Rich Landscape of Colloidal Semiconductor-Metal Hybrid Nanostructures: Synthesis, Synergetic Characteristics, and Emerging Applications.

Nanochemistry provides powerful synthetic tools allowing one to combine different materials on a single nanostructure, thus unfolding numerous possibilities to tailor their properties toward diverse functionalities. Herein, we review the progress in the field of semiconductor-metal hybrid nanoparticles (HNPs) focusing on metal-chalcogenides-metal combined systems. The fundamental principles of their synthesis are discussed, leading to a myriad of possible hybrid architectures including Janus zero-dimensional quantum dot-based systems and anisotropic quasi 1D nanorods and quasi-2D platelets. The properties of HNPs are described with particular focus on emergent synergetic characteristics. Of these, the light-induced charge-separation effect across the semiconductor-metal nanojunction is of particular interest as a basis for the utilization of HNPs in photocatalytic applications. The extensive studies on the charge-separation behavior and its dependence on the HNPs structural characteristics, environmental and chemical conditions, and light excitation regime are surveyed. Combining the advanced synthetic control with the charge-separation effect has led to demonstration of various applications of HNPs in different fields. A particular promise lies in their functionality as photocatalysts for a variety of uses, including solar-to-fuel conversion, as a new type of photoinitiator for photopolymerization and 3D printing, and in novel chemical and biomedical uses.

Evaluating the dynamic interplay of social distancing policies regarding airborne pathogens through a temporal interaction-driven model that uses real-world and synthetic data.

OBJECTIVE: The recent SARS-CoV-2 pandemic has exhibited diverse patterns of spread across countries and communities, emphasizing the need to consider the underlying population dynamics in modeling its progression and the importance of evaluating the effectiveness of non-pharmaceutical intervention strategies in combating viral transmission within human communities. Such an understanding requires accurate modeling of the interplay between the community dynamics and the disease propagation dynamics within the community. METHODS: We build on an interaction-driven model of an airborne disease over contact networks that we have defined. Using the model, we evaluate the effectiveness of temporal, spatial, and spatiotemporal social distancing policies. Temporal social distancing involves a pure dilation of the timeline while preserving individual activity potential and thus prolonging the period of interaction; spatial distancing corresponds to social distancing pods; and spatiotemporal distancing pertains to the situation in which fixed subgroups of the overall group meet at alternate times. We evaluate these social distancing policies over real-world interactions' data and over history-preserving synthetic temporal random networks. Furthermore, we evaluate the policies for the disease's with different number of initial patients, corresponding to either the phase in the progression of the infection through a community or the number of patients infected together at the initial infection event. We expand our model to consider the exposure to viral load, which we correlate with the meetings' duration. RESULTS: Our results demonstrate the superiority of decreasing social interactions (i.e., time dilation) within the community over partial isolation strategies, such as the spatial distancing pods and the spatiotemporal distancing strategy. In addition, we found that slow-spreading pathogens (i.e., pathogens that require a longer exposure to infect) spread roughly at the same rate as fast-spreading ones in highly active communities. This result is surprising since the pathogens may follow different paths. However, we demonstrate that the dilation of the timeline considerably slows the spread of the slower pathogens. CONCLUSIONS: Our results demonstrate that the temporal dynamics of a community have a more significant effect on the spread of the disease than the characteristics of the spreading processes.

Implementation and evaluation of a system for assessment of the quality of long-term management of patients at a geriatric hospital.

BACKGROUND: The increasing aging population presents a significant challenge, accompanied by a shortage of professional caregivers, adding to the therapeutic burden. Clinical decision support systems, utilizing computerized clinical guidelines, can improve healthcare quality, reduce expenses, save time, and boost caregiver efficiency. OBJECTIVES: 1) Develop and evaluate an automated quality assessment (QA) system for retrospective longitudinal care quality analysis, focusing on clinical staff adherence to evidence-based guidelines (GLs). 2) Assess the system's technical feasibility and functional capability for senior nurse use in geriatric pressure-ulcer management. METHODS: A computational QA system using our Quality Assessment Temporal Patterns (QATP) methodology was designed and implemented. Our methodology transforms the GL's procedural-knowledge into declarative-knowledge temporal-abstraction patterns representing the expected execution trace in the patient's data for correct therapy application. Fuzzy temporal logic allows for partial compliance, reflecting individual and grouped action performance considering their values and temporal aspects. The system was tested using a pressure ulcer treatment GL and data from 100 geriatric patients' Electronic Medical Records (EMR). After technical evaluation for accuracy and feasibility, an extensive functional evaluation was conducted by an experienced nurse, comparing QA scores with and without system support, and versus automated system scores. Time efficiency was also measured. RESULTS: QA scores from the geriatric nurse, with and without system's support, did not significantly differ from those provided by the automated system (p < 0.05), demonstrating the effectiveness and reliability of both manual and automated methods. The system-supported manual QA process reduced scoring time by approximately two-thirds, from an average of 17.3 min per patient manually to about 5.9 min with the system's assistance, highlighting the system's efficiency potential in clinical practice. CONCLUSION: The QA system based on QATP, produces scores consistent with an experienced nurse's assessment for complex care over extended periods. It enables quick and accurate quality care evaluation for multiple patients after brief training. Such automated QA systems may empower nursing staff, enabling them to manage more patients, accurately and consistently, while reducing costs due to saved time and effort, and enhanced compliance with evidence-based guidelines.

Vibrational spectroscopy characterization of impregnated activated carbon adsorption of H2S.

Activated carbon filters are used for the removal of hazardous gases from the air. This research applied vibrational spectroscopy methods, including Fourier-transform infrared spectroscopy and Raman spectroscopy to characterize hydrogen sulfide adsorption on impregnated carbon materials with metals having reactivity toward hydrogen sulfide. The Fourier-transform infrared spectroscopy results demonstrated the formation of a new chemical bond between the impregnating metals and the sulfur, indicated by the appearance of a new band at 618 cm-1. The Raman spectra results showed that for the copper-impregnated activated carbon with the highest hydrogen sulfide adsorption capacity, a new vibrational band at 475 cm-1 evolved, indicating a copper-sulfur bond. In addition, upshifts in the carbon D sub-bands were observed after efficient hydrogen sulfide adsorption, along with a larger area of the approximately 1500 cm-1 band. Therefore, Fourier-transform infrared spectroscopy and Raman spectroscopy combination can potentially indicate H2S adsorption on impregnated activated carbon filters.

The Impact of US County-Level Factors on COVID-19 Morbidity and Mortality.

The effect of socio-economic factors, ethnicity, and other factors, on the morbidity and mortality of COVID-19 at the sub-population-level, rather than at the individual level, and their temporal dynamics, is only partially understood. Fifty-three county-level features were collected between 4/2020 and 11/2020 from 3,071 US counties from publicly available data of various American government and news websites: ethnicity, socio-economic factors, educational attainment, mask usage, population density, age distribution, COVID-19 morbidity and mortality, presidential election results, and ICU beds. We trained machine learning models that predict COVID-19 mortality and morbidity using county-level features and then performed a SHAP value game theoretic importance analysis of the predictive features for each model. The classifiers produced an AUROC of 0.863 for morbidity prediction and an AUROC of 0.812 for mortality prediction. A SHAP value-based analysis indicated that poverty rate, obesity rate, mean commute time, and mask usage statistics significantly affected morbidity rates, while ethnicity, median income, poverty rate, and education levels heavily influenced mortality rates. Surprisingly, the correlation between several of these factors and COVID-19 morbidity and mortality gradually shifted and even reversed during the study period; our analysis suggests that this phenomenon was probably due to COVID-19 being initially associated with more urbanized areas and, then, from 9/2020, with less urbanized ones. Thus, socio-economic features such as ethnicity, education, and economic disparity are the major factors for predicting county-level COVID-19 mortality rates. Between counties, low variance factors (e.g., age) are not meaningful predictors. The inversion of some correlations over time can be explained by COVID-19 spreading from urban to rural areas.

Visualizing Ultrafast Electron Transfer Processes in Semiconductor-Metal Hybrid Nanoparticles: Toward Excitonic-Plasmonic Light Harvesting.

Recently, it was demonstrated that charge separation in hybrid metal-semiconductor nanoparticles (HNPs) can be obtained following photoexcitation of either the semiconductor or of the localized surface plasmon resonance (LSPR) of the metal. This suggests the intriguing possibility of photocatalytic systems benefiting from both plasmon and exciton excitation, the main challenge being to outcompete other ultrafast relaxation processes. Here we study CdSe-Au HNPs using ultrafast spectroscopy with high temporal resolution. We describe the complete pathways of electron transfer for both semiconductor and LSPR excitation. In the former, we distinguish hot and band gap electron transfer processes in the first few hundred fs. Excitation of the LSPR reveals an ultrafast (<30 fs) electron transfer to CdSe, followed by back-transfer from the semiconductor to the metal within 210 fs. This study establishes the requirements for utilization of the combined excitonic-plasmonic contribution in HNPs for diverse photocatalytic applications.

A Cyber-Security Risk Assessment Methodology for Medical Imaging Devices: the Radiologists' Perspective.

Medical imaging devices (MIDs) are exposed to cyber-security threats. Currently, a comprehensive, efficient methodology dedicated to MID cyber-security risk assessment is lacking. We propose the Threat identification, ontology-based Likelihood, severity Decomposition, and Risk assessment (TLDR) methodology and demonstrate its feasibility and consistency with existing methodologies, while being more efficient, providing details regarding the severity components, and supporting organizational prioritization and customization. Using our methodology, the impact of 23 MIDs attacks (that were previously identified) was decomposed into six severity aspects. Four Radiology Medical Experts (RMEs) were asked to assess these six aspects for each attack. The TLDR methodology's external consistency was demonstrated by calculating paired T-tests between TLDR severity assessments and those of existing methodologies (and between the respective overall risk assessments, using attack likelihood estimates by four healthcare cyber-security experts); the differences were insignificant, implying externally consistent risk assessment. The TLDR methodology's internal consistency was evaluated by calculating the pairwise Spearman rank correlations between the severity assessments of different groups of two to four RMEs and each of their individual group members, showing that the correlations between the severity rankings, using the TLDR methodology, were significant (P < 0.05), demonstrating that the severity rankings were internally consistent for all groups of RMEs. Using existing methodologies, however, the internal correlations were insignificant for groups of less than four RMEs. Furthermore, compared to standard risk assessment techniques, the TLDR methodology is also sensitive to local radiologists' preferences, supports a greater level of flexibility regarding risk prioritization, and produces more transparent risk assessments.

Implementation and evaluation of a multivariate abstraction-based, interval-based dynamic time-warping method as a similarity measure for longitudinal medical records.

OBJECTIVES: A common prerequisite for tasks such as classification, prediction, clustering and retrieval of longitudinal medical records is a clinically meaningful similarity measure that considers both [multiple] variable (concept) values and their time. Currently, most similarity measures focus on raw, time-stamped data as these are stored in a medical record. However, clinicians think in terms of clinically meaningful temporal abstractions, such as "decreasing renal functions", enabling them to ignore minor time and value variations and focus on similarities among the clinical trajectories of different patients. Our objective was to define an abstraction- and interval-based methodology for matching longitudinal, multivariate medical records, and rigorously assess its value, versus the option of using just the raw, time-stamped data. METHODS: We have developed a new methodology for determination of the relative distance between a pair of longitudinal records, by extending the known dynamic time warping (DTW) method into an interval-based dynamic time warping (iDTW) methodology. The iDTW methodology includes (A): A three-steps interval-based representation (iRep) method: [1] abstracting the raw, time-stamped data of the longitudinal records into clinically meaningful interval-based abstractions, using a domain-specific knowledge base, [2] scoping the period of comparison of the records, [3] creating from the intervals a symbolic time series, by partitioning them into a predetermined temporal granularity; (B) An interval-based matching (iMatch) method to match each relevant pair of multivariate longitudinal records, each represented as multiple series of short symbolic intervals in the determined temporal granularity, using a modified DTW version. EVALUATION: Three classification or prediction tasks were defined: (1) classifying 161 records of oncology patients as having had autologous versus allogenic bone-marrow transplantation; (2) classifying the longitudinal records of 125 hepatitis patients as having B or C hepatitis; and (3) predicting micro- or macro-albuminuria in the second year, for 151 diabetes patients who were followed for five years. The raw, time-stamped, multivariate data within each medical record, for one, two, or three concepts out of four or five concepts judged as relevant in each medical domain, were abstracted into clinically meaningful intervals using the Knowledge-Based Temporal-Abstraction method, using previously acquired knowledge. We focused on two temporal-abstraction types: (1) State abstractions, which discretize a concept's raw value into a predetermined range (e.g., LOW or HIGH Hemoglobin); and (2) Gradient abstractions, which indicate the trend of the concept's value (e.g., INCREASING, DECREASING Hemoglobin value). We created all of the combinations of either uni-dimensional (State or Gradient) or multi-dimensional (State and Gradient) abstractions, of all of the concepts used. Classification of a record was determined by using a majority of the k-Nearest-Neighbors (KNN) of the given record, k ranging over the odd numbers (to break ties) from 1 to N, N being the size of the training set. We have experimented with all possible configurations of the parameters that our method uses. Overall, a total of 75,936 experiments were performed: 33,600 in the Oncology domain, 28,800 in the Hepatitis domain, and 13,536 in the Diabetes domain. Each experiment involved the performance of a 10-fold Cross Validation to compute the mean performance of a particular iDTW method-configuration set of settings, for a specific subset of one, two, or three concepts out of all of the domain-specific concepts relevant to the classification or prediction task on which the experiment focuses. We measured for each such experimental combination the Area Under the Curve (AUC) and the optimal Specificity/Sensitivity ratio using Youden's Index. We then aggregated the experiments by the types of unidimensional or multidimensional abstractions used in them (including the use of only raw concepts as a special case); for example, two state abstractions of different concepts, and one gradient abstraction of a third concept. We compared the mean AUC when using each such feature representation, or combination of abstractions, across all possible method-setting configurations, to the mean AUC when using as a feature representation, for the same task, only raw concepts, also across all possible method-setting configurations. Finally, we applied a paired t-test, to determine whether the mean difference between the accuracy of each temporal-abstraction representation, across all concept and configuration combinations, and the respective raw-concept combinations, across all concept subset and configuration combinations, is significant (P < 0.05). RESULTS: The mean performance of the classification and prediction tasks when using, as a feature representation, the various temporal-abstraction combinations, was significantly higher than that performance when using only raw data. Furthermore, in each domain and task, there existed at least one representation using interval-based abstractions whose use led, on average (over all concept subset combinations and method configurations) to a significantly better performance than the use of only subsets of the raw time-stamped data. In seven of nine combinations of domain type (out of three) and number of concepts used (one, two, or three), the variance of the AUCs (for all representations and configurations) was considerably higher across all raw-concept subsets, compared to all abstract combinations. Increasing the number of features used by the matching task enhanced performance. Using multi-dimensional abstractions of the same concept further enhanced the performance. When using only raw data, increasing the number of neighbors monotonically increased the mean performance (over all concept combinations and method configurations) until reaching an optimal saddle-point aroundN; when using abstractions, however, optimal mean performance was often reached after matching only five nearest neighbors. CONCLUSIONS: Using multivariate and multidimensional interval-based, abstraction-based similarity measures is feasible, and consistently and significantly improved the mean classification and prediction performance in time-oriented domains, using DTW-inspired methods, compared to the use of only raw, time-stamped data. It also made the KNN classification more effective. Nevertheless, although the mean performance for the abstract representations was higher than the mean performance when using only raw-data concepts, the actual optimal classification performance in each domain and task depends on the choice of the specific raw or abstract concepts used as features.

Charge Carrier Dynamics in Photocatalytic Hybrid Semiconductor-Metal Nanorods: Crossover from Auger Recombination to Charge Transfer.

Hybrid semiconductor-metal nanoparticles (HNPs) manifest unique, synergistic electronic and optical properties as a result of combining semiconductor and metal physics via a controlled interface. These structures can exhibit spatial charge separation across the semiconductor-metal junction upon light absorption, enabling their use as photocatalysts. The combination of the photocatalytic activity of the metal domain with the ability to generate and accommodate multiple excitons in the semiconducting domain can lead to improved photocatalytic performance because injecting multiple charge carriers into the active catalytic sites can increase the quantum yield. Herein, we show a significant metal domain size dependence of the charge carrier dynamics as well as the photocatalytic hydrogen generation efficiencies under nonlinear excitation conditions. An understanding of this size dependence allows one to control the charge carrier dynamics following the absorption of light. Using a model hybrid semiconductor-metal CdS-Au nanorod system and combining transient absorption and hydrogen evolution kinetics, we reveal faster and more efficient charge separation and transfer under multiexciton excitation conditions for large metal domains compared to small ones. Theoretical modeling uncovers a competition between the kinetics of Auger recombination and charge separation. A crossover in the dominant process from Auger recombination to charge separation as the metal domain size increases allows for effective multiexciton dissociation and harvesting in large metal domain HNPs. This was also found to lead to relative improvement of their photocatalytic activity under nonlinear excitation conditions.

Clinical decision support models and frameworks: Seeking to address research issues underlying implementation successes and failures.

Computer-based clinical decision support (CDS) has been pursued for more than five decades. Despite notable accomplishments and successes, wide adoption and broad use of CDS in clinical practice has not been achieved. Many issues have been identified as being partially responsible for the relatively slow adoption and lack of impact, including deficiencies in leadership, recognition of purpose, understanding of human interaction and workflow implications of CDS, cognitive models of the role of CDS, and proprietary implementations with limited interoperability and sharing. To address limitations, many approaches have been proposed and evaluated, drawing on theoretical frameworks, as well as management, technical and other disciplines and experiences. It seems clear, because of the multiple perspectives involved, that no single model or framework is adequate to encompass these challenges. This Viewpoint paper seeks to review the various foci of CDS and to identify aspects in which theoretical models and frameworks for CDS have been explored or could be explored and where they might be expected to be most useful.

Rapid Three-Dimensional Printing in Water Using Semiconductor-Metal Hybrid Nanoparticles as Photoinitiators.

Additive manufacturing processes enable fabrication of complex and functional three-dimensional (3D) objects ranging from engine parts to artificial organs. Photopolymerization, which is the most versatile technology enabling such processes through 3D printing, utilizes photoinitiators that break into radicals upon light absorption. We report on a new family of photoinitiators for 3D printing based on hybrid semiconductor-metal nanoparticles. Unlike conventional photoinitiators that are consumed upon irradiation, these particles form radicals through a photocatalytic process. Light absorption by the semiconductor nanorod is followed by charge separation and electron transfer to the metal tip, enabling redox reactions to form radicals in aerobic conditions. In particular, we demonstrate their use in 3D printing in water, where they simultaneously form hydroxyl radicals for the polymerization and consume dissolved oxygen that is a known inhibitor. We also demonstrate their potential for two-photon polymerization due to their giant two-photon absorption cross section.

Consistent discovery of frequent interval-based temporal patterns in chronic patients' data.

Increasingly, frequent temporal patterns discovered in longitudinal patient records are proposed as features for classification and prediction, and as means to cluster patient clinical trajectories. However, to justify that, we must demonstrate that most frequent temporal patterns are indeed consistently discoverable within the records of different patient subsets within similar patient populations. We have developed several measures for the consistency of the discovery of temporal patterns. We focus on time-interval relations patterns (TIRPs) that can be discovered within different subsets of the same patient population. We expect the discovered TIRPs (1) to be frequent in each subset, (2) preserve their "local" metrics - the absolute frequency of each pattern, measured by a Proportion Test, and (3) preserve their "global" characteristics - their overall distribution, measured by a Kolmogorov-Smirnov test. We also wanted to examine the effect on consistency, over a variety of settings, of varying the minimal frequency threshold for TIRP discovery, and of using a TIRP-filtering criterion that we previously introduced, the Semantic Adjacency Criterion (SAC). We applied our methodology to three medical domains (oncology, infectious hepatitis, and diabetes). We found that, within the minimal frequency ranges we had examined, 70-95% of the discovered TIRPs were consistently discoverable; 40-48% of them maintained their local frequency. TIRP global distribution similarity varied widely, from 0% to 65%. Increasing the threshold usually increased the percentage of TIRPs that were repeatedly discovered across different patient subsets within the same domain, and the probability of a similar TIRP distribution. Using the SAC principle, enhanced, for most minimal support levels, the percentage of repeating TIRPs, their local consistency and their global consistency. The effect of using the SAC was further strengthened as the minimal frequency threshold was raised.

Photocatalytic Reactive Oxygen Species Formation by Semiconductor-Metal Hybrid Nanoparticles. Toward Light-Induced Modulation of Biological Processes.

Semiconductor-metal hybrid nanoparticles manifest efficient light-induced spatial charge separation at the semiconductor-metal interface, as demonstrated by their use for hydrogen generation via water splitting. Here, we pioneer a study of their functionality as efficient photocatalysts for the formation of reactive oxygen species. We observed enhanced photocatalytic activity forming hydrogen peroxide, superoxide, and hydroxyl radicals upon light excitation, which was significantly larger than that of the semiconductor nanocrystals, attributed to the charge separation and the catalytic function of the metal tip. We used this photocatalytic functionality for modulating the enzymatic activity of horseradish peroxidase as a model system, demonstrating the potential use of hybrid nanoparticles as active agents for controlling biological processes through illumination. The capability to produce reactive oxygen species by illumination on-demand enhances the available peroxidase-based tools for research and opens the path for studying biological processes at high spatiotemporal resolution, laying the foundation for developing novel therapeutic approaches.

An automated knowledge-based textual summarization system for longitudinal, multivariate clinical data.

OBJECTIVES: Design and implement an intelligent free-text summarization system: The system's input includes large numbers of longitudinal, multivariate, numeric and symbolic clinical raw data, collected over varying periods of time, and in different complex contexts, and a suitable medical knowledge base. The system then automatically generates a textual summary of the data. We aim to prove the feasibility of implementing such a system, and to demonstrate its potential benefits for clinicians and for enhancement of quality of care. METHODS: We have designed a new, domain-independent, knowledge-based system, the CliniText system, for automated summarization in free text of longitudinal medical records of any duration, in any context. The system is composed of six components: (1) A temporal abstraction module generates all possible abstractions from the patient's raw data using a temporal-abstraction knowledge base; (2) The abductive reasoning module infers abstractions or events from the data, which were not explicitly included in the database; (3) The pruning module filters out raw or abstract data based on predefined heuristics; (4) The document structuring module organizes the remaining raw or abstract data, according to the desired format; (5) The microplanning module, groups the raw or abstract data and creates referring expressions; (6) The surface realization module, generates the text, and applies the grammar rules of the chosen language. We have performed an initial technical evaluation of the system in the cardiac intensive-care and diabetes domains. We also summarize the results of a more detailed evaluation study that we have performed in the intensive-care domain that assessed the completeness, correctness, and overall quality of the system's generated text, and its potential benefits to clinical decision making. We assessed these measures for 31 letters originally composed by clinicians, and for the same letters when generated by the CliniText system. RESULTS: We have successfully implemented all of the components of the CliniText system in software. We have also been able to create a comprehensive temporal-abstraction knowledge base to support its functionality, mostly in the intensive-care domain. The initial technical evaluation of the system in the cardiac intensive-care and diabetes domains has shown great promise, proving the feasibility of constructing and operating such systems. The detailed results of the evaluation in the intensive-care domain are out of scope of the current paper, and we refer the reader to a more detailed source. In all of the letters composed by clinicians, there were at least two important items per letter missed that were included by the CliniText system. The clinicians' letters got a significantly better grade in three out of four measured quality parameters, as judged by an expert; however, the variance in the quality was much higher in the clinicians' letters. In addition, three clinicians answered questions based on the discharge letter 40% faster, and answered four out of the five questions equally well or significantly better, when using the CliniText-generated letters, than when using the clinician-composed letters. CONCLUSIONS: Constructing a working system for automated summarization in free text of large numbers of varying periods of multivariate longitudinal clinical data is feasible. So is the construction of a large knowledge base, designed to support such a system, in a complex clinical domain, such as the intensive-care domain. The integration of the quality and functionality results suggests that the optimal discharge letter should exploit both human and machine, possibly by creating a machine-generated draft that will be polished by a human clinician.

An architecture for a continuous, user-driven, and data-driven application of clinical guidelines and its evaluation.

OBJECTIVES: Design, implement, and evaluate a new architecture for realistic continuous guideline (GL)-based decision support, based on a series of requirements that we have identified, such as support for continuous care, for multiple task types, and for data-driven and user-driven modes. METHODS: We designed and implemented a new continuous GL-based support architecture, PICARD, which accesses a temporal reasoning engine, and provides several different types of application interfaces. We present the new architecture in detail in the current paper. To evaluate the architecture, we first performed a technical evaluation of the PICARD architecture, using 19 simulated scenarios in the preeclampsia/toxemia domain. We then performed a functional evaluation with the help of two domain experts, by generating patient records that simulate 60 decision points from six clinical guideline-based scenarios, lasting from two days to four weeks. Finally, 36 clinicians made manual decisions in half of the scenarios, and had access to the automated GL-based support in the other half. The measures used in all three experiments were correctness and completeness of the decisions relative to the GL. RESULTS: Mean correctness and completeness in the technical evaluation were 1±0.0 and 0.96±0.03 respectively. The functional evaluation produced only several minor comments from the two experts, mostly regarding the output's style; otherwise the system's recommendations were validated. In the clinically oriented evaluation, the 36 clinicians applied manually approximately 41% of the GL's recommended actions. Completeness increased to approximately 93% when using PICARD. Manual correctness was approximately 94.5%, and remained similar when using PICARD; but while 68% of the manual decisions included correct but redundant actions, only 3% of the actions included in decisions made when using PICARD were redundant. CONCLUSIONS: The PICARD architecture is technically feasible and is functionally valid, and addresses the realistic continuous GL-based application requirements that we have defined; in particular, the requirement for care over significant time frames. The use of the PICARD architecture in the domain we examined resulted in enhanced completeness and in reduction of redundancies, and is potentially beneficial for general GL-based management of chronic patients.

Improving condition severity classification with an efficient active learning based framework.

Classification of condition severity can be useful for discriminating among sets of conditions or phenotypes, for example when prioritizing patient care or for other healthcare purposes. Electronic Health Records (EHRs) represent a rich source of labeled information that can be harnessed for severity classification. The labeling of EHRs is expensive and in many cases requires employing professionals with high level of expertise. In this study, we demonstrate the use of Active Learning (AL) techniques to decrease expert labeling efforts. We employ three AL methods and demonstrate their ability to reduce labeling efforts while effectively discriminating condition severity. We incorporate three AL methods into a new framework based on the original CAESAR (Classification Approach for Extracting Severity Automatically from Electronic Health Records) framework to create the Active Learning Enhancement framework (CAESAR-ALE). We applied CAESAR-ALE to a dataset containing 516 conditions of varying severity levels that were manually labeled by seven experts. Our dataset, called the "CAESAR dataset," was created from the medical records of 1.9 million patients treated at Columbia University Medical Center (CUMC). All three AL methods decreased labelers' efforts compared to the learning methods applied by the original CAESER framework in which the classifier was trained on the entire set of conditions; depending on the AL strategy used in the current study, the reduction ranged from 48% to 64% that can result in significant savings, both in time and money. As for the PPV (precision) measure, CAESAR-ALE achieved more than 13% absolute improvement in the predictive capabilities of the framework when classifying conditions as severe. These results demonstrate the potential of AL methods to decrease the labeling efforts of medical experts, while increasing accuracy given the same (or even a smaller) number of acquired conditions. We also demonstrated that the methods included in the CAESAR-ALE framework (Exploitation and Combination_XA) are more robust to the use of human labelers with different levels of professional expertise.

Effect of surface coating on the photocatalytic function of hybrid CdS-Au nanorods.

Hybrid semiconductor-metal nanoparticles are interesting materials for use as photocatalysts due to their tunable properties and chemical processibility. Their function in the evolution of hydrogen in photocatalytic water splitting is the subject of intense current investigation. Here, the effects of the surface coatings on the photocatalytic function are studied, with Au-tipped CdS nanorods as a model hybrid nanoparticle system. Kinetic measurements of the hydrogen evolution rate following photocatalytic water reduction are performed on similar nanoparticles but with different surface coatings, including various types of thiolated alkyl ligands and different polymer coatings. The apparent hydrogen evolution quantum yields are found to strongly depend on the surface coating. The lowest yields are observed for thiolated alkyl ligands. Intermediate values are obtained with L-glutathione and poly(styrene-co-maleic anhydride) polymer coatings. The highest efficiency is obtained for polyethylenimine (PEI) polymer coating. These pronounced differences in the photocatalytic efficiencies are correlated with ultrafast transient absorption spectroscopy measurements, which show a faster bleach recovery for the PEI-coated hybrid nanoparticles, consistent with faster and more efficient charge separation. These differences are primarily attributed to the effects of surface passivation by the different coatings affecting the surface trapping of charge carriers that compete with effective charge separation required for the photocatalysis. Further support of this assignment is provided from steady-state emission and time-resolved spectral measurements, performed on related strongly fluorescing CdSe/CdS nanorods. The control and understanding of the effect of the surface coating of the hybrid nanosystems on the photocatalytic processes is of importance for the potential application of hybrid nanoparticles as photocatalysts.

Treatment Prediction in the ICU Using a Partitioned, Sequential, Deep Time Series Analysis.

We have developed a time-oriented machine-learning tool to predict the binary decision of administering a medication and the quantitative decision regarding the specific dose. We evaluated our tool on the MIMIC-IV ICU database, for three common medical scenarios. We use an LSTM based neural network, and considerably extend its use by introducing several new concepts. We partition the common 12-hour prediction horizon into three sub-windows. Partitioning models the treatment dynamics better, and allows the use of previous sub-windows' data as additional training data with improved performance. We also introduce a sequential prediction process, composed of a binary treatment-decision model, followed, when relevant, by a quantitative dose-decision model, with improved accuracy. Finally, we examined two methods for including non-temporal features, such as age, within the temporal network. Our results provide additional treatment-prediction tools, and thus another step towards a reliable and trustworthy decision-support system that reduces the clinicians' cognitive load.

Automated Process Mining and Learning of Therapeutic Actions in the Intensive Care Unit.

In this study, we implemented a hybrid approach, incorporating temporal data mining, machine learning, and process mining for modeling and predicting the course of treatment of Intensive Care Unit (ICU) patients. We used process mining algorithms to construct models of management of ICU patients. Then, we extracted the decision points from the mined models and used temporal data mining of the periods preceding the decision points to create temporal-pattern features. We trained classifiers to predict the next actions expected for each point. The methodology was evaluated on medical ICU data from the hypokalemia and hypoglycemia domains. The study's contributions include the representation of medical treatment trajectories of ICU patients using process models, and the integration of Temporal Data Mining and Machine Learning with Process Mining, to predict the next therapeutic actions in the ICU.