Development of oculomics artificial intelligence for cardiovascular risk factors: A case study in fundus oculomics for HbA1c assessment and clinically relevant considerations for clinicians.

Artificial Intelligence (AI) is transforming healthcare, notably in ophthalmology, where its ability to interpret images and data can significantly enhance disease diagnosis and patient care. Recent developments in oculomics, the integration of ophthalmic features to develop biomarkers for systemic diseases, have demonstrated the potential for providing rapid, non-invasive methods of screening leading to enhance in early detection and improve healthcare quality, particularly in underserved areas. However, the widespread adoption of such AI-based technologies faces challenges primarily related to the trustworthiness of the system. We demonstrate the potential and considerations needed to develop trustworthy AI in oculomics through a pilot study for HbA1c assessment using an AI-based approach. We then discuss various challenges, considerations, and solutions that have been developed for powerful AI technologies in the past in healthcare and subsequently apply these considerations to the oculomics pilot study. Building upon the observations in the study we highlight the challenges and opportunities for advancing trustworthy AI in oculomics. Ultimately, oculomics presents as a powerful and emerging technology in ophthalmology and understanding how to optimize transparency prior to clinical adoption is of utmost importance.

Memory Classifiers for Robust ECG Classification against Physiological Noise.

The development of sophisticated machine learning algorithms has made it possible to detect critical health conditions like cardiac arrhythmia, directly from electrocardiogram (ECG) recordings. Large-scale machine learning models, like deep neural networks, are well known to underperform when subjected to small perturbations which would not pose a challenge to physicians. This is a hurdle that needs to be removed to facilitate wide-scale adoption. We find this to be true even for models trained using data-augmentation schemes.In this paper, we show that using memory classifiers it is possible to attain a boost in robustness using expert-informed features. Memory classifiers combine standard deep neural network training with a domain knowledge-guided similarity metric to boost the robustness of classifiers. We evaluate the performance of the models against naturally occurring physiological perturbations, specifically electrode movement, muscle artifact, and baseline wander noise. Our approach demonstrates improved robustness across all evaluated noises for an average improvement in F1 score of 3.13% compared to models using data augmentation techniques.Clinical relevance- This approach improves the robustness of deep learning methods in safety-critical medical applications.

Prolonged Use of an Automated Insulin Delivery System Improves Sleep in Long-Standing Type 1 Diabetes Complicated by Impaired Awareness of Hypoglycemia.

BACKGROUND: This study assessed changes in actigraphy-estimated sleep and glycemic outcomes after initiating automated insulin delivery (AID). METHODS: Ten adults with long-standing type 1 diabetes and impaired awareness of hypoglycemia (IAH) participated in an 18-month clinical trial assessing an AID intervention on hypoglycemia and counter-regulatory mechanisms. Data from eight participants (median age = 58 years) with concurrent wrist actigraph and continuous glucose monitoring (CGM) data were used in the present analyses. Actigraphs and CGM measured sleep and glycemic control at baseline (one week) and months 3, 6, 9, 12, 15, and 18 (three weeks) following AID initiation. HypoCount software integrated actigraphy with CGM data to separate wake and sleep-associated glycemic measures. Paired sample t-tests and Cohen's d effect sizes modeled changes and their magnitude in sleep, glycemic control, IAH (Clarke score), hypoglycemia severity (HYPO score), hypoglycemia exposure (CGM), and glycemic variability (lability index [LI]; CGM coefficient-of-variation [CV]) from baseline to 18 months. RESULTS: Sleep improved from baseline to 18 months (shorter sleep latency [P < .05, d = 1.74], later sleep offset [P < .05, d = 0.90], less wake after sleep onset [P < .01, d = 1.43]). Later sleep onset (d = 0.74) and sleep midpoint (d = 0.77) showed medium effect sizes. Sleep improvements were evident from 12 to 15 months after AID initiation and were preceded by improved hypoglycemia awareness (Clarke score [d = 1.18]), reduced hypoglycemia severity (HYPO score [d = 2.13]), reduced sleep-associated hypoglycemia (percent time glucose was < 54 mg/dL, < 60 mg/dL,< 70 mg/dL; d = 0.66-0.81), and reduced glucose variability (LI, d = 0.86; CV, d = 0.62). CONCLUSION: AID improved sleep initiation and maintenance. Improved awareness of hypoglycemia, reduced hypoglycemia severity, hypoglycemia exposure, and glucose variability preceded sleep improvements.This trial is registered with ClinicalTrials.gov NCT03215914 https://clinicaltrials.gov/ct2/show/NCT03215914.

Automated Insulin Delivery for Hypoglycemia Avoidance and Glucose Counterregulation in Long-Standing Type 1 Diabetes with Hypoglycemia Unawareness.

Objective: Automated insulin delivery (AID) may benefit individuals with long-standing type 1 diabetes where frequent exposure to hypoglycemia impairs counterregulatory responses. This study assessed the effect of 18 months AID on hypoglycemia avoidance and glucose counterregulatory responses to insulin-induced hypoglycemia in long-standing type 1 diabetes complicated by impaired awareness of hypoglycemia. Methods: Ten participants mean ± standard deviation age 49 ± 16 and diabetes duration 34 ± 16 years were initiated on AID. Continuous glucose monitoring was paired with actigraphy to assess awake- and sleep-associated hypoglycemia exposure every 3 months. Hyperinsulinemic hypoglycemic clamp experiments were performed at baseline, 6, and 18 months postintervention. Hypoglycemia exposure was reduced by 3 months, especially during sleep, with effects sustained through 18 months (P ≤ 0.001) together with reduced glucose variability (P < 0.01). Results: Hypoglycemia awareness and severity scores improved (P < 0.01) with severe hypoglycemia events reduced from median (interquartile range) 3 (3-10) at baseline to 0 (0-1) events/person·year postintervention (P = 0.005). During the hypoglycemic clamp experiments, no change was seen in the endogenous glucose production (EGP) response, however, peripheral glucose utilization during hypoglycemia was reduced following intervention [pre: 4.6 ± 0.4, 6 months: 3.8 ± 0.5, 18 months: 3.4 ± 0.3 mg/(kg·min), P < 0.05]. There were increases over time in pancreatic polypeptide (Pre:62 ± 29, 6 months:127 ± 44, 18 months:176 ± 58 pmol/L, P < 0.01), epinephrine (Pre: 199 ± 53, 6 months: 332 ± 91, 18 months: 386 ± 95 pg/mL, P = 0.001), and autonomic symptom (Pre: 6 ± 2, 6 months: 6 ± 2, 18 months: 10 ± 2, P < 0.05) responses. Conclusions: AID led to a sustained reduction of hypoglycemia exposure. EGP in response to insulin-induced hypoglycemia remained defective, however, partial recovery of glucose counterregulation was evidenced by a reduction in peripheral glucose utilization likely mediated by increased epinephrine secretion and, together with improved autonomic symptoms, may contribute to the observed clinical reduction in hypoglycemia.

Automatically Predicting Perceived Conversation Quality in a Pediatric Sample Enriched for Autism.

Social interaction quality ratings derived from short natural conversations can differentiate children with and without autism at the group level. In this work, we explored conversations between children and an unfamiliar adult who rated their social interaction success on six dimensions. Using hand-crafted acoustic and lexical features, we built different classifiers to predict children's dimensional conversation quality. The best classifier achieved 61% accuracy, which outperformed human raters (49%). Follow-up analyses revealed that a subset of features determined communication quality scores. Additionally, we extracted acoustic features using a pretrained audio transformer and improved our prediction to 68%. This study suggests that automatically predicting conversation quality could be an inexpensive and objective way to monitor intervention progress in children with communication challenges, and could be used to identify intervention targets for improving conversational success.

Carbon-Based Ternary Nanocomposite: Bullet Type ZnO-SWCNT-CuO for Substantial Solar-Driven Photocatalytic Decomposition of Aqueous Organic Contaminants.

A facile two-step synthesis of ternary hetero-composites of ZnO, CuO, and single-walled carbon nanotubes (SWCNTs) was developed through a recrystallization process followed by annealing. A series of nanocomposites were prepared by varying the weight ratio of copper(II) acetate hydrate and zinc(II) acetate dihydrate and keeping the weight ratio of SWCNTs constant. The results revealed the formation of heterojunctions (ZnO-SWCNT-CuO, ZSC) of three crystal structures adjacent to each other, forming a ternary wurtzite-structured nanoparticles along with defects. Enhanced charge separation (electron-hole pairs), reduced band gap, defect-enhanced specific surface area, and promoted oxidation potential were key factors for the enhanced photocatalytic activity of the ternary nanocomposites. OH• radicals were the main active species during dye degradation, and O2-• and h+ were also involved to a lesser extent. A type II heterojunction mechanism approach is proposed based on the charge carrier migration pattern. Among the synthesized nanocomposites, the sample prepared using copper(II) acetate hydrate and zinc(II) acetate dihydrate in a 1: 9 ratio (designated a ZSC3) showed the highest photocatalytic activity. ZSC3 achieved 99.2% photodecomposition of methylene blue in 20 min, 94.1% photodecomposition of Congo red in 60 min, and 99.6% photodecomposition of Rhodamine B in 40 min under simulated sunlight. Additionally, ZSC3 showed excellent reusability and stability, maintaining 96.7% of its activity even after five successive uses. Based on overall results, the ZSC sample was proposed as an excellent candidate for water purification applications.

Facile Preparation of a Bispherical Silver-Carbon Photocatalyst and Its Enhanced Degradation Efficiency of Methylene Blue, Rhodamine B, and Methyl Orange under UV Light.

The combination of organic and inorganic materials is attracting attention as a photocatalyst that promotes the decomposition of organic dyes. A facile thermal procedure has been proposed to produce spherical silver nanoparticles (AgNPs), carbon nanospheres (CNSs), and a bispherical AgNP-CNS nanocomposite. The AgNPs and CNSs were each synthesized from silver acetate and glucose via single- and two-step annealing processes under sealed conditions, respectively. The AgNP-CNS nanocomposite was synthesized by the thermolysis of a mixture of silver acetate and a mesophase, where the mesophase was formed by annealing glucose in a sealed vessel at 190 °C. The physicochemical features of the as-prepared nanoparticles and composite were evaluated using several analytical techniques, revealing (i) increased light absorption, (ii) a reduced bandgap, (iii) the presence of chemical interfacial heterojunctions, (iv) an increased specific surface area, and (v) favorable band-edge positions of the AgNP-CNS nanocomposite compared with those of the individual AgNP and CNS components. These characteristics led to the excellent photocatalytic efficacy of the AgNP-CNS nanocomposite for the decomposition of three pollutant dyes under ultraviolet (UV) radiation. In the AgNP-CNS nanocomposite, the light absorption and UV utilization capacity increased at more active sites. In addition, effective electron-hole separation at the heterojunction between the AgNPs and CNSs was possible under favorable band-edge conditions, resulting in the creation of reactive oxygen species. The decomposition rates of methylene blue were 95.2, 80.2, and 73.2% after 60 min in the presence of the AgNP-CNS nanocomposite, AgNPs, and CNSs, respectively. We also evaluated the photocatalytic degradation efficiency at various pH values and loadings (catalysts and dyes) with the AgNP-CNS nanocomposite. The AgNP-CNS nanocomposite was structurally rigid, resulting in 93.2% degradation of MB after five cycles of photocatalytic degradation.

Hierarchical Nanocauliflower Chemical Assembly Composed of Copper Oxide and Single-Walled Carbon Nanotubes for Enhanced Photocatalytic Dye Degradation.

We present the fabrication and proficient photocatalytic performance of a series of heterojunction nanocomposites with cauliflower-like architecture synthesized from copper(II) oxide (CuO) nanocrystals and carbon nanotubes with single walls (SWCNTs). These unique photocatalysts were constructed via simplistic recrystallization succeeded by calcination and were labeled as CuOSC-1, CuOSC-2, and CuOSC-3 (representing the components; CuO and SC for SWCNTs, and the calcination time in hours). The photocatalytic potency of the fabricated nanocomposites was investigated on the basis of their capability to decompose methylene blue (MB) dye under visible-light irradiation. Every as-synthesized nanocomposite was effective photocatalyst for the photodecomposition of an MB solution. Moreover, CuOSC-3 exhibited the best photocatalytic activity, with 96% degradation of the visible-light irradiated MB solution in 2 h. Pure CuO nanocrystals generated through the same route and pure SWCNTs were used as controls, where the photocatalytic actions of the nanocomposite samples were found to be remarkably better than that of either the pure CuO or the pure SWCNTs. The recycling proficiency of the photocatalysts was also explored; the results disclosed that the samples could be applied for five cycles without exhibiting a notable change in photocatalytic performance or morphology.

Stacked LSTM based deep recurrent neural network with kalman smoothing for blood glucose prediction.

BACKGROUND: Blood glucose (BG) management is crucial for type-1 diabetes patients resulting in the necessity of reliable artificial pancreas or insulin infusion systems. In recent years, deep learning techniques have been utilized for a more accurate BG level prediction system. However, continuous glucose monitoring (CGM) readings are susceptible to sensor errors. As a result, inaccurate CGM readings would affect BG prediction and make it unreliable, even if the most optimal machine learning model is used. METHODS: In this work, we propose a novel approach to predicting blood glucose level with a stacked Long short-term memory (LSTM) based deep recurrent neural network (RNN) model considering sensor fault. We use the Kalman smoothing technique for the correction of the inaccurate CGM readings due to sensor error. RESULTS: For the OhioT1DM (2018) dataset, containing eight weeks' data from six different patients, we achieve an average RMSE of 6.45 and 17.24 mg/dl for 30 min and 60 min of prediction horizon (PH), respectively. CONCLUSIONS: To the best of our knowledge, this is the leading average prediction accuracy for the ohioT1DM dataset. Different physiological information, e.g., Kalman smoothed CGM data, carbohydrates from the meal, bolus insulin, and cumulative step counts in a fixed time interval, are crafted to represent meaningful features used as input to the model. The goal of our approach is to lower the difference between the predicted CGM values and the fingerstick blood glucose readings-the ground truth. Our results indicate that the proposed approach is feasible for more reliable BG forecasting that might improve the performance of the artificial pancreas and insulin infusion system for T1D diabetes management.

Characterizing Glycemic Control and Sleep in Adults with Long-Standing Type 1 Diabetes and Hypoglycemia Unawareness Initiating Hybrid Closed Loop Insulin Delivery.

Nocturnal hypoglycemia is life threatening for individuals with type 1 diabetes (T1D) due to loss of hypoglycemia symptom recognition (hypoglycemia unawareness) and impaired glucose counter regulation. These individuals also show disturbed sleep, which may result from glycemic dysregulation. Whether use of a hybrid closed loop (HCL) insulin delivery system with integrated continuous glucose monitoring (CGM) designed for improving glycemic control, relates to better sleep across time in this population remains unknown. The purpose of this study was to describe long-term changes in glycemic control and objective sleep after initiating hybrid closed loop (HCL) insulin delivery in adults with type 1 diabetes and hypoglycemia unawareness. To accomplish this, six adults (median age = 58 y) participated in an 18-month ongoing trial assessing HCL effectiveness. Glycemic control and sleep were measured using continuous glucose monitoring and wrist accelerometers every 3 months. Paired sample t-tests and Cohen's d effect sizes modeled glycemic and sleep changes and the magnitude of these changes from baseline to 9 months. Reduced hypoglycemia (d = 0.47-0.79), reduced basal insulin requirements (d = 0.48), and a smaller glucose coefficient of variation (d = 0.47) occurred with medium-large effect sizes from baseline to 9 months. Hypoglycemia awareness improved from baseline to 6 months with medium-large effect sizes (Clarke score (d = 0.60), lability index (d = 0.50), HYPO score (d = 1.06)). Shorter sleep onset latency (d = 1.53; p < 0.01), shorter sleep duration (d = 0.79), fewer total activity counts (d = 1.32), shorter average awakening length (d = 0.46), and delays in sleep onset (d = 1.06) and sleep midpoint (d = 0.72) occurred with medium-large effect sizes from baseline to 9 months. HCL led to clinically significant reductions in hypoglycemia and improved hypoglycemia awareness. Sleep showed a delayed onset, reduced awakening length and onset latency, and maintenance of high sleep efficiency after initiating HCL. Our findings add to the limited evidence on the relationships between diabetes therapeutic technologies and sleep health. This trial is registered with ClinicalTrials.gov (NCT03215914).

VitalCore: Analytics and Support Dashboard for Medical Device Integration.

Medical professionals spend extensive time collecting, validating, reviewing, and analyzing medical device data. These devices use vendor-specific applications with lengthy troubleshooting times, causing extended downtimes where medical professionals have to manually document patient data in the electronic health record (EHR). Manual logging of this data creates delays and leaves it vulnerable to errors, manipulation, and omissions. In this paper, we present VitalCore, a medical device integration platform that supports access to medical device data in real-time. We deploy VitalCore in three applications at Penn Medicine: Medical Device Dashboard, Ventilation Alert, and Anomaly Detector. In the Medical Device Dashboard, we reduced, by up to six times, the amount of time required of medical professionals, clinical engineers, and IT analysts by simplifying the troubleshooting workflow, thus decreasing downtimes and increasing clinical productivity. In Ventilation Alert, we demonstrated the ability to assist medical professionals by alerting them to newly ventilated patients. In Anomaly Detector, we showed that we could predict anomalous patterns in our data with 93% accuracy.

Intelligent and Dynamic Ransomware Spread Detection and Mitigation in Integrated Clinical Environments.

Medical Cyber-Physical Systems (MCPS) hold the promise of reducing human errors and optimizing healthcare by delivering new ways to monitor, diagnose and treat patients through integrated clinical environments (ICE). Despite the benefits provided by MCPS, many of the ICE medical devices have not been designed to satisfy cybersecurity requirements and, consequently, are vulnerable to recent attacks. Nowadays, ransomware attacks account for 85% of all malware in healthcare, and more than 70% of attacks confirmed data disclosure. With the goal of improving this situation, the main contribution of this paper is an automatic, intelligent and real-time system to detect, classify, and mitigate ransomware in ICE. The proposed solution is fully integrated with the ICE++ architecture, our previous work, and makes use of Machine Learning (ML) techniques to detect and classify the spreading phase of ransomware attacks affecting ICE. Additionally, Network Function Virtualization (NFV) and Software Defined Networking (SDN)paradigms are considered to mitigate the ransomware spreading by isolating and replacing infected devices. Different experiments returned a precision/recall of 92.32%/99.97% in anomaly detection, an accuracy of 99.99% in ransomware classification, and promising detection and mitigation times. Finally, different labelled ransomware datasets in ICE have been created and made publicly available.

Continuous Glucose Monitoring for Hypoglycemia Avoidance and Glucose Counterregulation in Long-Standing Type 1 Diabetes.

Context: Patients with long-standing type 1 diabetes (T1D) are at increased risk for severe hypoglycemia because of defects in glucose counterregulation and recognition of hypoglycemia symptoms, in part mediated through exposure to hypoglycemia. Objective: To determine whether implementation of real-time continuous glucose monitoring (CGM) as a strategy for hypoglycemia avoidance could improve glucose counterregulation in patients with long-standing T1D and hypoglycemia unawareness. Design, Setting, Participants, and Intervention: Eleven patients with T1D disease duration of ∼31 years were studied longitudinally in the Clinical & Translational Research Center of the University of Pennsylvania before and 6 and 18 months after initiation of CGM and were compared with 12 nondiabetic control participants. Main Outcome Measure: Endogenous glucose production response derived from paired hyperinsulinemic stepped-hypoglycemic and euglycemic clamps with infusion of 6,6-2H2-glucose. Results: In patients with T1D, hypoglycemia awareness (Clarke score) and severity (HYPO score and severe events) improved (P < 0.01 for all) without change in hemoglobin A1c (baseline, 7.2% ± 0.2%). In response to insulin-induced hypoglycemia, endogenous glucose production did not change from before to 6 months (0.42 ± 0.08 vs 0.54 ± 0.07 mg·kg-1·min-1) but improved after 18 months (0.84 ± 0.15 mg·kg-1·min-1; P < 0.05 vs before CGM), albeit remaining less than in controls (1.39 ± 0.11 mg·kg-1·min-1; P ≤ 0.01 vs all). Conclusions: Real-time CGM can improve awareness and reduce the burden of problematic hypoglycemia in patients with long-standing T1D, but with only modest improvement in the endogenous glucose production response that is required to prevent or correct low blood glucose.

Reducing Pulse Oximetry False Alarms Without Missing Life-Threatening Events.

Alarm fatigue has been increasingly recognized as one of the most significant problems in the hospital environment. One of the major causes is the excessive number of false physiologic monitor alarms. An underlying problem is the inefficient traditional threshold alarm system for physiologic parameters such as low blood oxygen saturation (SpO2). In this paper, we propose a robust classification procedure based on the AdaBoost algorithm with reject option that can identify and silence false SpO2 alarms, while ensuring zero misclassified clinically significant alarms. Alarms and vital signs related to SpO2 such as heart rate and pulse rate, within monitoring interval are extracted into different numerical features for the classifier. We propose a variant of AdaBoost with reject option by allowing a third decision (i.e., reject) expressing doubt. Weighted outputs of each weak classifier are input to a softmax function optimizing to satisfy a desired false negative rate upper bound while minimizing false positive rate and indecision rate. We evaluate the proposed classifier using a dataset collected from 100 hospitalized children at Children's Hospital of Philadelphia and show that the classifier can silence 23.12% of false SpO2 alarms without missing any clinically significant alarms.

Direct observation of the conformational transitions of single pyridine molecules on a Ag(110) surface induced by long-range repulsive intermolecular interactions.

The transition between two conformations of pyridine molecules adsorbed on a Ag(110) surface at 13 K was investigated by performing single-molecule manipulation at a very low coverage and the track-imaging of pyridines for various surface coverages using a variable low-temperature scanning tunneling microscope. A single tilted conformer was converted to an upright conformer when another coadsorbed tilted pyridine molecule approached to within ∼2 nm. The conversion probability depends on the molecular separation. The tilted conformers that are prevalent at a very low coverage were converted to upright conformers with an increasing surface coverage. The minimum molecular separation before this transition is induced was determined to be 2.2 nm using molecular track-imaging and statistical analysis of the pyridine separation as a function of the molecular coverage. The conformation transition was attributed to substrate-mediated long-range repulsive interactions between the pyridine molecules, which are produced by charge redistribution that occurs upon pyridine adsorption on the silver surface.

Physiology-Invariant Meal Detection for Type 1 Diabetes.

BACKGROUND: Fully automated artificial pancreas systems require meal detectors to supplement blood glucose level regulation, where false meal detections can cause unnecessary insulin delivery with potentially fatal consequences, and missed detections may cause the patient to experience extreme hyperglycemia. Most existing meal detectors monitor various measures of glucose rate-of-change to detect meals where varying physiology and meal content complicate balancing detector sensitivity versus specificity. METHODS: We developed a novel meal detector based on a minimal glucose-insulin metabolism model and show that the detector is, by design, invariant to patient-specific physiological parameters in the minimal model. Our physiological parameter-invariant (PAIN) detector achieves a near-constant false alarm rate across all individuals and is evaluated against three other major existing meal detectors on a clinical type 1 diabetes data set. RESULTS: In the clinical evaluation, the PAIN-based detector achieves an 86.9% sensitivity for an average false alarm rate of two alarms per day. In addition, for all false alarm rates, the PAIN-based detector performance is significantly better than three other existing meal detectors. In addition, the evaluation results show that the PAIN-based detector uniquely (as compared with the other meal detectors) has low variance in detection and false alarm rates across all patients, without patient-specific personalization. CONCLUSIONS: The PAIN-based meal detector has demonstrated better detection performance than existing meal detectors, and it has the unique strength of achieving a consistent performance across a population with varying physiology without any individual-level parameter tuning or training.

Functional Alarms for Systems of Interoperable Medical Devices.

Alarms are essential for medical systems in order to ensure patient safety during deteriorating clinical situations and inevitable device malfunction. As medical devices are connected together to become interoperable, alarms become crucial part in making them high-assurance, in nature. Traditional alarm systems for interoperable medical devices have been patientcentric. In this paper, we introduce the need for an alarm system that focuses on the correct functionality of the interoperability architecture itself, along with several considerations and design challenges in enabling them.

Prediction of significant vasospasm in aneurysmal subarachnoid hemorrhage using automated data.

BACKGROUND: When vasospasm is detected after aneurysmal subarachnoid hemorrhage (aSAH), it is treated with hypertensive or endovascular therapy. Current classification methods are resource-intensive, relying on specialty-trained professionals (nursing exams, transcranial dopplers, and perfusion imaging). More passively obtained variables such as cerebrospinal fluid drainage volumes, sodium, glucose, blood pressure, intracranial pressure, and heart rate, have not been used to predict vasospasm. We hypothesize that these features may yield as much information as resource-intensive features to classify vasospasm. METHODS: We studied data from 81 aSAH patients presenting within two days of onset. Vasospasm class (VSP) was defined by angiographic vasospasm warranting endovascular treatment. Naïve Bayes (NB) and logistic regression (LR) classifiers were trained on selected variable feature sets from the first three days of illness. Performance of trained classifiers was evaluated using area under the receiver operator characteristic curve (AUC classifier) and F-measure (F classifier). Ablation analysis determined incremental utility of each variable and subsets. RESULTS: 43.2 % developed VSP. During feature selection, the only passively collected variable that did not yield a statistically significant summary statistic was CSF drainage volume. NB classifier trained on all passively obtained features (AUC NB 0.708 and F NB 0.636) outperformed NB classifier trained on resource-intensive features (AUC NB 0.501 and F NB 0.349). CONCLUSIONS: Data-driven analysis of passively obtained clinical data predicted VSP better than current targeted resource-intensive monitoring techniques after aSAH. Automated classification of VSP may be possible.