An empirical study of preprocessing techniques with convolutional neural networks for accurate detection of chronic ocular diseases using fundus images.

Chronic Ocular Diseases (COD) such as myopia, diabetic retinopathy, age-related macular degeneration, glaucoma, and cataract can affect the eye and may even lead to severe vision impairment or blindness. According to a recent World Health Organization (WHO) report on vision, at least 2.2 billion individuals worldwide suffer from vision impairment. Often, overt signs indicative of COD do not manifest until the disease has progressed to an advanced stage. However, if COD is detected early, vision impairment can be avoided by early intervention and cost-effective treatment. Ophthalmologists are trained to detect COD by examining certain minute changes in the retina, such as microaneurysms, macular edema, hemorrhages, and alterations in the blood vessels. The range of eye conditions is diverse, and each of these conditions requires a unique patient-specific treatment. Convolutional neural networks (CNNs) have demonstrated significant potential in multi-disciplinary fields, including the detection of a variety of eye diseases. In this study, we combined several preprocessing approaches with convolutional neural networks to accurately detect COD in eye fundus images. To the best of our knowledge, this is the first work that provides a qualitative analysis of preprocessing approaches for COD classification using CNN models. Experimental results demonstrate that CNNs trained on the region of interest segmented images outperform the models trained on the original input images by a substantial margin. Additionally, an ensemble of three preprocessing techniques outperformed other state-of-the-art approaches by 30% and 3%, in terms of Kappa and F 1 scores, respectively. The developed prototype has been extensively tested and can be evaluated on more comprehensive COD datasets for deployment in the clinical setup.

Examining the weekend effect across ICU performance metrics.

BACKGROUND: Known colloquially as the "weekend effect," the association between weekend admissions and increased mortality within hospital settings has become a highly contested topic over the last two decades. Drawing interest from practitioners and researchers alike, a sundry of works have emerged arguing for and against the presence of the effect across various patient cohorts. However, it has become evident that simply studying population characteristics is insufficient for understanding how the effect manifests. Rather, to truly understand the effect, investigations into its underlying factors must be considered. As such, the work presented in this manuscript serves to address this consideration by moving beyond identification of patient cohorts to examining the role of ICU performance. METHODS: Employing a comprehensive, publicly available database of electronic medical records (EMR), we began by utilizing multiple logistic regression to identify and isolate a specific cohort in which the weekend effect was present. Next, we leveraged the highly detailed nature of the EMR to evaluate ICU performance using well-established ICU quality scorecards to assess differences in clinical factors among patients admitted to an ICU on the weekend versus weekday. RESULTS: Our results demonstrate the weekend effect to be most prevalent among emergency surgery patients (OR 1.53; 95% CI 1.19, 1.96), specifically those diagnosed with circulatory diseases (P<.001). Differences between weekday and weekend admissions for this cohort included a variety of clinical factors such as ventilatory support and night-time discharges. CONCLUSIONS: This work reinforces the importance of accounting for differences in clinical factors as well as patient cohorts in studies investigating the weekend effect.

Incorporating medical code descriptions for diagnosis prediction in healthcare.

BACKGROUND: Diagnosis aims to predict the future health status of patients according to their historical electronic health records (EHR), which is an important yet challenging task in healthcare informatics. Existing diagnosis prediction approaches mainly employ recurrent neural networks (RNN) with attention mechanisms to make predictions. However, these approaches ignore the importance of code descriptions, i.e., the medical definitions of diagnosis codes. We believe that taking diagnosis code descriptions into account can help the state-of-the-art models not only to learn meaning code representations, but also to improve the predictive performance, especially when the EHR data are insufficient. METHODS: We propose a simple, but general diagnosis prediction framework, which includes two basic components: diagnosis code embedding and predictive model. To learn the interpretable code embeddings, we apply convolutional neural networks (CNN) to model medical descriptions of diagnosis codes extracted from online medical websites. The learned medical embedding matrix is used to embed the input visits into vector representations, which are fed into the predictive models. Any existing diagnosis prediction approach (referred to as the base model) can be cast into the proposed framework as the predictive model (called the enhanced model). RESULTS: We conduct experiments on two real medical datasets: the MIMIC-III dataset and the Heart Failure claim dataset. Experimental results show that the enhanced diagnosis prediction approaches significantly improve the prediction performance. Moreover, we validate the effectiveness of the proposed framework with insufficient EHR data. Finally, we visualize the learned medical code embeddings to show the interpretability of the proposed framework. CONCLUSIONS: Given the historical visit records of a patient, the proposed framework is able to predict the next visit information by incorporating medical code descriptions.

From narrative descriptions to MedDRA: automagically encoding adverse drug reactions.

CONTEXT: The collection of narrative spontaneous reports is an irreplaceable source for the prompt detection of suspected adverse drug reactions (ADRs). In such task qualified domain experts manually revise a huge amount of narrative descriptions and then encode texts according to MedDRA standard terminology. The manual annotation of narrative documents with medical terminology is a subtle and expensive task, since the number of reports is growing up day-by-day. OBJECTIVES: Natural Language Processing (NLP) applications can support the work of people responsible for pharmacovigilance. Our objective is to develop NLP algorithms and tools for the detection of ADR clinical terminology. Efficient applications can concretely improve the quality of the experts' revisions. NLP software can quickly analyze narrative texts and offer an encoding (i.e., a list of MedDRA terms) that the expert has to revise and validate. METHODS: MagiCoder, an NLP algorithm, is proposed for the automatic encoding of free-text descriptions into MedDRA terms. MagiCoder procedure is efficient in terms of computational complexity. We tested MagiCoder through several experiments. In the first one, we tested it on a large dataset of about 4500 manually revised reports, by performing an automated comparison between human and MagiCoder encoding. Moreover, we tested MagiCoder on a set of about 1800 reports, manually revised ex novo by some experts of the domain, who also compared automatic solutions with the gold reference standard. We also provide two initial experiments with reports written in English, giving a first evidence of the robustness of MagiCoder w.r.t. the change of the language. RESULTS: For the current base version of MagiCoder, we measured an average recall and precision of 86.9% and 91.8%, respectively. CONCLUSIONS: From a practical point of view, MagiCoder reduces the time required for encoding ADR reports. Pharmacologists have only to review and validate the MedDRA terms proposed by the application, instead of choosing the right terms among the 70 K low level terms of MedDRA. Such improvement in the efficiency of pharmacologists' work has a relevant impact also on the quality of the subsequent data analysis. We developed MagiCoder for the Italian pharmacovigilance language. However, our proposal is based on a general approach, not depending on the considered language nor the term dictionary.

Automatic recognition of symptom severity from psychiatric evaluation records.

This paper presents a novel method for automatically recognizing symptom severity by using natural language processing of psychiatric evaluation records to extract features that are processed by machine learning techniques to assign a severity score to each record evaluated in the 2016 RDoC for Psychiatry Challenge from CEGS/N-GRID. The natural language processing techniques focused on (a) discerning the discourse information expressed in questions and answers; (b) identifying medical concepts that relate to mental disorders; and (c) accounting for the role of negation. The machine learning techniques rely on the assumptions that (1) the severity of a patient's positive valence symptoms exists on a latent continuous spectrum and (2) all the patient's answers and narratives documented in the psychological evaluation records are informed by the patient's latent severity score along this spectrum. These assumptions motivated our two-step machine learning framework for automatically recognizing psychological symptom severity. In the first step, the latent continuous severity score is inferred from each record; in the second step, the severity score is mapped to one of the four discrete severity levels used in the CEGS/N-GRID challenge. We evaluated three methods for inferring the latent severity score associated with each record: (i) pointwise ridge regression; (ii) pairwise comparison-based classification; and (iii) a hybrid approach combining pointwise regression and the pairwise classifier. The second step was implemented using a tree of cascading support vector machine (SVM) classifiers. While the official evaluation results indicate that all three methods are promising, the hybrid approach not only outperformed the pairwise and pointwise methods, but also produced the second highest performance of all submissions to the CEGS/N-GRID challenge with a normalized MAE score of 84.093% (where higher numbers indicate better performance). These evaluation results enabled us to observe that, for this task, considering pairwise information can produce more accurate severity scores than pointwise regression - an approach widely used in other systems for assigning severity scores. Moreover, our analysis indicates that using a cascading SVM tree outperforms traditional SVM classification methods for the purpose of determining discrete severity levels.

A Systematic Review of Wearable Patient Monitoring Systems - Current Challenges and Opportunities for Clinical Adoption.

The aim of this review is to investigate barriers and challenges of wearable patient monitoring (WPM) solutions adopted by clinicians in acute, as well as in community, care settings. Currently, healthcare providers are coping with ever-growing healthcare challenges including an ageing population, chronic diseases, the cost of hospitalization, and the risk of medical errors. WPM systems are a potential solution for addressing some of these challenges by enabling advanced sensors, wearable technology, and secure and effective communication platforms between the clinicians and patients. A total of 791 articles were screened and 20 were selected for this review. The most common publication venue was conference proceedings (13, 54%). This review only considered recent studies published between 2015 and 2017. The identified studies involved chronic conditions (6, 30%), rehabilitation (7, 35%), cardiovascular diseases (4, 20%), falls (2, 10%) and mental health (1, 5%). Most studies focussed on the system aspects of WPM solutions including advanced sensors, wireless data collection, communication platform and clinical usability based on a specific area or disease. The current studies are progressing with localized sensor-software integration to solve a specific use-case/health area using non-scalable and 'silo' solutions. There is further work required regarding interoperability and clinical acceptance challenges. The advancement of wearable technology and possibilities of using machine learning and artificial intelligence in healthcare is a concept that has been investigated by many studies. We believe future patient monitoring and medical treatments will build upon efficient and affordable solutions of wearable technology.

Transfer Learning for Class Imbalance Problems with Inadequate Data.

A fundamental problem in data mining is to effectively build robust classifiers in the presence of skewed data distributions. Class imbalance classifiers are trained specifically for skewed distribution datasets. Existing methods assume an ample supply of training examples as a fundamental prerequisite for constructing an effective classifier. However, when sufficient data is not readily available, the development of a representative classification algorithm becomes even more difficult due to the unequal distribution between classes. We provide a unified framework that will potentially take advantage of auxiliary data using a transfer learning mechanism and simultaneously build a robust classifier to tackle this imbalance issue in the presence of few training samples in a particular target domain of interest. Transfer learning methods use auxiliary data to augment learning when training examples are not sufficient and in this paper we will develop a method that is optimized to simultaneously augment the training data and induce balance into skewed datasets. We propose a novel boosting based instance-transfer classifier with a label-dependent update mechanism that simultaneously compensates for class imbalance and incorporates samples from an auxiliary domain to improve classification. We provide theoretical and empirical validation of our method and apply to healthcare and text classification applications.

The politics of healthcare informatics: knowledge management using an electronic medical record system.

The design and implementation of an electronic medical record system pose significant epistemological and practical complexities. Despite optimistic assessments of their potential contribution to the quality of care, their implementation has been problematic, and their actual employment in various clinical settings remains controversial. Little is known about how their use actually mediates knowing. Employing a variety of qualitative research methods, this article attempts an answer by illustrating how omitting, editing and excessive reporting were employed as part of nurses' and physicians' political efforts to shape knowledge production and knowledge sharing in a technologically mediated healthcare setting.

Implementation of an electronic health records system within an interprofessional model of care.

Implementation of electronic health records (EHR) systems is challenging even in traditional healthcare settings, where administrative and clinical roles and responsibilities are clearly defined. However, even in these traditional settings the conflicting needs of stakeholders can trigger hierarchical decision-making processes that reflect the traditional power structures in healthcare today. These traditional processes are not structured to allow for incorporation of new patient-care models such as patient-centered care and interprofessional teams. New processes for EHR implementation and evaluation will be required as healthcare shifts to a patient-centered model that includes patients, families, multiple agencies, and interprofessional teams in short- and long-term clinical decision-making. This new model will be enabled by healthcare information technology and defined by information flow, workflow, and communication needs. We describe a model in development for the configuration and implementation of an EHR system in an interprofessional, interagency, free-clinic setting. The model uses a formative evaluation process that is rooted in usability to configure the EHR to fully support the needs of the variety of providers working as an interprofessional team. For this model to succeed, it must include informaticists as equal and essential members of the healthcare team.

YouTube Videos for Public Health Literacy? A Machine Learning Pipeline to Curate Covid-19 Videos.

The COVID-19 pandemic has highlighted the dire necessity to improve public health literacy for societal resilience. YouTube provides a vast repository of user-generated health information in a multi-media-rich format which may be easier for the public to understand and use if major concerns about content quality and accuracy are addressed. This study develops an automated solution to identify, retrieve and shortlist medically relevant and understandable YouTube videos that domain experts can subsequently review and recommend for disseminating and educating the public on the COVID-19 pandemic and similar public health outbreaks. Our approach leverages domain knowledge from human experts and machine learning and natural language processing methods to provide a scalable, replicable, and generalizable approach that can also be applied to enhance the management of many health conditions.

The Contribution of Informatics to Overcoming the Covid-19 Fake News Outbreak by Learning to Navigate the Infodemic.

Daily, people are being exposed to an enormous amount of Covid-19 information, but not all of it is reliable. This phenomenon seriously affects the public health policy effectiveness, because there is a lot of misleading or inaccurate information, which is spreading rapidly and makes it more difficult to restrict the pandemic. Healthcare informatics has emerged as a diverse and important new field. Healthcare informatics applications are becoming more and more popular and are providing easy access to new sources of knowledge. This way, the quality of patient care will improve and productivity will increase. However, people should also learn how to navigate this infodemic properly.

A data-centric artificial intelligent and extended reality technology in smart healthcare systems.

Extended reality (XR) solutions are quietly maturing, and their novel use cases are already being investigated, particularly in the healthcare industry. By 2022, the extended reality market is anticipated to be worth $209 billion. Certain diseases, such as Alzheimer's, Schizophrenia, Stroke rehabilitation stimulating specific areas of the patient's brain, healing brain injuries, surgeon training, realistic 3D visualization, touch-free interfaces, and teaching social skills to children with autism, have shown promising results with XR-assisted treatments. Similar effects have been used in video game therapies like Akili Interactive's EndeavorRx, which has previously been approved by the Food and Drug Administration (FDA) as a treatment regimen for children with attention deficit hyperactivity disorder (ADHD). However, while these improvements have received positive feedback, the field of XR-assisted patient treatment is in its infancy. The growth of XR in the healthcare sphere has the potential to transform the delivery of medical services. Imagine an elderly patient in a remote setting having a consultation with a world-renowned expert without ever having to leave their house. Rather than operating on cadavers in a medical facility, a surgical resident does surgery in a virtual setting at home. On the first try, a nurse uses a vein finder to implant an IV. Through cognitive treatment in a virtual world, a war veteran recovers from post-traumatic stress disorder (PTSD). The paper discusses the potential impact of XR in transforming the healthcare industry, as well as its use cases, challenges, XR tools and techniques for intelligent health care, recent developments of XR in intelligent healthcare services, and the potential benefits and future aspects of XR techniques in the medical domain.

The role of data science in healthcare advancements: applications, benefits, and future prospects.

Data science is an interdisciplinary field that extracts knowledge and insights from many structural and unstructured data, using scientific methods, data mining techniques, machine-learning algorithms, and big data. The healthcare industry generates large datasets of useful information on patient demography, treatment plans, results of medical examinations, insurance, etc. The data collected from the Internet of Things (IoT) devices attract the attention of data scientists. Data science provides aid to process, manage, analyze, and assimilate the large quantities of fragmented, structured, and unstructured data created by healthcare systems. This data requires effective management and analysis to acquire factual results. The process of data cleansing, data mining, data preparation, and data analysis used in healthcare applications is reviewed and discussed in the article. The article provides an insight into the status and prospects of big data analytics in healthcare, highlights the advantages, describes the frameworks and techniques used, briefs about the challenges faced currently, and discusses viable solutions. Data science and big data analytics can provide practical insights and aid in the decision-making of strategic decisions concerning the health system. It helps build a comprehensive view of patients, consumers, and clinicians. Data-driven decision-making opens up new possibilities to boost healthcare quality.

Explainable Artificial Intelligence for Predictive Modeling in Healthcare.

The principle behind artificial intelligence is mimicking human intelligence in the way that it can perform tasks, recognize patterns, or predict outcomes through learning from the acquired data of various sources. Artificial intelligence and machine learning algorithms have been widely used in autonomous driving, recommender systems in electronic commerce and social media, fintech, natural language understanding, and question answering systems. Artificial intelligence is also gradually changing the landscape of healthcare research (Yu et al. in Biomed Eng 2:719-731, 25). The rule-based approach that relied on the curation of medical knowledge and the construction of robust decision rules had drawn significant attention in diagnosing diseases and clinical decision support since half a century ago. In recent years, machine learning algorithms such as deep learning that can account for complex interactions between features is shown to be promising in predictive modeling in healthcare (Deo in Circulation 132:1920-1930, 26). Although many of these artificial intelligence and machine learning algorithms can achieve remarkably high performance, it is often difficult to be completely adopted in practical clinical environments due to the lack of explainability in some of these algorithms. Explainable artificial intelligence (XAI) is emerging to assist in the communication of internal decisions, behavior, and actions to health care professionals. Through explaining the prediction outcomes, XAI gains the trust of the clinicians as they may learn how to apply the predictive modeling in practical situations instead of blindly following the predictions. There are still many scenarios to explore how to make XAI effective in clinical settings due to the complexity of medical knowledge.

GAR-Net: Guided Attention Residual Network for Polyp Segmentation from Colonoscopy Video Frames.

Colorectal Cancer is one of the most common cancers found in human beings, and polyps are the predecessor of this cancer. Accurate Computer-Aided polyp detection and segmentation system can help endoscopists to detect abnormal tissues and polyps during colonoscopy examination, thereby reducing the chance of polyps growing into cancer. Many of the existing techniques fail to delineate the polyps accurately and produce a noisy/broken output map if the shape and size of the polyp are irregular or small. We propose an end-to-end pixel-wise polyp segmentation model named Guided Attention Residual Network (GAR-Net) by combining the power of both residual blocks and attention mechanisms to obtain a refined continuous segmentation map. An enhanced Residual Block is proposed that suppresses the noise and captures low-level feature maps, thereby facilitating information flow for a more accurate semantic segmentation. We propose a special learning technique with a novel attention mechanism called Guided Attention Learning that can capture the refined attention maps both in earlier and deeper layers regardless of the size and shape of the polyp. To study the effectiveness of the proposed GAR-Net, various experiments were carried out on two benchmark collections viz., CVC-ClinicDB (CVC-612) and Kvasir-SEG dataset. From the experimental evaluations, it is shown that GAR-Net outperforms other previously proposed models such as FCN8, SegNet, U-Net, U-Net with Gated Attention, ResUNet, and DeepLabv3. Our proposed model achieves 91% Dice co-efficient and 83.12% mean Intersection over Union (mIoU) on the benchmark CVC-ClinicDB (CVC-612) dataset and 89.15% dice co-efficient and 81.58% mean Intersection over Union (mIoU) on the Kvasir-SEG dataset. The proposed GAR-Net model provides a robust solution for polyp segmentation from colonoscopy video frames.

A survey of data element perspective: Application of artificial intelligence in health big data.

Artificial intelligence (AI) based on the perspective of data elements is widely used in the healthcare informatics domain. Large amounts of clinical data from electronic medical records (EMRs), electronic health records (EHRs), and electroencephalography records (EEGs) have been generated and collected at an unprecedented speed and scale. For instance, the new generation of wearable technologies enables easy-collecting peoples' daily health data such as blood pressure, blood glucose, and physiological data, as well as the application of EHRs documenting large amounts of patient data. The cost of acquiring and processing health big data is expected to reduce dramatically with the help of AI technologies and open-source big data platforms such as Hadoop and Spark. The application of AI technologies in health big data presents new opportunities to discover the relationship among living habits, sports, inheritances, diseases, symptoms, and drugs. Meanwhile, with the development of fast-growing AI technologies, many promising methodologies are proposed in the healthcare field recently. In this paper, we review and discuss the application of machine learning (ML) methods in health big data in two major aspects: (1) Special features of health big data including multimodal, incompletion, time validation, redundancy, and privacy. (2) ML methodologies in the healthcare field including classification, regression, clustering, and association. Furthermore, we review the recent progress and breakthroughs of automatic diagnosis in health big data and summarize the challenges, gaps, and opportunities to improve and advance automatic diagnosis in the health big data field.

Use of web-based health information portals in primary health care: Experience from a rural Primary Health Centre in Haryana.

BACKGROUND: Health care informatics is the scientific field that deals with the data capture, storage, retrieval, and use of biomedical data, information, and knowledge for problem solving and decision-making. The objectives of the study were to describe the web-based portals used at the Primary Health Centre (PHC) and to appraise its utilization at the local level. METHODS: Various methodologies included observation of portal use, record review, interview of stakeholders using the portals. RESULTS: Health Workers workload increased because of physical record entry and time spent for entry in web-based health information portals. Web-based portals did not have options for utilization of the data generated at the PHC level. The options of feedback and helpline were not universally available. CONCLUSION: Web-based portals are integral part of health system at primary healthcare level. Adequate utilization of web-based health information portals may lead to efficient provision of health services at the primary health care level.

A Systematic Approach to Supporting Faculty Knowledge Development in Nursing and Health Informatics.

Using a systematic communication strategy the knowledge of nursing/health informatics amongst Faculty members has been developed resulting in the inclusion of informatics across the curriculum as part of the essential role of nurses and other healthcare practitioners in all areas of practice.

An Efficient Agent Based Data Management Method of NoSQL Environments for Health Care Applications.

BACKGROUND: As medical knowledge is continuously expanding and diversely located, Health Information Technology (HIT) applications are proposed as a good prospect for improving not only the efficiency and the effectiveness but also the quality of healthcare services delivery. The technologies expected to shape such innovative HIT architectures include: Mobile agents (Mas) and NoSQL technologies. Mobile agents provide an inherent way of tackling distributed problems of accessing heterogeneous and spatially diverse data sources. NoSQL technology gains ground for the development of scalable applications with non-static and open data schema from complex and diverse sources. METHODS AND DESIGN: This paper conducts a twofold study: It attempts a literature review of the applications based on the mobile agent (MA) and NoSQL technologies for healthcare support services. Subsequently, a pilot system evaluates the NoSQL technology against the relational one within a distributed environment based on mobile agents for information retrieval. Its objective is to study the feasibility of developing systems that will employ ontological data representation and task implementation through mobile agents towards flexible and transparent health data monitoring. RESULTS AND DISCUSSION: The articles studied focus on applying mobile agents for patient support and healthcare services provision thus as to make a positive contribution to the treatment of chronic diseases. In addition, attention is put on the design of platform neutral techniques for clinical data gathering and dissemination over NoSQL. The experimental environment was based on the Apache Jena Fuseki NoSQL server and the JAVA Agent DEvelopment Framework -JADE agent platform. The results reveal that the NoSQL implementation outperforms the standard relational one.

Knowledge-Infused Abstractive Summarization of Clinical Diagnostic Interviews: Framework Development Study.

BACKGROUND: In clinical diagnostic interviews, mental health professionals (MHPs) implement a care practice that involves asking open questions (eg, "What do you want from your life?" "What have you tried before to bring change in your life?") while listening empathetically to patients. During these interviews, MHPs attempted to build a trusting human-centered relationship while collecting data necessary for professional medical and psychiatric care. Often, because of the social stigma of mental health disorders, patient discomfort in discussing their presenting problem may add additional complexities and nuances to the language they use, that is, hidden signals among noisy content. Therefore, a focused, well-formed, and elaborative summary of clinical interviews is critical to MHPs in making informed decisions by enabling a more profound exploration of a patient's behavior, especially when it endangers life. OBJECTIVE: The aim of this study is to propose an unsupervised, knowledge-infused abstractive summarization (KiAS) approach that generates summaries to enable MHPs to perform a well-informed follow-up with patients to improve the existing summarization methods built on frequency heuristics by creating more informative summaries. METHODS: Our approach incorporated domain knowledge from the Patient Health Questionnaire-9 lexicon into an integer linear programming framework that optimizes linguistic quality and informativeness. We used 3 baseline approaches: extractive summarization using the SumBasic algorithm, abstractive summarization using integer linear programming without the infusion of knowledge, and abstraction over extractive summarization to evaluate the performance of KiAS. The capability of KiAS on the Distress Analysis Interview Corpus-Wizard of Oz data set was demonstrated through interpretable qualitative and quantitative evaluations. RESULTS: KiAS generates summaries (7 sentences on average) that capture informative questions and responses exchanged during long (58 sentences on average), ambiguous, and sparse clinical diagnostic interviews. The summaries generated using KiAS improved upon the 3 baselines by 23.3%, 4.4%, 2.5%, and 2.2% for thematic overlap, Flesch Reading Ease, contextual similarity, and Jensen Shannon divergence, respectively. On the Recall-Oriented Understudy for Gisting Evaluation-2 and Recall-Oriented Understudy for Gisting Evaluation-L metrics, KiAS showed an improvement of 61% and 49%, respectively. We validated the quality of the generated summaries through visual inspection and substantial interrater agreement from MHPs. CONCLUSIONS: Our collaborator MHPs observed the potential utility and significant impact of KiAS in leveraging valuable but voluminous communications that take place outside of normally scheduled clinical appointments. This study shows promise in generating semantically relevant summaries that will help MHPs make informed decisions about patient status.