Evaluation of 6 years of eHealth data in the alcohol use disorder field indicates improved efficacy of care.

Background: Predictive eHealth tools will change the field of medicine, however long-term data is scarce. Here, we report findings on data collected over 6 years with an AI-based eHealth system for supporting the treatment of alcohol use disorder. Methods: Since the deployment of Previct Alcohol, structured data has been archived in a data warehouse, currently comprising 505,641 patient days. The frequencies of relapse and caregiver-patient messaging over time was studied. The effects of both introducing an AI-driven relapse prediction tool and the COVID-19 pandemic were analyzed. Results: The relapse frequency per patient day among Previct Alcohol users was 0.28 in 2016, 0.22 in 2020 and 0.25 in 2022 with no drastic change during COVID-19. When a relapse was predicted, the actual occurrence of relapse in the days immediately after was found to be above average. Additionally, there was a noticeable increase in caregiver interactions following these predictions. When caregivers were not informed of these predictions, the risk of relapse was found to be higher compared to when the prediction tool was actively being used. The prediction tool decreased the relapse risk by 9% for relapses that were of short duration and by 18% for relapses that lasted more than 3 days. Conclusions: The eHealth system Previct Alcohol allows for high resolution measurements, enabling precise identifications of relapse patterns and follow up on individual and population-based alcohol use disorder treatment. eHealth relapse prediction aids the caregiver to act timely, which reduces, delays, and shortens relapses.

Processing incomplete questionnaire data into continuous digital biomarkers for addiction monitoring.

PURPOSE: eHealth systems allow efficient daily smartphone-based collection of self-reported data on mood, wellbeing, routines, and motivation; however, missing data is frequent. Within addictive disorders, missing data may reflect lack of motivation to stay sober. We hypothesize that qualitative questionnaire data contains valuable information, which after proper handling of missing data becomes more useful for practitioners. METHODS: Anonymized data from daily questionnaires containing 11 questions was collected with an eHealth system for 751 patients with alcohol use disorder (AUD). Two digital continuous biomarkers were composed from 9 wellbeing questions (WeBe-i) and from two questions representing motivation/self-confidence to remain sober (MotSC-i). To investigate possible loss of information in the process of composing the digital biomarkers, performance of neural networks to predict exacerbation events (relapse) in alcohol use disorder was compared. RESULTS: Long short-term memory (LSTM) neural networks predicted a coming exacerbation event 1-3 days (AUC 0.68-0.70) and 5-7 days (AUC 0.65-0.68) in advance on unseen patients. The predictive capability of digital biomarkers and raw questionnaire data was equal, indicating no loss of information. The transformation into digital biomarkers enable a continuous graphical display of each patient's clinical course and a combined interpretation of qualitative and quantitative aspects of recovery on a time scale. CONCLUSION: By transforming questionnaire data with large proportion of missing data into continuous digital biomarkers, the information captured by questionnaires can be more easily used in clinical practice. Information, assessed by the capability to predict exacerbation events of AUD, is preserved when processing raw questionnaire data into digital biomarkers.

The Clinical Course of Alcohol Use Disorder Depicted by Digital Biomarkers.

Aims: This study introduces new digital biomarkers to be used as precise, objective tools to measure and describe the clinical course of patients with alcohol use disorder (AUD). Methods: An algorithm is outlined for the calculation of a new digital biomarker, the recovery and exacerbation index (REI), which describes the current trend in a patient's clinical course of AUD. A threshold applied to the REI identifies the starting point and the length of an exacerbation event (EE). The disease patterns and periodicity are described by the number, length, and distance between EEs. The algorithms were tested on data from patients from previous clinical trials (n = 51) and clinical practice (n = 1,717). Results: Our study indicates that the digital biomarker-based description of the clinical course of AUD might be superior to the traditional self-reported relapse/remission concept and conventional biomarkers due to higher data quality (alcohol measured) and time resolution. We found that EEs and the REI introduce distinct tools to identify qualitative and quantitative differences in drinking patterns (drinks per drinking day, phosphatidyl ethanol levels, weekday and holiday patterns) and effect of treatment time. Conclusions: This study indicates that the disease state-level, trend and periodicity-can be mathematically described and visualized with digital biomarkers, thereby improving knowledge about the clinical course of AUD and enabling clinical decision-making and adaptive care. The algorithms provide a basis for machine-learning-driven research that might also be applied for other disorders where daily data are available from digital health systems.

Breathalyser-Based eHealth Data Suggest That Self-Reporting of Abstinence Is a Poor Outcome Measure for Alcohol Use Disorder Clinical Trials.

AIMS: To evaluate the efficacy and monitoring capabilities of a breathalyser-based eHealth system for patients with alcohol use disorder (AUD) and to investigate the quality and validity of timeline follow-back (TLFB) as outcome measure in clinical trials and treatment. METHODS: Patients (n = 115) were recruited to clinical trials from a 12-step aftercare programme (12S-ABS) and from hospital care with abstinence (HC-ABS) or controlled drinking (HC-CDR) as goal and randomly divided into an eHealth and a control group. The effect of the eHealth system was analysed with TLFB-derived primary outcomes-change in number of abstinent days (AbsDay) and heavy drinking days (HDDs) compared to baseline-and phosphatidyl ethanol (PEth) measurements. Validity and quality of TLFB were evaluated by comparison with breath alcohol content (BrAC) and eHealth digital biomarkers (DBs): Addiction Monitoring Index (AMI) and Maximum Time Between Tests (MTBT). TLFB reports were compared to eHealth data regarding reported abstinence. RESULTS: The primary outcome (TLFB) showed no significant difference between eHealth and control groups, but PEth did show a significant difference especially at months 2 and 3. Self-reported daily abstinence suffered from severe quality issues: of the 28-day TLFB reports showing full abstinence eHealth data falsified 34% (BrAC measurements), 39% (MTBT), 54% (AMI) and 68% (BrAC/MTBT/AMI). 12S-ABS and HC-ABS patients showed severe under-reporting. CONCLUSIONS: No effect of the eHealth system was measured with TLFB, but a small positive effect was measured with PEth. The eHealth system revealed severe quality problems with TLFB, especially regarding abstinence-should measurement-based eHealth data replace TLFB as outcome measure for AUD?

Maximum Time Between Tests: A Digital Biomarker to Detect Therapy Compliance and Assess Schedule Quality in Measurement-Based eHealth Systems for Alcohol Use Disorder.

AIM: To evaluate, in a breathalyzer-based eHealth system, whether the time-based digital biomarker 'maximum time between tests' (MTBT) brings valuable information on alcohol consumption patterns as confirmed by correlation with blood phosphatidyl ethanol (PEth), serum carbohydrate deficient transferrin (CDT) and timeline follow-back data. METHOD: Data on 54 patients in follow-up for treatment of alcohol use disorder were analysed. RESULTS: The model of weekly averages of 24-log transformed MTBT adequately described timeline follow-back data (P  <  0.0001, R =  0.27-0.38, n  =  650). Significant correlations were noted between MTBT and PEth (P  <  0.0001, R  =  0.41, n  =  148) and between MTBT and CDT (P  <  0.0079, R  =  0.22, n  =  120). CONCLUSIONS: The time-based digital biomarker 'maximum time between tests' described here has the potential to become a generally useful metric for all scheduled measurement-based eHealth systems to monitor test behaviour and compliance, factors important for 'dosing' of eHealth systems and for early prediction and interventions of lapse/relapse.

Real-time Monitoring using a breathalyzer-based eHealth system can identify lapse/relapse patterns in alcohol use disorder Patients.

AIM: We introduce a new remote real-time breathalyzer-based method for monitoring and early identification of lapse/relapse patterns for alcohol use disorder (AUD) patients using a composite measure of sobriety, the Addiction Monitoring Index (AMI). METHODS: We constructed AMI from (a) obtained test results and (b) the pattern of ignored tests using data from the first 30 patients starting in the treatment arms of two on-going clinical trials. The patients performed 2-4 scheduled breath alcohol content (BrAC)-tests per day presented as blood alcohol content (BAC) data. In total, 10,973 tests were scheduled, 7743 were performed and 3230 were ignored during 3982 patient days. RESULTS: AMI-time profiles could be used to monitor the daily trends of alcohol consumption and detect early signs of lapse and relapses. The pattern of ignored tests correlates with the onset of drinking. AMI correlated with phosphatidyl ethanol (n = 61, F-ratio = 34.6, P < 0.0001, R = -0.61). The recognition of secret drinking could further be improved using a low alcohol detection threshold (BrAC = 0.025 mg/l, BACSwe = 0.05‰ or US = 0.0053g/dl), in addition to the legal Swedish traffic limit (BrAC = 0.1 mg/l, BACSwe = 0.2‰ or US = 0.021 g/dl). Nine out of 10 patients who dropped out from the study showed early risk signs as reflected in the level and pattern in AMI before the actual dropout. CONCLUSIONS: AMI-time profiles from an eHealth system are useful for monitoring the recovery process and for early identification of lapse/relapse patterns. High-resolution monitoring of sobriety enables new measurement-based treatment methods for proactive personalized long-term relapse prevention and treatment of AUD patients. CLINICAL TRIAL REGISTRATION: The data used for construction of AMI was from two clinical trials approved by the Regional Ethics Committee of Uppsala, Sweden and performed in accordance with the Declaration of Helsinki. Written informed consent was obtained from all participating subjects. The study was registered at ClinicalTrials.gov (NCT03195894).

Increased sensitivity of SPR assays in plasma through efficient parallel assay optimization.

The sensitivity of biosensor assays in complex media such as plasma or serum is often limited by non-specific binding. The degree of binding often varies between individuals and therefore a large number of different plasma samples have to be used during assay development. Some surface plasmon resonance (SPR) biosensors allow for parallel screening of several running buffer compositions, with a number of different immobilization levels for each buffer. These technical possibilities combined with statistical design of experiments (DoE) enable efficient parallel optimization of multiple assay conditions. In this paper we outline how to increase the sensitivity in SPR-based assays by minimizing background binding and variability from negative control plasma while retaining high signals from positive samples. To mimic immunogenicity studies of biotherapeutics we have used a model assay with anti-rituximab as an anti-drug antibody to be detected in plasma by binding to immobilized rituximab. Immobilization level and sodium chloride concentration were found to be the most important factors to optimize. There were also a number of significant interaction effects and strong non-linearites between the buffer composition/immobilization level and the assay performance, which necessitated DoE based optimization strategies. The applicability of the optimized conditions was verified with several assays (anti-erythropoietin, omalizumab, anti-IgE and anti-myoglobin) in spiked plasma samples resulting in detection levels in the range of 80-170 ng ml(-1). The buffer conditions presented in this paper can be used for other immunogenicity assays on biosensor platforms or as a good starting point for further assay development for new immunogenicity assays.

Label-free primary screening and affinity ranking of fragment libraries using parallel analysis of protein panels.

The authors present fragment screening data obtained using a label-free parallel analysis approach where the binding of fragment library compounds to 4 different target proteins can be screened simultaneously using surface plasmon resonance detection. They suggest this method as a first step in fragment screening to identify and select binders, reducing the demanding requirements on subsequent X-ray or nuclear magnetic resonance studies, and as a valuable "clean-up" tool to eliminate unwanted promiscuous binders from libraries. A small directed fragment library of known thrombin binders and a general 500-compound fragment library were used in this study. Thrombin, blocked thrombin, carbonic anhydrase, and glutathione-S-transferase were immobilized on the sensor chip surface, and the direct binding of the fragments was studied in real time. Only 12 microg of each protein is needed for screening of a 3000-compound fragment library. For screening, a binding site-blocked target as reference facilitates the identification of binding site-selective hits and the signals from other reference proteins for the elimination of false positives. The scope and limitations of this screening approach are discussed for both target-directed and general fragment libraries.

Label-free kinetic binding data as a decisive element in drug discovery.

The emerging possibilities to obtain label-free, kinetic-based binding data for drug-target and drug absorption, distribution, metabolism and excretion (ADME)-marker interactions have proven useful in many drug discovery related issues. Multiple reports have demonstrated that the common use of affinity as an early measure of drug potency may be directly misleading. This review summarises findings in the literature related to compound selection in the drug discovery process. It is important to understand the different properties of association and dissociation rates, the former being related to both structure and dosage and the latter depending solely on molecular structure. By performing parallel optimisations of association and dissociation rates, compounds with desirable kinetic profiles for target binding may be generated. In addition, compound selection may also consider the kinetic properties of the drug-ADME-marker binding profiles, further refining the quality of compounds early in the drug discovery process. The promising results found in the literature indicate that kinetic data on drug-protein interactions may soon become a crucial decisive element in modern drug discovery.

Biosensor analysis of the interaction between drug compounds and liposomes of different properties; a two-dimensional characterization tool for estimation of membrane absorption.

The interactions between 78 drug compounds and immobilised liposomes were investigated using an assay based on surface plasmon resonance technology. The drugs were screened at a single concentration and allowed to interact simultaneously with two different types of liposomes. When the drug-liposome responses are plotted against one another they generally fall into three distinct bands: low response-low percent fraction absorbed in humans (Fa), medium response-medium Fa, and high response-high Fa. For drugs with medium to high Fa values, basic compounds could be resolved from acidic and neutral compounds to a large extent. This technique has the potential to be utilized as a screening tool for binning novel compounds into low, medium, or high Fa based on a simple experimental measurement. The assay was applied to 11 kinase inhibitors, 9 thrombin inhibitors, and 11 carbonic anhydrase inhibitors highlighting a subset that may have incomplete intestinal absorption (low to medium Fa). Assay conditions were optimized making the assay suitable for routine analysis and for compound characterization early in drug discovery where solubility may be an issue.

Kinetic and thermodynamic characterization of HIV-1 protease inhibitors.

Interaction kinetic and thermodynamic analyses provide information beyond that obtained in general inhibition studies, and may contribute to the design of improved inhibitors and increased understanding of molecular interactions. Thus, a biosensor-based method was used to characterize the interactions between HIV-1 protease and seven inhibitors, revealing distinguishing kinetic and thermodynamic characteristics for the inhibitors. Lopinavir had fast association and the highest affinity of the tested compounds, and the interaction kinetics were less temperature-dependent as compared with the other inhibitors. Amprenavir, indinavir and ritonavir showed non-linear temperature dependencies of the kinetics. The free energy, enthalpy and entropy (DeltaG, DeltaH, DeltaS) were determined, and the energetics of complex association (DeltaG(on), DeltaH(on), DeltaS(on)) and dissociation (DeltaG(off), DeltaH(off), DeltaS(off)) were resolved. In general, the energetics for the studied inhibitors was in the same range, with the negative free energy change (DeltaG < 0) due primarily to increased entropy (DeltaS > 0). Thus, the driving force of the interaction was increased degrees of freedom in the system (entropy) rather than the formation of bonds between the enzyme and inhibitor (enthalpy). Although the DeltaG(on) and DeltaG(off) were in the same range for all inhibitors, the enthalpy and entropy terms contributed differently to association and dissociation, distinguishing these phases energetically. Dissociation was accompanied by positive enthalpy (DeltaH(off) > 0) and negative entropy (DeltaS(off) < 0) changes, whereas association for all inhibitors except lopinavir had positive entropy changes (DeltaS(on) > 0), demonstrating unique energetic characteristics for lopinavir. This study indicates that this type of data will be useful for the characterization of target-ligand interactions and the development of new inhibitors of HIV-1 protease.

QSAR studies applied to the prediction of antigen-antibody interaction kinetics as measured by BIACORE.

The objective of this work was to investigate the potential of the quantitative structure-activity relationships (QSAR) approach for predictive modulation of molecular interaction kinetics. A multivariate QSAR approach involving modifications in peptide sequence and buffer composition was recently used in an attempt to predict the kinetics of peptide-antibody interactions as measured by BIACORE. Quantitative buffer-kinetics relationships (QBKR) and quantitative sequence-kinetics relationships (QSKR) models were developed. Their predictive capacity was investigated in this study by comparing predicted and observed kinetic dissociation parameters (k(d)) for new antigenic peptides, or in new buffers. The range of experimentally measured k(d) variations was small (300-fold), limiting the practical value of the approach for this particular interaction. However, the models were validated from a statistical point of view. In QSKR, the leave-one-out cross validation gave Q(2) = 0.71 for 24 peptides (all but one outlier), compared to 0.81 for 17 training peptides. A more precise model (Q(2) = 0.92) could be developed when removing sets of peptides sharing distinctive structural features, suggesting that different peptides use slightly different binding modes. All models share the most important factor and are informative for structure-kinetics relationships. In QBKR, the measured effect on k(d) of individual additives in the buffers was consistent with the effect predicted from multivariate buffers. Our results open new perspectives for the predictive optimization of interaction kinetics, with important implications in pharmacology and biotechnology.