified and the influence of administration of alcohol or alprazolam was assessed to assist in designing a predictive model for abnormal driving behaviour. RESULTS: Adding additional features besides the SDLP increased the model performance for prediction of drug-induced abnormal driving behaviour (from an accuracy of 65 %-83 % after alprazolam intake and from 50 % to 76 % after alcohol ingestion). Driving behaviour influenced by alcohol and alprazolam was characterised by different feature importance, indicating that the two interventions influenced driving behaviour in a different way. CONCLUSION: Machine learning using multiple driving features in addition to the state-of-the-art SDLP improves the assessment of drug-induced abnormal driving behaviour. The created models may facilitate quantitative description of abnormal driving behaviour in the development and application of psychopharmacological medicines. Our models require further validation using similar and unknown interventions.

Development of Novel, Value-Based, Digital Endpoints for Clinical Trials: A Structured Approach Toward Fit-for-Purpose Validation.

Novel digital endpoints gathered via wearables, small devices, or algorithms hold great promise for clinical trials. However, implementation has been slow because of a lack of guidelines regarding the validation process of these new measurements. In this paper, we propose a pragmatic approach toward selection and fit-for-purpose validation of digital endpoints. Measurements should be value-based, meaning the measurements should directly measure or be associated with meaningful outcomes for patients. Devices should be assessed regarding technological validity. Most importantly, a rigorous clinical validation process should appraise the tolerability, difference between patients and controls, repeatability, detection of clinical events, and correlation with traditional endpoints. When technically and clinically fit-for-purpose, case building in interventional clinical trials starts to generate evidence regarding the response to new or existing health-care interventions. This process may lead to the digital endpoint replacing traditional endpoints, such as clinical rating scales or questionnaires in clinical trials. We recommend initiating more data-sharing collaborations to prevent unnecessary duplication of research and integration of value-based measurements in clinical care to enhance acceptance by health-care professionals. Finally, we invite researchers and regulators to adopt this approach to ensure a timely implementation of digital measurements and value-based thinking in clinical trial design and health care. SIGNIFICANCE STATEMENT: Novel digital endpoints are often cited as promising for the clinical trial of the future. However, clear validation guidelines are lacking in the literature. This paper contains pragmatic criteria for the selection, technical validation, and clinical validation of novel digital endpoints and provides recommendations for future work and collaboration.

Mobile e-diary application facilitates the monitoring of patient-reported outcomes and a high treatment adherence for clinical trials in dermatology.

BACKGROUND: Assessment of treatment effects in clinical trials requires valid information on treatment adherence, adverse events and symptoms. Paper-based diaries are often inconvenient and have limited reliability, particularly for outpatient trials. OBJECTIVES: To investigate the utility of an electronic diary (e-diary) application for patients with skin diseases in outpatient clinical trials. METHODS: An e-diary application was developed and technically validated. Treatment adherence was defined as topical administration by the patient, and patient-reported outcomes, i.e. pain and itch, were evaluated by the e-diary in six clinical trials on newly tested topical drugs. Additionally, the proportion of patients capturing the applied topical drug by camera and filling in the pain and itch scores was defined as e-diary adherence, and patients' perception of usefulness and acceptability of the e-diary were evaluated. RESULTS: Treatment adherence rates of the included 256 patients were high (median 98%, range 97-99%). E-diary adherence was also high with a median of 93% (range 87-97%) for capturing the applied drug by camera, and 89% (range 87-96%) and 94% (range 87-96%) for entering respectively the itch and pain score. Daily symptom scores provided good insights into the disease burden, and patients rated the e-diary as good to excellent with respect to user acceptability. CONCLUSIONS: The results suggest that the e-diary is an excellent way to ensure proper treatment administration, indicated by both the high user acceptability scores and high treatment adherence. Moreover, the e-diary may also be valuable for frequent and reliable monitoring of patient-reported outcomes in daily clinical practice.

Retinal oximetry and fractal analysis of capillary maps in sickle cell disease patients and matched healthy volunteers.

PURPOSE: Fractal analysis can be used to quantitatively analyze the retinal microvasculature and might be a suitable method to quantify retinal capillary changes in sickle cell disease (SCD) patients. Retinal oximetry measurements might function as a proxy for the pathophysiology of cerebrovascular diseases. Moreover, hypoxia has an important role in the pathophysiology of diabetic and other retinopathies. However, little is known about the oximetry around the macula in SCD patients. With this study, we explored the feasibility to perform these quantified measurements in SCD patients. METHODS: Retinal microvascular and oximetry measurements were performed in eight SCD patients and eight healthy matched controls. Oximetry pictures and non-invasive capillary perfusion maps (nCPM) were obtained by the retinal function imager. Measurements were conducted twice on two different study days. Measured variables included monofractal dimension (Dbox), relative saturation, deoxygenated hemoglobin (deoxyHb), and oxygenated hemoglobin (oxyHb) concentration. RESULTS: No statistically significant differences in vessel density were found in the different annular zones (large vessels, p = 0.66; small vessels, p = 0.66) and anatomical quadrants (large vessels, p = 0.74; small vessels, p = 0.72). Furthermore, no significant between-group differences were found in the other different anatomical quadrants and annular zones around the fovea for relative saturation levels and deoxygenated Hb. However, the oxyHb levels were significantly lower in SCD patients, compared with those in matched controls in the temporal quadrants (p = 0.04; p = 0.02) and the superior nasal quadrant (p = 0.05). CONCLUSIONS: Our study demonstrated the feasibility of multispectral imaging to measure retinal changes in oxygenation in both SCD patients and matched volunteers. The results suggest that in SCD patients before any structural microvascular changes in the central retina are present, functional abnormalities can be observed with abnormal oximetry measurements.

Correction to: Retinal oximetry and fractal analysis of capillary maps in sickle cell disease patients and matched healthy volunteers.

In the published online PDF version, Figure 3 was incorrectly captured the same as Figure 1.

[The life cycle of clinical drug research]. / De levensloop van klinisch geneesmiddelonderzoek.

Recently, it was shown that more than 40% of the clinical drug trials in the Netherlands does not reach the stage of publication. Although the non-publication rate of clinical trials seems to have improved compared to previous studies, it is still far from optimal, in particular among phase I trials. In this article the life cycle of clinical drug research is discussed, in order to explain the non-publication rate in the Netherlands and to point out how the publication rate of phase I trials could be improved.

Impact of (chemo)radiotherapy on immune cell composition and function in cervical cancer patients.

New treatments based on combinations of standard therapeutic modalities and immunotherapy are of potential use, but require a profound understanding of immune modulatory properties of standard therapies. Here, the impact of standard (chemo)radiotherapy on the immune system of cervical cancer patients was evaluated. Thirty patients with cervical cancer were treated with external beam radiation therapy (EBRT), using conventional three-dimensional or intensity modulated radiation therapy without constraints for bone marrow sparing. Serial blood sampling for immunomonitoring was performed before, midway and at 3, 6 and 9 weeks after EBRT to analyze the composition of lymphocyte and myeloid-cell populations, the expression of co-stimulatory molecules, T-cell reactivity and antigen presenting cell (APC) function. Therapy significantly decreased the absolute numbers of circulating leukocytes and lymphocytes. Furthermore, the capacity of the remaining T cells to respond to antigenic or mitogenic stimulation was impaired. During treatment the frequency of both CD4+ and CD8+ T cells dropped and CD4+ T cells displayed an increased expression of programmed cell death-1 (PD-1). In vitro blocking of PD-1 successfully increased T-cell reactivity in all five samples isolated before radiotherapy but was less successful in restoring reactivity in samples isolated at later time points. Moreover, (chemo)radiotherapy was associated with an increase in both circulating monocytes and myeloid-derived suppressor cells (MDSCs) and an impaired capacity of APCs to stimulate allogeneic T cells. T-cell reactivity was slowly restored at 6-9 weeks after cessation of therapy. We conclude that conventional (chemo)radiotherapy profoundly suppresses the immune system in cervical cancer patients, and may restrict its combination with immunotherapy.

Quantifying Beta-Galactosylceramide Kinetics in Cerebrospinal Fluid of Healthy Subjects Using Deuterium Labeling.

Therapeutics promoting myelin synthesis may enhance recovery in demyelinating diseases, such as multiple sclerosis. However, no suitable method exists to quantify myelination. The turnover of galactosylceramide (myelin component) is indicative of myelination in mice, but its turnover has not been determined in humans. Here, six healthy subjects consumed 120 mL 70% D2 O daily for 70 days to label galactosylceramide. We then used mass spectrometry and compartmental modeling to quantify the turnover rate of galactosylceramide in cerebrospinal fluid. Maximum deuterium enrichment of body water ranged from 1.5-3.9%, whereas that of galactosylceramide was much lower: 0.05-0.14%. This suggests a slow turnover rate, which was confirmed by the model-estimated galactosylceramide turnover rate of 0.00168 day-1 , which corresponds to a half-life of 413 days. Additional studies in patients with multiple sclerosis are needed to investigate whether galactosylceramide turnover could be used as an outcome measure in clinical trials with remyelination therapies.

Olaparib.

Olaparib is used to treat BReast CAncer susceptibility protein (BRCA)-associated, platinum-sensitive ovarian cancer. Olaparib inhibits poly(ADP-ribose) polymerase, thereby blocking the repair of single-strand DNA breaks. This results in synthetic lethality in BRCA-associated cancer cells, which have a dysfunction of another DNA repair pathway - homologous recombination.

The use of biomarkers in human pharmacology (Phase I) studies.

The development of a new medicine is a risky and costly undertaking that requires careful planning. This planning is largely applied to the operational aspects of the development and less so to the scientific objectives and methodology. The drugs that will be developed in the future will increasingly affect pathophysiological pathways that have been largely unexplored. Such drug prototypes cannot be immediately introduced in large clinical trials. The effects of the drug on normal physiology, pathophysiology, and eventually the desired clinical effects will need to be evaluated in a structured approach, based on the definition of drug development as providing answers to important questions by appropriate clinical studies. This review describes the selection process for biomarkers that are fit-for-purpose for the stage of drug development in which they are used. This structured and practical approach is widely applicable and particularly useful for the early stages of innovative drug development.

Characterization of a standardized glucagon challenge test as a pharmacodynamic tool in pharmacological research.

The aim of this study was to characterize a glucagon challenge test as a tool in diabetes research by assessing the inter- and intra-individual variability, and investigating the activity of the autonomic nervous system (ANS) during the challenge, as this might have an indirect impact on glucose homeostasis. The study was performed in 24 healthy volunteers separated in 2 groups. The first group of 12 volunteers underwent a 5-h glucagon challenge during a pancreatic clamp procedure with infusion of [6,6-2H2]-glucose infusion in combination with heart rate variability measurements. In the second group, 12 other healthy volunteers underwent two 6-h glucagon challenges separated by 6 weeks, and fat biopsies were taken for analysis of glucagon receptor expression. Serum glucose rose rapidly after glucagon infusion, and reached a plateau at 90 min. The time profiles suggested rapid development of tolerance for glucagon-induced hyperglycemia. During the glucagon challenge intra- and inter-individual variabilities for hepatic glucose production, the rate of disappearance of glucose, and plasma glucose were approximately 10-15% for all variables. Hyperglucagonemia did not affect heart rate variability. Human adipose tissue had a low, but variable, expression of glucagon receptor mRNA. This standardized glucagon challenge test has a good reproducibility with only limited variability over 6 weeks. It is a robust tool to explore in detail the contribution of glucagon in normal and altered glucose homeostasis and can also be used to evaluate the effects of drugs antagonizing glucagon action in humans without confounding changes in ANS tone.

Pharmacokinetics and pharmacodynamics of orally administered clonidine: a model-based approach.

BACKGROUND/AIMS: The oral clonidine test is a diagnostic procedure performed in children with suspected growth hormone (GH) deficiency. It is associated with untoward effects, including bradycardia, hypotension and sedation. Serum clonidine levels have not previously been assessed during this test. METHODS: In 40 children referred for an oral clonidine test, blood samples were drawn for clonidine and GH. Vital statistics and sedation scores were recorded until 210 min post-dose. We explored the relationship between clonidine concentrations and effects such as GH peak and blood pressure. RESULTS: Of 40 participants, 5 children were GH deficient. Peak clonidine concentrations of 0.846 ± 0.288 ng/ml were reached after 1 h. Serum levels declined slowly, with concentrations of 0.701 ± 0.189 ng/ml 210 min post-dose. A large interindividual variation of serum levels was observed. During the procedure, systolic blood pressure dropped by 12.8%, diastolic blood pressure by 19.7% and heart rate by 8.4%. Moderate sedation levels were observed. Concentration-effect modeling showed that the amount of GH available for secretion as determined by previous bursts was an important factor influencing GH response. CONCLUSION: Clonidine concentrations during the test were higher than necessary according to model-based predictions. A lower clonidine dose may be sufficient and may produce fewer side effects.

The effects of a novel histamine-3 receptor inverse agonist on essential tremor in comparison to stable levels of alcohol.

Essential tremor (ET) is a common movement disorder. Animal studies show that histaminergic modulation may affect the pathological processes involved in the generation of ET. Histamine-3 receptor inverse agonists (H3RIA) have demonstrated attenuating effects on ET in the harmaline rat model. In this double-blind, three-way cross-over, single-dose, double-dummy study the effects of 25 mg of a novel H3RIA (MK-0249) and a stable alcohol level (0.6 g L(-1)) were compared with placebo, in 18 patients with ET. Tremor was evaluated using laboratory tremorography, portable tremorography and a clinical rating scale. The Leeds Sleep Evaluation Questionnaire (LSEQ) and a choice reaction time (CRT) test were performed to evaluate potential effects on sleep and attention, respectively. A steady state of alcohol significantly diminished tremor as assessed by laboratory tremorography, portable tremorography and clinical ratings compared with placebo. A high single MK-0249 dose was not effective in reducing tremor, but caused significant effects on the LSEQ and the CRT test. These results suggest that treatment with a single dose of MK-0249 does not improve tremor in alcohol-responsive patients with ET, whereas stable levels of alcohol as a positive control reproduced the commonly reported tremor-diminishing effects of alcohol.

The effects of TPA023, a GABAAα2,3 subtype-selective partial agonist, on essential tremor in comparison to alcohol.

Essential tremor (ET) is a relatively frequent neurological disorder that responds in some patients to gamma-aminobutyric acid A (GABA(A)) agonists such as the benzodiazepines. Partial subtype-selective GABA(A) agonists may have an improved side effect profile compared to non-selective GABA(A) agonists. However, it is unknown which GABA(A) subtypes are involved in the therapeutic effects of benzodiazepines in ET. The effects of 2 mg TPA023, a GABA(A) α2,3 subtype-selective partial agonist, on ET were compared to the effects of a stable alcohol level (0.6 g/L) and placebo in nine patients with ET. Tremor evaluation included laboratory accelerometry and a performance-based scale. Additional measurements were performed to evaluate other effects on the central nervous system (CNS). Alcohol significantly diminished tremor symptoms in the postural and kinetic condition, as assessed by laboratory accelerometry, but the performance-based rating scale was unaffected. Tremor was also reduced after TPA023 treatment in the kinetic condition, albeit not significantly. Additionally, TPA023 decreased saccadic peak velocity, while alcohol decreased subjective feelings of alertness. This study showed that alcohol reduced maximum tremor power, as assessed by laboratory accelerometry, unlike TPA023, which decreased tremor symptoms to some extent but not significantly. This study showed that treatment with an α2,3 subunit-selective GABA(A) partial agonist was less effective than a stable level of alcohol in reducing ET symptoms. These results provide no support for a therapeutic role of TPA023 in the suppression of ET symptoms.

Hypothalamic glutamate levels following serotonergic stimulation: a pilot study using 7-Tesla magnetic resonance spectroscopy in healthy volunteers.

INTRODUCTION AND PURPOSE: Functional proton magnetic resonance spectroscopy (MRS) can be applied to measure pharmacodynamic effects of central nervous system (CNS)-active drugs. The serotonin precursor 5-hydroxytryptophan (5-HTP), administered together with carbidopa and granisetron to improve kinetics and reduce adverse effects, acutely enhances central serotonergic neurotransmission and induces hypothalamus-pituitary-adrenal-(HPA) axis activation. We studied the hypothalamic levels of glutamate/glutamine (Glx), choline (Chol), N-acetyl-aspartate (NAA) and creatine using 7-Tesla (7T) MRS, and adrenocorticotropic hormone (ACTH) and cortisol in peripheral blood, after the administration of the 5-HTP function test in healthy volunteers. METHODS: A randomized, double blind, placebo-controlled, two-way cross-over study was performed in 12 healthy males with a 7day wash-out period. After administration of the oral 5-HTP function test, ACTH and cortisol were measured over 4h and MRS scans at 7T were performed every 30min over 3h measuring Glx:Creatine, Chol:Creatine and NAA:Creatine ratios. RESULTS: In the hypothalamus, the administration of 5-HTP had no effect on the average Glx, Chol or NAA levels over 180min but induced a significant decrease of Glx at 60min on post-hoc analysis. 5-HTP-induced significant ACTH release reaching an E(max) of 60.2ng/L at 80min followed by cortisol with an E(max) of 246.4ng/mL at 110min. CONCLUSIONS: The reduction in hypothalamic Glx levels after serotonergic stimulation is compatible with activation of excitatory neurons in this region, which is expected to cause depletion of local glutamate stores. The hypothalamic MRS-response reached its maximum prior to subsequent increases of ACTH and cortisol, which support the functional relevance of hypothalamic Glx-depletion for activation of the HPA-axis. This exploratory study shows that MRS is capable of detecting neuronal activation following functional stimulation of a targeted brain area.