A drug recommender system for the treatment of hypertension.

BACKGROUND: One third (20% to 30%) of patients suffering from hypertension show increased blood pressure resistant to treatment. This resistance often has multifactorial causes, like therapeutic inertia and inappropriate medication but also poor patient adherence. Evidence-based guidelines aim to support appropriate health care decisions. However, (i) research and appraisal of clinical guidelines is often not practicable in daily routine care and (ii) guidelines alone are often insufficient to make suitable and personalized treatment decisions. Shared decision-making (SDM) can significantly improve patient adherence, but is also difficult to implement in routine care due to time constraints. METHODS: Clinical Decision Support Systems (CDSSs), designed to support clinical decision-making by providing explainable and personalized treatment recommendations, are expected to remedy the aforementioned issues. In this work we describe a digital recommendation system for the pharmaceutical treatment of hypertension and compare its recommendations with clinical experts. The proposed therapy recommender algorithm combines external evidence (knowledge-based) - derived from clinical guidelines and drugs' professional information - with information stored in routine care data (data-based) - derived from 298 medical records and 900 doctor-patient contacts from 7 general practitioners practices. The developed Graphical User Interface (GUI) visualizes recommendations along with personalized treatment information and intents to support SDM. The CDSS was evaluated on 23 artificial test patients (case vignettes), by comparing its output with recommendations from five specialized physicians. RESULTS: The results show that the proposed algorithm provides personalized treatment recommendations with large agreement with clinical experts. This is true for agreement with all experts (agree_all), with any expert (agree_any), and with the majority vote of all experts (agree_majority). The performance of a solely data-based approach can be additionally improved by applying evidence-based rules (external evidence). When comparing the achieved results (agree_all) with the inter-rater agreement among experts, the CDSS's recommendations partly agree more often with the experts than the experts among each other. CONCLUSION: Overall, the feasibility and performance of medication recommendation systems for the treatment of hypertension could be shown. The major challenges when developing such a CDSS arise from (i) the availability of sufficient and appropriate training and evaluation data and (ii) the absence of standardized medical knowledge such as computerized guidelines. If these challenges are solved, such treatment recommender systems can support physicians with exploiting knowledge stored in routine care data, help to comply with the best available clinical evidence and increase the adherence of the patient by reducing site-effects and individualizing therapies.

Acceptance of a digital therapy recommender system for psoriasis.

BACKGROUND: About 2% of the German population are affected by psoriasis. A growing number of cost-intensive systemic treatments are available. Surveys have shown high proportions of patients with moderate to severe psoriasis are not adequately treated despite a high disease burden. Digital therapy recommendation systems (TRS) may help implement guideline-based treatment. However, little is known about the acceptance of such clinical decision support systems (CDSSs). Therefore, the aim of the study was to access the acceptance of a prototypical TRS demonstrator. METHODS: Three scenarios (potential test patients with psoriasis but different sociodemographic and clinical characteristics, previous treatments, desire to have children, and multiple comorbidities) were designed in the demonstrator. The TRS demonstrator and test patients were presented to a random sample of 76 dermatologists attending a national dermatology conference in a cross-sectional face-to-face survey with case vignettes. The dermatologist were asked to rate the demonstrator by system usability scale (SUS), whether they would use it for certain patients populations and barriers of usage. Reasons for potential usage of the TRS demonstrator were tested via a Poisson regression with robust standard errors. RESULTS: Acceptance of the TRS was highest for patients eligible for systemic therapy (82%). 50% of participants accepted the system for patients with additional comorbidities and 43% for patients with special subtypes of psoriasis. Dermatologists in the outpatient sector or with many patients per week were less willing to use the TRS for patients with special psoriasis-subtypes. Dermatologists rated the demonstrator as acceptable with an mean SUS of 76.8. Participants whose SUS was 10 points above average were 27% more likely to use TRS for special psoriasis-subtypes. The main barrier in using the TRS was time demand (47.4%). Participants who perceived time as an obstacle were 22.3% less willing to use TRS with systemic therapy patients. 27.6% of physicians stated that they did not understand exactly how the recommendation was generated by the TRS, with no effect on the preparedness to use the system. CONCLUSION: The considerably high acceptance and the preparedness to use the psoriasis CDSS suggests that a TRS appears to be implementable in routine healthcare and may improve clinical care. Main barrier is the additional time demand posed on dermatologists in a busy clinical setting. Therefore, it will be a major challenge to identify a limited set of variables that still allows a valid recommendation with precise prediction of the patient-individual benefits and harms.

Predicting sepsis with a recurrent neural network using the MIMIC III database.

OBJECTIVE: Predicting sepsis onset with a recurrent neural network and performance comparison with InSight - a previously proposed algorithm for the prediction of sepsis onset. METHODOLOGY: A retrospective analysis of adult patients admitted to the intensive care unit (from the MIMIC III database) who did not fall under the definition of sepsis at the time of admission. The area under the receiver operating characteristic (AUROC) measures the performance of the prediction task. We examine the sequence length given to the machine learning algorithms for different points in time before sepsis onset concerning the prediction performance. Additionally, the impact of sepsis onset's definition is investigated. We evaluate the model with a relatively large and thus more representative patient population compared to related works in the field. RESULTS: For a prediction 3 h prior to sepsis onset, our network achieves an AUROC of 0.81 (95% CI: 0.78-0.84). The InSight algorithm achieves an AUROC of 0.72 (95% CI: 0.69-0.75). For a fixed sensitivity of 90% our network reaches a specificity of 47.0% (95% CI: 43.1%-50.8%) compared to 31.1% (95% CI: 24.8%-37.5%) for InSight. In addition, we compare the performance for 6 and 12 h prediction time for both approaches. CONCLUSION: Our findings demonstrate that a recurrent neural network is superior to InSight considering the prediction performance. Most probably, the improvement results from the network's ability of revealing time dependencies. We show that the length of the look back has a significant impact on the performance of the classifier. We also demonstrate that for the correct detection of sepsis onset for a retrospective analysis, further research is necessary.

Lesional and perilesional tissue characterization by automated image processing in a novel gyrencephalic animal model of peracute intracerebral hemorrhage.

Intracerebral hemorrhage (ICH) is an important stroke subtype, but preclinical research is limited by a lack of translational animal models. Large animal models are useful to comparatively investigate key pathophysiological parameters in human ICH. To (i) establish an acute model of moderate ICH in adult sheep and (ii) an advanced neuroimage processing pipeline for automatic brain tissue and hemorrhagic lesion determination; 14 adult sheep were assigned for stereotactically induced ICH into cerebral white matter under physiological monitoring. Six hours after ICH neuroimaging using 1.5T MRI including structural as well as perfusion and diffusion, weighted imaging was performed before scarification and subsequent neuropathological investigation including immunohistological staining. Controlled, stereotactic application of autologous blood caused a space-occupying intracerebral hematoma of moderate severity, predominantly affecting white matter at 5 h post-injection. Neuroimage post-processing including lesion probability maps enabled automatic quantification of structural alterations including perilesional diffusion and perfusion restrictions. Neuropathological and immunohistological investigation confirmed perilesional vacuolation, axonal damage, and perivascular blood as seen after human ICH. The model and imaging platform reflects key aspects of human ICH and enables future translational research on hematoma expansion/evacuation, white matter changes, hematoma evacuation, and other aspects.

Therapy Decision Support Based on Recommender System Methods.

We present a system for data-driven therapy decision support based on techniques from the field of recommender systems. Two methods for therapy recommendation, namely, Collaborative Recommender and Demographic-based Recommender, are proposed. Both algorithms aim to predict the individual response to different therapy options using diverse patient data and recommend the therapy which is assumed to provide the best outcome for a specific patient and time, that is, consultation. The proposed methods are evaluated using a clinical database incorporating patients suffering from the autoimmune skin disease psoriasis. The Collaborative Recommender proves to generate both better outcome predictions and recommendation quality. However, due to sparsity in the data, this approach cannot provide recommendations for the entire database. In contrast, the Demographic-based Recommender performs worse on average but covers more consultations. Consequently, both methods profit from a combination into an overall recommender system.