Patient healthcare trajectory. An essential monitoring tool: a systematic review

Contribution to pulmonary diseases diagnostic from X-ray images using innovative deep learning models

Pulmonary disease identification and characterization are among the most intriguing research topics of recent years since they require an accurate and prompt diagnosis. Although pulmonary radiography has helped in lung disease diagnosis, the interpretation of the radiographic image has always been a major concern for doctors and radiologists to reduce diagnosis errors. Due to their success in image classification and segmentation tasks, cutting-edge artificial intelligence techniques like machine learning (ML) and deep learning (DL) are widely encouraged to be applied in the field of diagnosing lung disorders and identifying them using medical images, particularly radiographic ones. For this end, the researchers are concurring to build systems based on these techniques in particular deep learning ones. In this paper, we proposed three deep-learning models that were trained to identify the presence of certain lung diseases using thoracic radiography. The first model, named "CovCXR-Net", identifies the COVID-19 disease (two cases: COVID-19 or normal). The second model, named "MDCXR3-Net", identifies the COVID-19 and pneumonia diseases (three cases: COVID-19, pneumonia, or normal), and the last model, named "MDCXR4-Net", is destined to identify the COVID-19, pneumonia and the pulmonary opacity diseases (4 cases: COVID-19, pneumonia, pulmonary opacity or normal). These models have proven their superiority in comparison with the state-of-the-art models and reached an accuracy of 99,09 %, 97.74 %, and 90,37 % respectively with three benchmarks.

Task-based assessment of resolution properties of CT images with a new index using deep convolutional neural network

In this study, we propose a method for obtaining a new index to evaluate the resolution properties of computed tomography (CT) images in a task-based manner. This method applies a deep convolutional neural network (DCNN) machine learning system trained on CT images with known modulation transfer function (MTF) values to output an index representing the resolution properties of the input CT image [i.e., the resolution property index (RPI)]. Sample CT images were obtained for training and testing of the DCNN by scanning the American Radiological Society phantom. Subsequently, the images were reconstructed using a filtered back projection algorithm with different reconstruction kernels. The circular edge method was used to measure the MTF values, which were used as teacher information for the DCNN. The resolution properties of the sample CT images used to train the DCNN were created by intentionally varying the field of view (FOV). Four FOV settings were considered. The results of adapting this method to the filtered back projection (FBP) and hybrid iterative reconstruction (h-IR) images indicated highly correlated values with the MTF10% in both cases. Furthermore, we demonstrated that the RPIs could be estimated in the same manner under the same imaging conditions and reconstruction kernels, even for other CT systems, where the DCNN was trained on CT systems produced by the same manufacturer. In conclusion, the RPI, which is a new index that represents the resolution property using the proposed method, can be used to evaluate the resolution of a CT system in a task-based manner.

Dementia risk analysis using temporal event modeling on a large real-world dataset

The objective of the study is to identify healthcare events leading to a diagnosis of dementia from a large real-world dataset. This study uses a data-driven approach to identify temporally ordered pairs and trajectories of healthcare codes in the electronic health record (EHR). This allows for discovery of novel temporal risk factors leading to an outcome of interest that may otherwise be unobvious. We identified several known (Down syndrome RR = 116.1, thiamine deficiency RR = 76.1, and Parkinson's disease RR = 41.1) and unknown (Brief psychotic disorder RR = 68.6, Toxic effect of metals RR = 40.4, and Schizoaffective disorders RR = 40.0) factors for a specific dementia diagnosis. The associations with the greatest risk for any dementia diagnosis were found to be primarily related to mental health (Brief psychotic disorder RR = 266.5, Dissociative and conversion disorders RR = 169.8), or neurologic conditions or procedures (Dystonia RR = 121.9, Lumbar Puncture RR = 119.0). Trajectory and clustering analysis identified factors related to cerebrovascular disorders, as well as diagnoses which increase the risk of toxic imbalances. The results of this study have the ability to provide valuable insights into potential patient progression towards dementia and improve recognition of patients at risk for developing dementia.

Analytical methods for identifying sequences of utilization in health data: a scoping review

BACKGROUND

Healthcare, as with other sectors, has undergone progressive digitalization, generating an ever-increasing wealth of data that enables research and the analysis of patient movement. This can help to evaluate treatment processes and outcomes, and in turn improve the quality of care. This scoping review provides an overview of the algorithms and methods that have been used to identify care pathways from healthcare utilization data.

METHOD

This review was conducted according to the methodology of the Joanna Briggs Institute and the Preferred Reporting Items for Systematic Reviews Extension for Scoping Reviews (PRISMA-ScR) Checklist. The PubMed, Web of Science, Scopus, and EconLit databases were searched and studies published in English between 2000 and 2021 considered. The search strategy used keywords divided into three categories: the method of data analysis, the requirement profile for the data, and the intended presentation of results. Criteria for inclusion were that health data were analyzed, the methodology used was described and that the chronology of care events was considered. In a two-stage review process, records were reviewed by two researchers independently for inclusion. Results were synthesized narratively.

RESULTS

The literature search yielded 2,865 entries; 51 studies met the inclusion criteria. Health data from different countries ([Formula: see text]) and of different types of disease ([Formula: see text]) were analyzed with respect to different care events. Applied methods can be divided into those identifying subsequences of care and those describing full care trajectories. Variants of pattern mining or Markov models were mostly used to extract subsequences, with clustering often applied to find care trajectories. Statistical algorithms such as rule mining, probability-based machine learning algorithms or a combination of methods were also applied. Clustering methods were sometimes used for data preparation or result compression. Further characteristics of the included studies are presented.

CONCLUSION

Various data mining methods are already being applied to gain insight from health data. The great heterogeneity of the methods used shows the need for a scoping review. We performed a narrative review and found that clustering methods currently dominate the literature for identifying complete care trajectories, while variants of pattern mining dominate for identifying subsequences of limited length.

"Healthcare should be the same for everyone": perceived inequities in therapeutic trajectories of adult patients with lung cancer in Chile, a qualitative study

Background

Globally, it has been reported that different social determinants of health affect health outcomes in lung cancer (LC). Research on the therapeutic trajectories of patients (TTP) is a novel field for identifying barriers and facilitators in health. The objective of this study was to reveal perceived differences in TTP with LC in Chile according to selected social determinants of health (SDH) and the experiences of patients, health professionals, and civil society leaders.

Methods

This is a qualitative paradigm, one case-study design. Online semi-structured interviews were conducted with patients with LC, health professionals, and civil society leaders. The strategies for the recruitment process included social networks, civil society organizations, health professionals, and the snowball technique. A thematic analysis was carried out.

Results

Selected SDH impact LC's TTP in Chile, particularly concerning health system access, health services, information, and patient navigation experiences. The analysis of the experiences of the participants allowed us to identify barriers related to the selected SDH in three stages of the TTP: initiation, examinations, and diagnosis and treatment. Individuals with limited education, those residing outside the capital, women, and those in the public health system encountered more barriers throughout their TTP.

Discussion

Study findings suggest that being a woman with low education, from the public health system, and not from the capital might represent one of the most powerful intersections for experiencing barriers to effective healthcare in LC in Chile. It is necessary to monitor the TTP from an SDH perspective to guarantee the rights of access, opportunity, quality, and financial protection.

Machine learning classification of plant genotypes grown under different light conditions through the integration of multi-scale time-series data

In order to mitigate the effects of a changing climate, agriculture requires more effective evaluation, selection, and production of crop cultivars in order to accelerate genotype-to-phenotype connections and the selection of beneficial traits. Critically, plant growth and development are highly dependent on sunlight, with light energy providing plants with the energy required to photosynthesize as well as a means to directly intersect with the environment in order to develop. In plant analyses, machine learning and deep learning techniques have a proven ability to learn plant growth patterns, including detection of disease, plant stress, and growth using a variety of image data. To date, however, studies have not assessed machine learning and deep learning algorithms for their ability to differentiate a large cohort of genotypes grown under several growth conditions using time-series data automatically acquired across multiple scales (daily and developmentally). Here, we extensively evaluate a wide range of machine learning and deep learning algorithms for their ability to differentiate 17 well-characterized photoreceptor deficient genotypes differing in their light detection capabilities grown under several different light conditions. Using algorithm performance measurements of precision, recall, F1-Score, and accuracy, we find that Suport Vector Machine (SVM) maintains the greatest classification accuracy, while a combined ConvLSTM2D deep learning model produces the best genotype classification results across the different growth conditions. Our successful integration of time-series growth data across multiple scales, genotypes and growth conditions sets a new foundational baseline from which more complex plant science traits can be assessed for genotype-to-phenotype connections.

Trajectories of care of community-dwelling people living with dementia: a multidimensional state sequence analysis

BACKGROUND

The type and level of healthcare services required to address the needs of persons living with dementia fluctuate over disease progression. Thus, their trajectories of care (the sequence of healthcare use over time) may vary significantly. We aimed to (1) propose a typology of trajectories of care among community-dwelling people living with dementia; (2) describe and compare their characteristics according to their respective trajectories; and (3) evaluate the association between trajectories membership, socioeconomic factors, and self-perceived health.

METHODS

This is an observational study using the data of the innovative Care Trajectories -Enriched Data (TorSaDE) cohort, a linkage between five waves of the Canadian Community Health Survey (CCHS), and health administrative data from the Quebec provincial health-insurance board. We analyzed data from 690 community-dwelling persons living with dementia who participated in at least one cycle of the CCHS (the date of the last CCHS completion is the index date). Trajectories of care were defined as sequences of healthcare use in the two years preceding the index date, using the following information: 1) Type of care units consulted (Hospitalization, Emergency department, Outpatient clinic, Primary care clinic); 2) Type of healthcare care professionals consulted (Geriatrician/psychiatrist/neurologist, Other specialists, Family physician).

RESULTS

Three distinct types of trajectories describe healthcare use in persons with dementia: 1) low healthcare use (n = 377; 54.6%); 2) high primary care use (n = 154; 22.3%); 3) high overall healthcare use (n = 159; 23.0%). Group 3 membership was associated with living in urban areas, a poorer perceived health status and higher comorbidity.

CONCLUSION

Further understanding how subgroups of patients use healthcare services over time could help highlight fragility areas in the allocation of care resources and implement best practices, especially in the context of resource shortage.

Biochemical surveillance versus clinical observation of term infants born after prolonged rupture of membranes - A quality assurance initiative

AIM

To examine whether biochemical surveillance vs clinical observation of term infants with prolonged rupture of membranes as a risk factor for early-onset sepsis is associated with differences in patient trajectories in maternity and neonatal intensive care units.

METHODS

A retrospective study of live-born infants with gestational age ≥ 37 + 0 weeks born after prolonged rupture of membranes (≥24 h) in four Norwegian hospitals 2017-2019. Two hospitals used biochemical surveillance, and two used predominantly clinical observation to identify early-onset sepsis cases.

RESULTS

The biochemical surveillance hospitals had more C-reactive protein measurements (p < 0.001), neonatal intensive care unit admissions (p < 0.001) and antibiotic treatment (p < 0.001). Hospitals using predominantly clinical observation initiated antibiotic treatment earlier in infants with suspected early-onset sepsis (p = 0.04) but not in infants fulfilling early-onset sepsis diagnostic criteria (p = 0.09). There was no difference in antibiotic treatment duration (p = 0.59), fraction of infants fulfilling early-onset sepsis diagnostic criteria (p = 0.49) or length of hospitalisation (p = 0.30), and no early-onset sepsis-related adverse outcomes.

CONCLUSION

The biochemical surveillance hospitals had more C-reactive protein measurements, but there was no difference in antibiotic treatment duration, early-onset sepsis cases, length of hospitalisation or adverse outcomes. Personnel resources needed for clinical surveillance should be weighed against the limitation of potentially painful procedures.

Artificial Intelligence in Biological Sciences

Artificial intelligence (AI), currently a cutting-edge concept, has the potential to improve the quality of life of human beings. The fields of AI and biological research are becoming more intertwined, and methods for extracting and applying the information stored in live organisms are constantly being refined. As the field of AI matures with more trained algorithms, the potential of its application in epidemiology, the study of host–pathogen interactions and drug designing widens. AI is now being applied in several fields of drug discovery, customized medicine, gene editing, radiography, image processing and medication management. More precise diagnosis and cost-effective treatment will be possible in the near future due to the application of AI-based technologies. In the field of agriculture, farmers have reduced waste, increased output and decreased the amount of time it takes to bring their goods to market due to the application of advanced AI-based approaches. Moreover, with the use of AI through machine learning (ML) and deep-learning-based smart programs, one can modify the metabolic pathways of living systems to obtain the best possible outputs with the minimal inputs. Such efforts can improve the industrial strains of microbial species to maximize the yield in the bio-based industrial setup. This article summarizes the potentials of AI and their application to several fields of biology, such as medicine, agriculture, and bio-based industry.

Needs assessment and planning for a clinic-community-based implementation program for hypertension control among blacks in New York City: a protocol paper

BACKGROUND

Hypertension (HTN) control among Blacks in the USA has become a major public health challenge. Barriers to HTN control exist at multiple levels including patient, physician, and the health system. Patients also encounter significant community-level barriers, such as poor linkage to social services that impact health (unstable housing, food access, transportation). We describe a multi-component needs assessment to inform the development, implementation, and evaluation of a program to improve HTN management within a large healthcare system in New York City (NYC).

METHODS

Guided by the Community-Based Participatory Research (CBPR) and Consolidated Framework for Implementation Research (CFIR) frameworks, data will be collected from four main sources: (1) quantitative surveys with health systems leadership, providers, and staff and with community-based organizations (CBOs) and faith-based organizations (FBOs); (2) qualitative interviews and focus groups with health systems leadership, providers, and staff and with CBOs and FBOs; (3) NYC Community Health Survey (CHS); and (4) New York University (NYU) Health system Epic Electronic Health Record (EHR) system. The data sources will allow for triangulation and synthesis of findings.

DISCUSSION

Findings from this comprehensive needs assessment will inform the development of a clinic-community-based practice facilitation program utilizing three multi-level evidence-based interventions (nurse case management, remote blood pressure (BP) monitoring, and social determinants of health (SDoH) support) integrated as a community-clinic linkage model for improved HTN control in Black patients. Integration of stakeholders' priorities, perspectives, and practices into the development of the program will improve adoption, sustainability, and the potential for scale-up.

TRIAL REGISTRATION

NCT05208450; registered on January 26, 2022.

Anxiety/Depression Predominance in Liaison-Psychiatry Users of a South-East Mexico Tertiary Hospital

Patients at tertiary hospitals may find themselves in need of mental health support due to the distress associated with the illness that may or not lead to a psychiatric condition. Here is an overview of the clinical cases treated by the liaison psychiatry service of a public tertiary hospital from Southeast Mexico during its first years of operation (2008–2018), with the purpose of gathering information about the status and needs of this population. A sample of 304 clinical records of patients treated for the first time by the psychiatry service was reviewed, and the distribution by demographic characteristics, diagnosis of mental illness and medical area of reference was analyzed. Anxiety and depression symptoms were the most frequent. Most patients were women, lived in Merida and returned after the first appointment. The neurology service referred most patients, yet most attended directly. General tertiary hospitals should prioritize integrating ad hoc mental and physical health care. Adult women with a profile of anxiety and/or depression would be the first target group. Some areas of opportunity for further research and improvement of mental health services are: preventive services for anxiety and depression, follow-up of patients, attention to relatives of patients at intensive care units, implementation of telehealth alternatives, training on mental health screening and inter- and intra-institutional collaboration.

Sequential Pattern Mining to Predict Medical In-Hospital Mortality from Administrative Data: Application to Acute Coronary Syndrome

Prediction of a medical outcome based on a trajectory of care has generated a lot of interest in medical research. In sequence prediction modeling, models based on machine learning (ML) techniques have proven their efficiency compared to other models. In addition, reducing model complexity is a challenge. Solutions have been proposed by introducing pattern mining techniques. Based on these results, we developed a new method to extract sets of relevant event sequences for medical events' prediction, applied to predict the risk of in-hospital mortality in acute coronary syndrome (ACS). From the French Hospital Discharge Database, we mined sequential patterns. They were further integrated into several predictive models using a text string distance to measure the similarity between patients' patterns of care. We computed combinations of similarity measurements and ML models commonly used. A Support Vector Machine model coupled with edit-based distance appeared as the most effective model. We obtained good results in terms of discrimination with the receiver operating characteristic curve scores ranging from 0.71 to 0.99 with a good overall accuracy. We demonstrated the interest of sequential patterns for event prediction. This could be a first step to a decision-support tool for the prevention of in-hospital death by ACS.

A conceptual model of Lean culture adoption in healthcare

Purpose

This work seeks to offer a greater understanding of Lean healthcare implementation challenges conceptually taking a situated cultural organizational change perspective.

Design/methodology/approach

A descriptive model of healthcare organizations’ Lean adoption trajectories is built using ripple and bridging modelization strategies from elements of three classic organizational change theories and knowledge from Lean, organizational culture, healthcare and operations management literature.

Findings

The “contingent Lean culture adoption” (CLCA) model suggests five theoretical trajectories the healthcare organizations may experience when conducting a Lean transformation. These trajectories evolve from a new concept of Lean cultural friction (LCF) which represents cultural friction that a healthcare organization encounters toward an ultimate Lean culture proficiency state through time. From high to low initial LCF, a healthcare organization may in its Lean proficiency course end up in three states: lower, similar or higher LCF situation.

Research limitations/implications

The CLCA model demonstrates the potential to be developed into a framework and possibly a Lean cultural friction theory pending further qualitative and quantitative validation.

Practical implications

The CLCA model may help healthcare managers to use more appropriate cultural change strategies during their organization’s Lean journey.

Originality/value

This work enriches the concept of Lean cultural change which may apply not only to healthcare organizations but also to other ones. It suggests the existence of a healthcare organization Lean culture proficiency archetype and introduces the notion of Lean cultural friction.

Research perspectives on animal health in the era of artificial intelligence

Leveraging artificial intelligence (AI) approaches in animal health (AH) makes it possible to address highly complex issues such as those encountered in quantitative and predictive epidemiology, animal/human precision-based medicine, or to study host × pathogen interactions. AI may contribute (i) to diagnosis and disease case detection, (ii) to more reliable predictions and reduced errors, (iii) to representing more realistically complex biological systems and rendering computing codes more readable to non-computer scientists, (iv) to speeding-up decisions and improving accuracy in risk analyses, and (v) to better targeted interventions and anticipated negative effects. In turn, challenges in AH may stimulate AI research due to specificity of AH systems, data, constraints, and analytical objectives. Based on a literature review of scientific papers at the interface between AI and AH covering the period 2009-2019, and interviews with French researchers positioned at this interface, the present study explains the main AH areas where various AI approaches are currently mobilised, how it may contribute to renew AH research issues and remove methodological or conceptual barriers. After presenting the possible obstacles and levers, we propose several recommendations to better grasp the challenge represented by the AH/AI interface. With the development of several recent concepts promoting a global and multisectoral perspective in the field of health, AI should contribute to defract the different disciplines in AH towards more transversal and integrative research.

Trajectories, bifurcations, and pseudo-time in large clinical datasets: applications to myocardial infarction and diabetes data

BACKGROUND

Large observational clinical datasets are becoming increasingly available for mining associations between various disease traits and administered therapy. These datasets can be considered as representations of the landscape of all possible disease conditions, in which a concrete disease state develops through stereotypical routes, characterized by "points of no return" and "final states" (such as lethal or recovery states). Extracting this information directly from the data remains challenging, especially in the case of synchronic (with a short-term follow-up) observations.

RESULTS

Here we suggest a semi-supervised methodology for the analysis of large clinical datasets, characterized by mixed data types and missing values, through modeling the geometrical data structure as a bouquet of bifurcating clinical trajectories. The methodology is based on application of elastic principal graphs, which can address simultaneously the tasks of dimensionality reduction, data visualization, clustering, feature selection, and quantifying the geodesic distances (pseudo-time) in partially ordered sequences of observations. The methodology allows a patient to be positioned on a particular clinical trajectory (pathological scenario) and the degree of progression along it to be characterized with a qualitative estimate of the uncertainty of the prognosis. We developed a tool ClinTrajan for clinical trajectory analysis implemented in the Python programming language. We test the methodology in 2 large publicly available datasets: myocardial infarction complications and readmission of diabetic patients data.

CONCLUSIONS

Our pseudo-time quantification-based approach makes it possible to apply the methods developed for dynamical disease phenotyping and illness trajectory analysis (diachronic data analysis) to synchronic observational data.

Patient or family perceived deterioration in functional status and outcome after intensive care admission: a retrospective cohort analysis of routinely collected data

OBJECTIVE

To explore the association of patient or family reported functional deterioration (defined by a single question) in the preceding year, with mortality outcome for those admitted to the intensive care unit (ICU).

DESIGN

Retrospective observational analysis of a routinely collected data source.

PARTICIPANTS

Patients that were admitted to the ICU at Northwick Park and St Marks Hospitals, London North West University Healthcare NHS Trust between 01 October 2017 to 15 June 2019 were included. Patients were excluded if they had a prior ICU admission during the existing hospital episode or if information on functional deterioration could not be retrieved from either the patient or their advocate.

PRIMARY OUTCOMES

Mortality at the point of hospital discharge and 1 year following admission to the ICU.

RESULTS

Of the 1006 patients who were admitted to the ICU during the study period, information on functional deterioration was available for 621 patients who were included in the analysis. From these, 251 (40.4%) patients had patient or family reported functional deterioration in the preceding year, while 370 (59.6%) patients had a perceived stable functional baseline. Comparing the two groups, mortality was significantly higher in those who had functionally deteriorated compared with those with stable baseline function, at the point of hospital discharge (45.4% vs 25.9%; p<0.0001) and at 1 year (59.4% vs 33.0%; p<0.0001).

CONCLUSION

Patient or family reported functional deterioration was significantly associated with higher mortality at the point of hospital discharge and at 1 year. The concept of functional deterioration in the lead up to ICU admission warrants further exploration.

Predictors of premature treatment termination in a large residential addiction medicine program

BACKGROUND

While inpatient programs are a common setting for addiction treatment, patients' premature termination is a major concern. Predicting premature treatment termination has the potential to substantially improve patient outcomes by identifying high-risk profiles and suggesting care paths that might reduce dropout. The current study examined the predictors of premature termination from an inpatient addiction medicine service.

METHODS

In 1082 patients admitted to a large inpatient addiction medicine service, we used intake assessments of severity of alcohol use disorder, illicit drug use disorder, post-traumatic stress disorder (PTSD), anxiety disorders, and major depressive disorder to predict planned termination (n = 922) or premature termination (n = 160). We used two complementary analytic approaches-traditional binary logistic regression and a data-driven latent profile analysis (LPA).

RESULTS

Binary logistic regression revealed that alcohol use severity, illicit drug use severity, and PTSD severity significantly predicted termination status, although alcohol use severity notably exhibited an inverse relationship. The LPA revealed four distinct profiles, with one profile exhibiting a significantly higher rate of premature termination and another exhibiting a significantly lower rate of premature termination. The high-risk profile was characterized by high drug severity, high comorbid psychopathology (PTSD, depression, and anxiety symptoms), but low alcohol severity. The low-risk profile was characterized by high alcohol severity, but low drug use and low comorbid psychopathology.

CONCLUSIONS

These results provide converging evidence that illicit drug severity and psychiatric severity, and particularly PTSD, were associated with premature termination. Moreover, the LPA revealed distinct latent subgroups of patients with meaningfully higher and lower risk of premature termination, suggesting that addiction services should develop strategies for identifying high-risk individuals or develop care paths for high-risk symptom clusters. Approaches that are trauma-informed or otherwise focus on the management of comorbid psychiatric conditions may be particularly appropriate for reducing premature termination.

SEIPS 3.0: Human-centered design of the patient journey for patient safety

The Systems Engineering Initiative for Patient Safety (SEIPS) and SEIPS 2.0 models provide a framework for integrating Human Factors and Ergonomics (HFE) in health care quality and patient safety improvement. As care becomes increasingly distributed over space and time, the "process" component of the SEIPS model needs to evolve and represent this additional complexity. In this paper, we review different ways that the process component of the SEIPS models have been described and applied. We then propose the SEIPS 3.0 model, which expands the process component, using the concept of the patient journey to describe the spatio-temporal distribution of patients' interactions with multiple care settings over time. This new SEIPS 3.0 sociotechnical systems approach to the patient journey and patient safety poses several conceptual and methodological challenges to HFE researchers and professionals, including the need to consider multiple perspectives, issues with genuine participation, and HFE work at the boundaries.

Evidence-based Clinical Decision Support Systems for the prediction and detection of three disease states in critical care: A systematic literature review

Background: Clinical decision support (CDS) systems have emerged as tools providing intelligent decision making to address challenges of critical care. CDS systems can be based on existing guidelines or best practices; and can also utilize machine learning to provide a diagnosis, recommendation, or therapy course. Methods: This research aimed to identify evidence-based study designs and outcome measures to determine the clinical effectiveness of clinical decision support systems in the detection and prediction of hemodynamic instability, respiratory distress, and infection within critical care settings. PubMed, ClinicalTrials.gov and Cochrane Database of Systematic Reviews were systematically searched to identify primary research published in English between 2013 and 2018. Studies conducted in the USA, Canada, UK, Germany and France with more than 10 participants per arm were included. Results: In studies on hemodynamic instability, the prediction and management of septic shock were the most researched topics followed by the early prediction of heart failure. For respiratory distress, the most popular topics were pneumonia detection and prediction followed by pulmonary embolisms. Given the importance of imaging and clinical notes, this area combined Machine Learning with image analysis and natural language processing. In studies on infection, the most researched areas were the detection, prediction, and management of sepsis, surgical site infections, as well as acute kidney injury. Overall, a variety of Machine Learning algorithms were utilized frequently, particularly support vector machines, boosting techniques, random forest classifiers and neural networks. Sensitivity, specificity, and ROC AUC were the most frequently reported performance measures. Conclusion: This review showed an increasing use of Machine Learning for CDS in all three areas. Large datasets are required for training these algorithms; making it imperative to appropriately address, challenges such as class imbalance, correct labelling of data and missing data. Recommendations are formulated for the development and successful adoption of CDS systems.

Evidence-based Clinical Decision Support Systems for the prediction and detection of three disease states in critical care: A systematic literature review

Background: Clinical decision support (CDS) systems have emerged as tools providing intelligent decision making to address challenges of critical care. CDS systems can be based on existing guidelines or best practices; and can also utilize machine learning to provide a diagnosis, recommendation, or therapy course. Methods: This research aimed to identify evidence-based study designs and outcome measures to determine the clinical effectiveness of clinical decision support systems in the detection and prediction of hemodynamic instability, respiratory distress, and infection within critical care settings. PubMed, ClinicalTrials.gov and Cochrane Database of Systematic Reviews were systematically searched to identify primary research published in English between 2013 and 2018. Studies conducted in the USA, Canada, UK, Germany and France with more than 10 participants per arm were included. Results: In studies on hemodynamic instability, the prediction and management of septic shock were the most researched topics followed by the early prediction of heart failure. For respiratory distress, the most popular topics were pneumonia detection and prediction followed by pulmonary embolisms. Given the importance of imaging and clinical notes, this area combined Machine Learning with image analysis and natural language processing. In studies on infection, the most researched areas were the detection, prediction, and management of sepsis, surgical site infections, as well as acute kidney injury. Overall, a variety of Machine Learning algorithms were utilized frequently, particularly support vector machines, boosting techniques, random forest classifiers and neural networks. Sensitivity, specificity, and ROC AUC were the most frequently reported performance measures. Conclusion: This review showed an increasing use of Machine Learning for CDS in all three areas. Large datasets are required for training these algorithms; making it imperative to appropriately address, challenges such as class imbalance, correct labelling of data and missing data. Recommendations are formulated for the development and successful adoption of CDS systems.

Multi-objective semi-supervised clustering to identify health service patterns for injured patients

Purpose

This study develops a pattern recognition method that identifies patterns based on their similarity and their association with the outcome of interest. The practical purpose of developing this pattern recognition method is to group patients, who are injured in transport accidents, in the early stages post-injury. This grouping is based on distinctive patterns in health service use within the first week post-injury. The groups also provide predictive information towards the total cost of medication process. As a result, the group of patients who have undesirable outcomes are identified as early as possible based health service use patterns.

Methods

We propose a multi-objective optimization model to group patients. An objective function is the cost function of k-medians clustering to recognize the similar patterns. Another objective function is the cross-validated root-mean-square error to examine the association with the total cost. The best grouping is obtained by minimizing both objective functions. As a result, the multi-objective optimization model is a semi-supervised clustering which learns health service use patterns in both unsupervised and supervised ways. We also introduce an evolutionary computation approach includes stochastic gradient descent and Pareto optimal solutions to find the optimal solution. In addition, we use the decision tree method to reproduce the optimal groups using an interpretable classification model.

Results

The results show that the proposed multi-objective semi-supervised clustering identifies distinct groups of health service uses and contributes to predict the total cost. The performance of the multi-objective model has been examined using two metrics such as the average silhouette width and the cross-validation error. The examination proves that the multi-objective model outperforms the single-objective ones. In addition, the interpretable classification model shows that imaging and therapeutic services are critical services in the first-week post-injury to group injured patients.

Conclusion

The proposed multi-objective semi-supervised clustering finds the optimal clusters that not only are well-separated from each other but can provide informative insights regarding the outcome of interest. It also overcomes two drawback of clustering methods such as being sensitive to the initial cluster centers and need for specifying the number of clusters.

Next Generation Networks: Featuring the Potential Role of Emerging Applications in Translational Oncology

Nowadays, networks are pervasively used as examples of models suitable to mathematically represent and visualize the complexity of systems associated with many diseases, including cancer. In the cancer context, the concept of network entropy has guided many studies focused on comparing equilibrium to disequilibrium (i.e., perturbed) conditions. Since these conditions reflect both structural and dynamic properties of network interaction maps, the derived topological characterizations offer precious support to conduct cancer inference. Recent innovative directions have emerged in network medicine addressing especially experimental omics approaches integrated with a variety of other data, from molecular to clinical and also electronic records, bioimaging etc. This work considers a few theoretically relevant concepts likely to impact the future of applications in personalized/precision/translational oncology. The focus goes to specific properties of networks that are still not commonly utilized or studied in the oncological domain, and they are: controllability, synchronization and symmetry. The examples here provided take inspiration from the consideration of metastatic processes, especially their progression through stages and their hallmark characteristics. Casting these processes into computational frameworks and identifying network states with specific modular configurations may be extremely useful to interpret or even understand dysregulation patterns underlying cancer, and associated events (onset, progression) and disease phenotypes.

Multi-level medical periodic patterns from human movement behaviors

Human movement behaviors could reveal many interesting medical patterns. Due to the advances in location-aware devices, a large volume of human movement behaviors has been captured in the form of spatio-temporal trajectories. These spatio-temporal trajectories are useful resources for medical data mining, and they could be used to classify which trajectory passes through medical centres and which one does not. Traditional approaches utilise time-series datasets while ignoring spatio-temporal semantics in order to detect periodic patterns in medical domains. They also fail to consider the inherent hierarchical nature of patterns. We investigate a medical data mining framework that generates multi-level medical periodic patterns. A Geolife dataset is used to test the feasibility and applicability of our framework. Experiments demonstrate that the proposed framework successfully distinguishes those who periodically visit medical centres from those who do not, and also to find multi-level medical periodic patterns revealing interesting hierarchical medical behaviours. One potential application includes an automated personalised medical service. For instance, medical institutions can send personalised relative medicine information to people who regularly visit certain medical centres. It will be useful for the discovery and diagnosis of diseases for patients.

Anticipatory Care in Potentially Preventable Hospitalizations: Making Data Sense of Complex Health Journeys

Purpose: Potentially preventable hospitalizations (PPH) are minimized when adults (usually with multiple morbidities ± frailty) benefit from alternatives to emergency hospital use. A complex systems and anticipatory journey approach to PPH, the Patient Journey Record System (PaJR) is proposed.

Application: PaJR is a web-based service supporting ≥weekly telephone calls by trained lay Care Guides (CG) to individuals at risk of PPH. The Victorian HealthLinks Chronic Care algorithm provides case finding from hospital big data. Prediction algorithms on call data helps optimize emergency hospital use through adaptive and anticipatory care. MonashWatch deployment incorporating PaJR is conducted by Monash Health in its Dandenong urban catchment area, Victoria, Australia.

Theory: A Complex Adaptive Systems (CAS) framework underpins PaJR, and recognizes unique individual journeys, their dependence on historical and biopsychosocial influences, and difficult to predict tipping points. Rosen's modeling relationship and anticipation theory additionally informed the CAS framework with data sense-making and care delivery. PaJR uses perceptions of current and future health (interoception) through ongoing conversations to anticipate possible tipping points. This allows for possible timely intervention in trajectories in the biopsychosocial dimensions of patients as “particulars” in their unique trajectories.

Evaluation: Monash Watch is actively monitoring 272 of 376 intervention patients, with 195 controls over 22 months (ongoing). Trajectories of poor health (SRH) and anticipation of worse/uncertain health (AH), and CG concerns statistically shifted at a tipping point, 3 days before admission in the subset who experienced ≥1 acute admission. The −3 day point was generally consistent across age and gender. Three randomly selected case studies demonstrate the processes of anticipatory and reactive care. PaJR-supported services achieved higher than pre-set targets—consistent reduction in acute bed days (20–25%) vs. target 10% and high levels of patient satisfaction.

Discussion: Anticipatory care is an emerging trajectory data analytic approach that uses human sense-making as its core metric demonstrates improvements in processes and outcomes. Multiple sources can provide big data to inform trajectory care, however simple tailored data collections may prove effective if they embrace human interoception and anticipation. Admission risk may be addressed with a simple data collections including SRH, AH, and CG perceptions, where practical.

Conclusion: Anticipatory care, as operationalized through PaJR approaches applied in MonashWatch, demonstrates processes and outcomes that successfully ameliorate PPH.

Emotion classification using flexible analytic wavelet transform for electroencephalogram signals

Emotion based brain computer system finds applications for impaired people to communicate with surroundings. In this paper, electroencephalogram (EEG) database of four emotions (happy, fear, sad, and relax) is recorded and flexible analytic wavelet transform (FAWT) is proposed for the emotion classification. FAWT analyzes the EEG signal into sub-bands and statistical measures are computed from the sub-bands for extraction of emotion specific information. The emotion classification performance of sub-band wise extracted features is examined over the variants of k-nearest-neighbor (KNN) classifier. The weighted-KNN provides the best emotion classification performance 86.1% as compared to other KNN variants. The proposed method shows better emotion classification performance as compared to other existing four emotions classification methods.