Challenges and barriers of using large language models (LLM) such as ChatGPT for diagnostic medicine with a focus on digital pathology - a recent scoping review.

BACKGROUND: The integration of large language models (LLMs) like ChatGPT in diagnostic medicine, with a focus on digital pathology, has garnered significant attention. However, understanding the challenges and barriers associated with the use of LLMs in this context is crucial for their successful implementation. METHODS: A scoping review was conducted to explore the challenges and barriers of using LLMs, in diagnostic medicine with a focus on digital pathology. A comprehensive search was conducted using electronic databases, including PubMed and Google Scholar, for relevant articles published within the past four years. The selected articles were critically analyzed to identify and summarize the challenges and barriers reported in the literature. RESULTS: The scoping review identified several challenges and barriers associated with the use of LLMs in diagnostic medicine. These included limitations in contextual understanding and interpretability, biases in training data, ethical considerations, impact on healthcare professionals, and regulatory concerns. Contextual understanding and interpretability challenges arise due to the lack of true understanding of medical concepts and lack of these models being explicitly trained on medical records selected by trained professionals, and the black-box nature of LLMs. Biases in training data pose a risk of perpetuating disparities and inaccuracies in diagnoses. Ethical considerations include patient privacy, data security, and responsible AI use. The integration of LLMs may impact healthcare professionals' autonomy and decision-making abilities. Regulatory concerns surround the need for guidelines and frameworks to ensure safe and ethical implementation. CONCLUSION: The scoping review highlights the challenges and barriers of using LLMs in diagnostic medicine with a focus on digital pathology. Understanding these challenges is essential for addressing the limitations and developing strategies to overcome barriers. It is critical for health professionals to be involved in the selection of data and fine tuning of the models. Further research, validation, and collaboration between AI developers, healthcare professionals, and regulatory bodies are necessary to ensure the responsible and effective integration of LLMs in diagnostic medicine.

Use of pager devices in New Zealand public hospitals as a critical communication tool: Barriers & way forward.

Objectives: The aim of this study was to analyse the current use, identify challenges and barriers and propose a way forward for the use of the pager devices in the in-hospital communications. Methods: Initially, 447 studies were identified through database searching. After checking against the eligibility, 39 studies were included. Full-text records were retrieved and reviewed by two authors. After excluding unrelated studies and duplicate records, a total of 12 articles were selected for the final review. Results: The use of pagers often lacks standardisation, content, format, urgency level, and clarity within the message. Some studies reported that medical staff preferred in-person interactions with consults instead of communicating over the phone or pagers. Productive communication can reduce the turnaround time by up to 50%. The key challenges are; (1) data security and privacy, (2) timely acknowledgement of received communication, (3) lack of two-way communications causing issues in critical care situations and (4) there is no standard process for the in-hospital communications. Conclusion: We found that the clinicians' age, experience, speciality and preferences greatly matter and influence the selection of tools and technology in healthcare. With revolutionary advances in technology, smartphones have inevitably become beneficial to healthcare, owing to multiple instant messaging applications (apps) that can streamline encrypted clinical communication between medical teams and could be safely used for in-hospital communications.

Vital signs and early warning score monitoring: perceptions of clinical staff about current practices and introducing an electronic rapid response system.

Aims and objectives: This study investigated clinical staff perceptions of learning about current monitoring practices and the planned introduction of an electronic system for patient monitoring. The aim of this research was to evaluate the perceptions of clinical staff (nurses and doctors) about the perceived strengths and weaknesses of the current state of the rapid response system (RRS) and how those strengths and weakness would be affected by introducing an electronic RRS. Methods: This research applied a descriptive study methodology. Two detailed sessions on demonstration on the electronic RRS for measuring and recording vital signs and the electronic Early Warning System (EWS) were followed by two structured surveys administered through an online portal (SurveyMonkey) for nurses and doctors working at Taranaki District Health Board. The study was planned and conducted between October 2020 and May 2021 at Taranaki Base Hospital, New Plymouth, New Zealand. Results: We found that the perceptions of clinical staff were a combination of key practice issues with current manual monitoring, expectations of improved visibility of vital sign charts, better communication between staff and thus improved patient care with the introduction of an electronic system. A majority (24, 60%) of nurses reported that, when called to assess deteriorating patients, the responders arrive at bedside within 5-30 min and an additional 11 (27%) said the responders arrive within 5 min. That is a collective 87% responder arrival within 30 min. Conclusion: Staff believe that an electronic RRS could improve communication, speed up decision making and have a positive impact on patient outcomes.

Failure mode and effect analysis (FMEA) to identify and mitigate failures in a hospital rapid response system (RRS).

We performed FMEA on the existing RRS with the help of routine users of the RRS who acted as subject matter experts and evaluated the failures for their criticality using the Risk Priority Number approach based on their experience of the RRS. The FMEA found 35 potential failure modes and 101 failure mode effects across 13 process steps of the RRS. The afferent limb of RRS was found to be more prone to these failures (62, 61.4%) than the efferent limb of the RRS (39, 38.6%). Modification of calling criteria (12, 11.9%) and calculation of New Zealand Early Warning Scores (NZEWS) calculation (11, 10.9%) steps were found to potentially give rise to the highest number of these failures. Causes of these failures include human error and related factors (35, 34.7%), staff workload/staffing levels (30, 29.7%) and limitations due to paper-based charts and organisational factors (n = 30, 29.7%). The demonstrated electronic system was found to potentially eliminate or reduce the likelihood of 71 (70.2%) failures. The failures not eliminated by the electronic RRS require targeted corrective measures including scenario-based training and education, and revised calling criteria to include triggers for hypothermia and high systolic blood pressure.

A systematic review of rapid response applications based on early warning score for early detection of inpatient deterioration.

AIM: The aim of this study was to investigate the effectiveness of current rapid response applications available in acute care settings for escalation of patient deterioration. Current challenges and barriers, as well as key recommendations, were also discussed. METHODS: We adopted PRISMA review methodology and screened a total of 559 articles. After considering the eligibility and selection criteria, we selected 13 articles published between 2015 and 2019. The selection criteria were based on the inclusion of studies that report on the advancement made to the current practice for providing rapid response to the patient deterioration in acute care settings. RESULTS: We found that current rapid response applications are complicated and time-consuming for detecting inpatient deterioration. Existing applications are either siloed or challenging to use, where clinicians are required to move between two or three different applications to complete an end-to-end patient escalation workflow - from vital signs collection to escalation of deteriorating patients. We found significant differences in escalation and responses when using an electronic tool compared to the manual approach. Moreover, encouraging results were reported in extensive documentation of vital signs and timely alerts for patient deterioration. CONCLUSION: The electronic vital signs monitoring applications are proved to be efficient and clinically suitable if they are user-friendly and interoperable. As an outcome, several key recommendations and features were identified that would be crucial to the successful implementation of any rapid response system in all clinical settings.

Early Detection of Prediabetes and T2DM Using Wearable Sensors and Internet-of-Things-Based Monitoring Applications.

BACKGROUND: Prediabetes and type 2 diabetes mellitus (T2DM) are one of the major long-term health conditions affecting global healthcare delivery. One of the few effective approaches is to actively manage diabetes via a healthy and active lifestyle. OBJECTIVES: This research is focused on early detection of prediabetes and T2DM using wearable technology and Internet-of-Things-based monitoring applications. METHODS: We developed an artificial intelligence model based on adaptive neuro-fuzzy inference to detect prediabetes and T2DM via individualized monitoring. The key contributing factors to the proposed model include heart rate, heart rate variability, breathing rate, breathing volume, and activity data (steps, cadence, and calories). The data was collected using an advanced wearable body vest and combined with manual recordings of blood glucose, height, weight, age, and sex. The model analyzed the data alongside a clinical knowledgebase. Fuzzy rules were used to establish baseline values via existing interventions, clinical guidelines, and protocols. RESULTS: The proposed model was tested and validated using Kappa analysis and achieved an overall agreement of 91%. CONCLUSION: We also present a 2-year follow-up observation from the prediction results of the original model. Moreover, the diabetic profile of a participant using M-health applications and a wearable vest (smart shirt) improved when compared to the traditional/routine practice.

A Usability and User-Experience Analysis of VitalsAssist: A mHealth Application to Monitor Vital Signs in Acute Care Settings.

M-health applications are playing an important role in current healthcare delivery, individual's health and well-being. Usability of mHealth applications (apps) is a critical factor for the success of the apps, yet this is often overlooked in the current health care solutions in primary care, secondary (acute) care, community care and especially in remote patient monitoring applications. This work aimed to co-design the vital signs monitoring application with end-users and clinicians. The co-design user-experience includes goals and objectives, participant inclusion and exclusion criteria, task list, testing documentation, laboratory-based usability testing and data analysis for identifying gaps and opportunities. The study found two main issues from the usability analysis, presentation of the information such as use of icons, text and graphs and clinical workflow related matters such as the number of mandatory steps required to finish a task.

A machine learning model for predicting risk of hospital readmission within 30 days of discharge: validated with LACE index and patient at risk of hospital readmission (PARR) model.

The objective of this study was to design and develop a predictive model for 30-day risk of hospital readmission using machine learning techniques. The proposed predictive model was then validated with the two most commonly used risk of readmission models: LACE index and patient at risk of hospital readmission (PARR). The study cohort consisted of 180,118 admissions with 22,565 (12.5%) of actual readmissions within 30 days of hospital discharge, from 01 Jan 2015 to 31 Dec 2016 from two Auckland-region hospitals. We developed a machine learning model to predict 30-day readmissions using the model types XGBoost, Random Forests, and Adaboost with decision stumps as a base learner with different feature combinations and preprocessing procedures. The proposed model achieved the F1-score (0.386 ± 0.006), sensitivity (0.598 ± 0.013), positive predictive value (PPV) (0.285 ± 0.004), and negative predictive value (NPV) (0.932 ± 0.002). When compared with LACE and PARR(NZ) models, the proposed model achieved better F1-score by 12.7% compared with LACE and 23.2% compared with PARR(NZ). The mean sensitivity of the proposed model was 6.0% higher than LACE and 41% higher than PARR(NZ). The mean PPV was 15.9% and 14.6% higher than LACE and PARR(NZ) respectively. We presented an all-cause predictive model for 30-day risk of hospital readmission with an area under the receiver operating characteristics (AUROC) of 0.75 for the entire dataset. Graphical abstract.

A Systematic Review of Wearable Sensors and IoT-Based Monitoring Applications for Older Adults - a Focus on Ageing Population and Independent Living.

This review aims to present current advancements in wearable technologies and IoT-based applications to support independent living. The secondary aim was to investigate the barriers and challenges of wearable sensors and Internet-of-Things (IoT) monitoring solutions for older adults. For this work, we considered falls and activity of daily life (ADLs) for the ageing population (older adults). A total of 327 articles were screened, and 14 articles were selected for this review. This review considered recent studies published between 2015 and 2019. The research articles were selected based on the inclusion and exclusion criteria, and studies that support or present a vision to provide advancement to the current space of ADLs, independent living and supporting the ageing population. Most studies focused on the system aspects of wearable sensors and IoT monitoring solutions including advanced sensors, wireless data collection, communication platform and usability. Moderate to low usability/ user-friendly approach is reported in most of the studies. Other issues found were inaccurate sensors, battery/ power issues, restricting the users within the monitoring area/ space and lack of interoperability. The advancement of wearable technology and the possibilities of using advanced IoT technology to assist older adults with their ADLs and independent living is the subject of many recent research and investigation.

A Cox-Based Risk Prediction Model for Early Detection of Cardiovascular Disease: Identification of Key Risk Factors for the Development of a 10-Year CVD Risk Prediction.

BACKGROUND AND OBJECTIVE: Current cardiovascular disease (CVD) risk models are typically based on traditional laboratory-based predictors. The objective of this research was to identify key risk factors that affect the CVD risk prediction and to develop a 10-year CVD risk prediction model using the identified risk factors. METHODS: A Cox proportional hazard regression method was applied to generate the proposed risk model. We used the dataset from Framingham Original Cohort of 5079 men and women aged 30-62 years, who had no overt symptoms of CVD at the baseline; among the selected cohort 3189 had a CVD event. RESULTS: A 10-year CVD risk model based on multiple risk factors (such as age, sex, body mass index (BMI), hypertension, systolic blood pressure (SBP), cigarettes per day, pulse rate, and diabetes) was developed in which heart rate was identified as one of the novel risk factors. The proposed model achieved a good discrimination and calibration ability with C-index (receiver operating characteristic (ROC)) being 0.71 in the validation dataset. We validated the model via statistical and empirical validation. CONCLUSION: The proposed CVD risk prediction model is based on standard risk factors, which could help reduce the cost and time required for conducting the clinical/laboratory tests. Healthcare providers, clinicians, and patients can use this tool to see the 10-year risk of CVD for an individual. Heart rate was incorporated as a novel predictor, which extends the predictive ability of the past existing risk equations.

Clinical decision support systems in hospital care using ubiquitous devices: Current issues and challenges.

Supporting clinicians in decision making using advanced technologies has been an active research area in biomedical engineering during the past years. Among a wide range of ubiquitous systems, smartphone applications have been increasingly developed in healthcare settings to help clinicians as well as patients. Today, many smartphone applications, from basic data analysis to advanced patient monitoring, are available to clinicians and patients. Such applications are now increasingly integrating into healthcare for clinical decision support, and therefore, concerns around accuracy, stability, and dependency of these applications are rising. In addition, lack of attention to the clinicians' acceptability, as well as the low impact on the medical professionals' decision making, are posing more serious issues on the acceptability of smartphone applications. This article reviews smartphone-based decision support applications, focusing on hospital care settings and their overall impact of these applications on the wider clinical workflow. Additionally, key challenges and barriers of the current ubiquitous device-based healthcare applications are identified. Finally, this article addresses current challenges, future directions, and the adoption of mobile healthcare applications.

Machine Learning-based Risk of Hospital Readmissions: Predicting Acute Readmissions within 30 Days of Discharge.

The objective of this study was to design and develop a 30-day risk of hospital readmission predictive model using machine learning techniques. The proposed risk of readmission predictive model was then validated with the two most commonly used risk of readmission models - LACE index and patient at-risk of hospital readmission (PARR). The study cohort consisted of 180,118 admissions with 22565 (12.5%) of actual readmissions within 30-day of hospital discharge, from 01 Jan 2015 to 31 Dec 2016 from two Auckland-region hospitals. We developed a machine learning model to predict 30-day readmissions using the model types: XGBoost, Random Forests and Adaboost with decision stumps as a base learner with different feature combinations and preprocessing procedures. The proposed model achieved the F1-score (0.386 ± 0.006), sensitivity (0.598 ± 0.013), positive predictive value (PPV) (0.285 ± 0.004) and negative predictive value (NPV) (0.932 ± 0.002). When compared with LACE and PARR (NZ) models, the proposed model achieved better F1-score by 12.5% compared to LACE and 22.9% compared to PARR (NZ). The mean sensitivity of the proposed model was 6.0% higher than LACE and 42.4% higher than PARR (NZ). The mean PPV was 15.9% and 13.5% higher than LACE and PARR (NZ) respectively.

Falls management framework for supporting an independent lifestyle for older adults: a systematic review.

Falls are one of the common health and well-being issues among the older adults. Internet of things (IoT)-based health monitoring systems have been developed over the past two decades for improving healthcare services for older adults to support an independent lifestyle. This research systematically reviews technological applications related to falls detection and falls management. The systematic review was conducted in accordance to the preferred reporting items for systematic reviews and meta-analysis statement (PRISMA). Twenty-four studies out of 806 articles published between 2015 and 2017 were identified and included in this review. Selected studies were related to pre-fall and post-fall applications using motion sensors (10; 41.67%), environment sensors (10; 41.67%) and few studies used the combination of these types of sensors (4; 16.67%). As an outcome of this review, we postulated a falls management framework (FMF). FMF considered pre- and post-fall strategies to support older adults live independently. A part of this approach involved active analysis of sensor data with the aim of helping the older adults manage their risk of fall and stay safe in their home. FMF aimed to serve the researchers, developers, clinicians and policy makers with pre- and post-falls management strategies to enhance the older adults' independent living and well-being.

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.

Falls risk assessment for hospitalised older adults: a combination of motion data and vital signs.

Health monitoring systems have rapidly evolved during the past two decades and have the potential to change the way healthcare is currently delivered. Currently hospital falls are a major healthcare concern worldwide because of the ageing population. Current observational data and vital signs give the critical information related to the patient's physiology, and motion data provide an additional tool in falls risk assessment. These data combined with the patient's medical history potentially may give the interpretation model high information accessibility to predict falls risk. This study aims to develop a robust falls risk assessment system, in order to avoid falls and its related long-term disabilities in hospitals especially among older adults. The proposed system employs real-time vital signs, motion data, falls history and other clinical information. The falls risk assessment model has been tested and evaluated with 30 patients. The results of the proposed system have been compared with and evaluated against the hospital's falls scoring scale.

Multiple physical signs detection and decision support system for hospitalized older adults.

Health monitoring systems have rapidly evolved during the past two decades and have the potential to change the way healthcare is currently delivered. Smart monitoring systems automate patient monitoring tasks and thereby improve patient workflow management. Moreover, expert systems have the potential to assist clinicians and improve their performance by accurately executing repetitive tasks, to which humans are ill-suited. Clinicians working in hospital wards are responsible for conducting a multitude of tasks which require constant vigilance, and thus the need for a smart decision support system has arisen. In particular, wireless patient monitoring systems are emerging as a low cost, reliable and accurate means of healthcare delivery. Vital signs monitoring systems are rapidly becoming part of today's healthcare delivery. The paradigm has shifted from traditional and manual recording to computer-based electronic records and, further, to handheld devices as versatile and innovative healthcare monitoring systems. The current study focuses on interpreting multiple physical signs and early warning for hospitalized older adults so that severe consequences can be minimized. Data from a total of 30 patients have been collated in New Zealand hospitals under local and national ethics approvals. The system records blood pressure, heart rate (pulse), oxygen saturation (SpO2), ear temperature and blood glucose levels from hospitalized patients and transfers this information to a web-based software application for remote monitoring and further interpretation. Ultimately, this system is aimed to achieve a high level of agreement with clinicians' interpretation when assessing specific physical signs such as bradycardia, tachycardia, hypertension, hypotension, hypoxaemia, fever and hypothermia to generate early warnings. The performance of the vital signs interpretation system was validated through off-line as well as real-time tests with a high level of agreement between the system and physician.

Advanced decision support system for older adults.

Decision support systems are rapidly becoming part of today's healthcare delivery. The paradigm has shifted from traditional and manual recording to computer-based electronic records and, further, to handheld devices as versatile and innovative healthcare monitoring systems. The current study focuses on interpreting multiple physical signs and early warning for hospitalized older adults so that severe consequences can be minimized. Data from a total of 30 patients have been collated in New Zealand Hospitals under local and national ethics approvals. The system records blood pressure, heart rate (pulse), oxygen saturation (SpO2), ear temperature and blood glucose levels from hospitalized patients and transfers this information to a web-based software application for remote monitoring and further interpretation. Ultimately, this system is aimed to achieve a high level of agreement with clinicians' interpretation when assessing specific physical signs such as bradycardia, tachycardia, hypertension, hypotension, hypoxemia, fever and hypothermia and to generate early warnings.

Tablet-based patient monitoring and decision support systems in hospital care.

Remote patient monitoring with evidence-based decision support is revolutionizing healthcare. This novel approach could enable both patients and healthcare providers to improve quality of care and reduce costs. Clinicians can also view patients' data within the hospital network on tablet computers as well as other ubiquitous devices. Today, a wide range of applications are available on tablet computers which are increasingly integrating into the healthcare mainstream as clinical decision support systems. Despite the benefits of tablet-based healthcare applications, there are concerns around the accuracy, security and stability of such applications. In this study, we developed five tablet-based application screens for remote patient monitoring at hospital care settings and identified related issues and challenges. The ultimate aim of this research is to integrate decision support algorithms into the monitoring system in order to improve inpatient care and the effectiveness of such applications.

Integrated vital signs monitoring system using ubiquitous devices: Multiple physical signs detection and decision support for hospitalized older adults.

Vital signs monitoring systems are rapidly becoming the core of today's healthcare deliveries. The paradigm has shifted from traditional and manual recording to computer based electronic records and further to handheld devices as versatile and innovative healthcare monitoring systems. Interpretation of vital signs to early detect multiple physical signs using a multifactorial and holistic approach is presented. A total of 30 patient data have been collected under local and national ethics approvals in New Zealand Hospitals. Ultimately, this system achieved a high level of agreement with clinicians' interpretation when assessing specific physical signs such as bradycardia, tachycardia, hypertension, hypotension, hypoxaemia, fever and hypothermia. The proposed vital signs interpretation system was validated through off-line as well as real-time tests with a high level of agreement between the system and the physician. The system achieved an accuracy of 95.83%, sensitivity of 100%, specificity of 93.15%, and predictability of 90.38% in compare with a clinician assessment for tachycardia, hypertension, hypotension, hypoxaemia and hypothermia.

Mobile healthcare applications: system design review, critical issues and challenges.

Mobile phones are becoming increasingly important in monitoring and delivery of healthcare interventions. They are often considered as pocket computers, due to their advanced computing features, enhanced preferences and diverse capabilities. Their sophisticated sensors and complex software applications make the mobile healthcare (m-health) based applications more feasible and innovative. In a number of scenarios user-friendliness, convenience and effectiveness of these systems have been acknowledged by both patients as well as healthcare providers. M-health technology employs advanced concepts and techniques from multidisciplinary fields of electrical engineering, computer science, biomedical engineering and medicine which benefit the innovations of these fields towards healthcare systems. This paper deals with two important aspects of current mobile phone based sensor applications in healthcare. Firstly, critical review of advanced applications such as; vital sign monitoring, blood glucose monitoring and in-built camera based smartphone sensor applications. Secondly, investigating challenges and critical issues related to the use of smartphones in healthcare including; reliability, efficiency, mobile phone platform variability, cost effectiveness, energy usage, user interface, quality of medical data, and security and privacy. It was found that the mobile based applications have been widely developed in recent years with fast growing deployment by healthcare professionals and patients. However, despite the advantages of smartphones in patient monitoring, education, and management there are some critical issues and challenges related to security and privacy of data, acceptability, reliability and cost that need to be addressed.