Access to reliable healthcare information remains a significant challenge in many low-resource settings, particularly in developing countries where shortages of healthcare professionals and inadequate healthcare infrastructure hinder timely access to quality healthcare services. This study presents the design, implementation, and evaluation of ePACK, an intelligent Artificial Intelligence (AI)-based health assistant developed to support symptom checking and preliminary clinical decision support within the Nigerian healthcare context. The system enables users to describe symptoms in natural language, which are processed using Natural Language Processing (NLP) techniques and analysed through machine learning algorithms to identify potential health conditions. Clinical recommendations are further validated using a rule-based decision-support engine derived from the Practical Approach to Care Kit (PACK) Nigeria clinical guidelines. The proposed framework integrates a responsive web-based user interface, NLP-driven symptom extraction, machine learning-based disease prediction, and a guideline-informed clinical recommendation engine. A Random Forest classifier was adopted as the primary prediction model due to its superior performance among the evaluated algorithms. The system was assessed using 200 patient cases obtained from healthcare facilities across Adamawa, Nasarawa, and Ondo States, Nigeria. Evaluation results demonstrated an overall diagnostic agreement rate of 78% when compared with physician-confirmed diagnoses, while user satisfaction assessments indicated positive perceptions regarding system usability, accessibility, and response efficiency. The findings demonstrate the potential of AI-enabled digital health assistants to enhance healthcare accessibility, support patient triage, and provide preliminary health guidance in resource-constrained environments. Furthermore, the study highlights the value of integrating machine learning techniques with locally adapted clinical guidelines to improve the relevance, safety, and effectiveness of digital health interventions within the Nigerian healthcare system.

Point-of-care ultrasound (POCUS) provides real-time diagnostic capabilities at the bedside. Implementing a POCUS program in an institution is a highly complex process. Coordinating the imaging workflow of numerous clinical specialties requires meticulous planning and appropriate oversight. This white paper describes the best practices for the critical pre-deployment phase of program implementation, after having established POCUS program governance. Important considerations during the pre-deployment phase include goal setting, scaling POCUS workflow across clinical, educational, and technological domains, and addressing budgetary concerns and complexity of deployment strategies. This paper also discusses the role of the POCUS workflow manager software in encounter-based imaging workflow and the role of a system-wide clinical ultrasound director. Furthermore, it outlines the necessary approvals needed to ensure compliance and program success, including securing approvals from key departments such as imaging informatics, information technology, cybersecurity, supply chain operations, clinical engineering, infection prevention, legal, and billing departments. Finally, it presents a sample comprehensive project charter to guide this complex integration process from business case development, to clinical go-live, emphasizing best practices for sustained adoption.

A checklist is an effective tool for ensuring patient safety. We have already been using a briefing checklist for hemodialysis. However, we did not have ones for apheresis therapy. From the experiences of incidents that occurred in February and March 2024. We decided to create a briefing checklist for apheresis therapy, especially for plasma exchange (PE) and double filtration plasmapheresis (DFPP). First, we made a briefing checklist specific to apheresis therapies, different from hemodialysis. Another incident occurred 6 months later, revealing that staff used the checklist in a manner different from the intended one. The fact prompted us to revise the apheresis therapy checklist, with items and the order of appearance similar to those of the hemodialysis checklist. We also provided detailed explanations of apheresis therapy for clinical engineers unfamiliar with it. We have not experienced any incident since September 2024, when the revised procedures were implemented, until May 2025. The briefing checklist provided benefits, including improved patient safety and education for clinical engineers unfamiliar with apheresis. the revision process further improved the checklist's efficiency.

• CARE: A clinical agentic reasoning engine for real-world diagnosis. • Two-stage alignment for stronger medical reasoning and self-correction. • CARE-Dx delivers top accuracy across extensive medical benchmarks. • Real-world clinical dataset shows CARE’s broad-disease generalization. Recent advancements in large language models (LLMs) have improved performance on standardized medical benchmarks. However, existing benchmarks often rely on truncated context and idealized scenarios. In practice, clinical diagnosis requires synthesizing patient history, physical examination, laboratory tests, and imaging under time constraints, and LLMs can struggle with accuracy and may hallucinate when confronted with authentic cases. To address this challenge, we propose the Clinical Agentic Reasoning Engine (CARE) , a physician-inspired workflow that structures diagnosis into retrieval, preliminary diagnosis, final diagnosis, and confidence-gated recheck, with intermediate outputs serialized in JSON for verifiable, training-free inference. Using CARE as a data-generation pipeline with clinician-prepared diagnostic criteria, we curate 2,000 de-identified real-world cases across 15 abdominal disease categories and produce stepwise CARE annotations under a fixed schema. We adopt Dual-stage Alignment for Reasoning Enhancement (DARE) , which trains on these CARE-annotated trajectories, uses supervised fine-tuning on physician-structured long-form demonstrations and then applies group relative policy optimization to refine policy and promote self-correction. Finally, we introduce CARE-Dx , the resulting diagnosis model obtained by applying DARE to an instruction-tuned backbone, while CARE also remains a training-free inference protocol that can be applied to other LLMs. Experiments show that, under DARE, CARE-Dx achieves strong in-domain and zero-shot out-of-domain performance and approaches leading closed-source accuracy on evaluations, with clinician assessment by 12 experienced physicians from multiple departments confirming that its reasoning aligns with real clinical workflows. Moreover, on the de-identified private cohort Rui-EHR , which covers a broader set of diseases, the CARE pipeline maintains diagnostic quality.

Automated Flow and local LLM-Driven clinical Context Engineering: Precision colorectal cancer recurrence registry.

This study aimed to develop a local large language model (LLM) specialized in clinical engineering and to evaluate its performance on the Japanese National Clinical Engineer Licensing Examination. Three local LLMs (Cogito-32b-think, GPT-4o-mini, and Qwen3-14B) and Gemini-2.5 Pro were tested. Among the local models, Qwen3-14B achieved the highest accuracy and was further improved through supervised fine-tuning (SFT) using reasoning data generated by Gemini-2.5 Pro. After SFT, the overall accuracy of Qwen3-14B increased from 77% to 82%, with improvements in image (39% to 52%) and calculation (58% to 68%) questions. Although Gemini-2.5 Pro outperformed Qwen3-14B with 94% accuracy, the results demonstrate that SFT effectively enhances local LLMs, offering a promising, secure, and cost-efficient approach for specialized clinical engineering applications.

Since 2020, Mongolia has begun developing phased policies and recommendations to implement artificial intelligence (AI) technology across education, healthcare, and business. In the health sector, international policy documents on the introduction of AI were developed by the World Health Organization (WHO) and the United Nations Educational, Scientific, and Cultural Organization (UNESCO) between 2019 and 2021, providing guidelines and recommendations for its use, application, and ethical standards. These policy documents emphasize that AI in healthcare should not replace doctors, but rather serve as a tool to support clinical decision-making in diagnosis and treatment, with the final decision always being made by the physician [1, 2]. After World War II, a group of people began working independently to create intelligent machines. In 1947, British mathematician Alan Turing presented his first research. He concluded that it was better to study AI through computer programming rather than by building machines. By the late 1950s, many people were studying AI, mostly based on computer programming [3].

Human bone marrow mesenchymal stromal/stem cells (BM-MSCs) are widely used in clinical trials and tissue engineering, yet their native microenvironment remains poorly understood. Here we introduce a tissue-clearing protocol, DeepBone, for human bones and integrate it with simultaneous mRNA and protein detection. Using this protocol, we spatially map BM-MSCs relative to key bone microenvironment components, including human blood capillaries, adipocytes, sinusoids and bony trabeculae. Quantitative analysis reveals that the native microenvironment of human BM-MSCs in young bone is enriched in vasculature, sinusoids, bone matrix and adipocytes. In contrast, in aged bone, BM-MSCs show no preferential association with bone or adipocytes. Proliferative BM-MSCs are predominantly found along blood vessels. Moreover, we identify a specialized microenvironment for BM-MSCs in young bone, characterized by sinusoids coiled around trabeculae and enriched by R-type vessels. These findings provide insights into the native niches of BM-MSCs, offering a foundation for the development of tissue engineering strategies that mimic their physiological context.

Improving alarm management to reduce alarm fatigue in critical care: a mixed-methods study.

Supercritical CO2-foamed hierarchically porous PLA/PBS-based scaffold for advanced bone regeneration.

This study examined the association between attendance in a first-year educational support program and academic performance among students in allied health education. This retrospective observational study was conducted at a single university and included 67 first-year students enrolled in clinical laboratory technology and clinical engineering programs during the first semester of 2025. Attendance was recorded across 11 sessions of the Introduction to Self-Learning Management program. The program was conceptually informed by self-regulated learning theory and included goal setting, individual learning activities, self-reflection, and instructor feedback. Academic performance was assessed using grade point average (GPA) at the end of the semester. Attendance was analyzed using multiple linear regression and independent-samples t-tests. In multiple linear regression analysis, attendance, academic foundation test score, and mathematics placement test score were included as explanatory variables. Multiple linear regression showed that attendance remained significantly associated with GPA after adjustment for baseline academic performance variables (β = 0.20, 95% confidence interval [CI] 0.06-0.34, P = 0.005), whereas academic foundation test score and mathematics placement test score were not significantly associated with GPA. For descriptive comparison, students with one or fewer absences showed a significantly higher mean GPA than those with two or more absences (mean difference 0.89, 95% CI 0.43-1.34, P = 0.0007, Cohen's d = 1.02). Attendance was positively associated with GPA in this sample. Because of the retrospective observational design and absence of direct self-regulated learning measures, causal interpretation is limited. Prospective studies with controlled designs are needed to determine whether attendance can serve as an indicator for identifying students requiring additional educational support.

Lipopolysaccharide (LPS), also known as an endotoxin, poses serious health risks, such as sepsis, shock, and fever. Detecting LPS is important for hemodiafiltration therapy. In this study, an electrochemical LPS sensor with carbon nanotubes (CNTs) and polymyxin B (PmB) was developed for the first time. Layer-by-layer fabrication was done using dispersed CNTs and a PmB solution. LPS selectively bound to sensing elements and hindered redox reaction of markers, causing the peak current to decrease. As the LPS concentration increased, the number of LPS molecules bound to sensing elements increased, and fewer markers could approach the electrode surface. Consequently, the peak current decreased with increasing LPS concentration. The CNTs contribute to enhance the electrochemical current due to marker ion because of theirs high conductivity and catalytic ability. PmB discriminates LPS, and the CNTs enhance the signal arising from this response. The measurement range was 10fg/mL-10ng/mL. This sensor did not respond to other chemicals, such as human serum albumin, glucose, and bicarbonate, present in biological samples. This performance makes it suitable for water quality management of dialysis fluids, helping reduce the workload of clinical engineers. The CNT-based platform can be expanded to detect other targets and has the potential for widespread application in various areas.

The increasing adoption of artificial intelligence and real-time analytics in healthcare has exposed fundamental limitations in traditional clinical data engineering approaches, which rely heavily on batch-oriented pipelines, rigid schemas, and manual data governance. These limitations introduce latency, interoperability challenges, and silent data-quality failures that directly affect clinical decision-making and model reliability. This paper presents a solution-oriented clinical data engineering paradigm based on real-time lakehouse architectures, interoperability-first design, and autonomous data quality management. The proposed approach unifies streaming and historical clinical data across heterogeneous sources, enabling low-latency analytics while preserving semantic consistency and auditability. Interoperability is addressed through canonical data modeling and real-time semantic normalization, allowing seamless integration of electronic health records, medical devices, and imaging systems. Autonomous data quality mechanisms continuously detect anomalies, drift, and inconsistencies, preventing corrupted data from propagating into downstream clinical applications. Real-world clinical scenarios demonstrate how this architecture improves operational readiness, enhances AI reliability, and supports trustworthy, real-time clinical decision support.

In this paper, we describe the design, implementation, and outcomes of the Hospital Rotation course (CPB 448) at Miami University, a required component of both the Clinical Engineering Master’s program and the minors in Clinical Engineering and Regulatory Affairs. The course integrates structured online lectures with immersive, in-person hospital visits to provide students with comprehensive exposure to hospital operations, medical technology, patient safety, clinical engineering practice, and the science behind the application of medical instruments and devices. Student feedback, challenges, and future directions—including the expansion to fully online delivery—are discussed.

We evaluated the accuracy and reliability of 12 low-cost CO₂ sensors that are commercially available and promoted for infection control in indoor settings, considering their potential use in clinical environments. A stepwise CO₂ injection protocol and alcohol exposure tests were conducted in a controlled acrylic chamber. Our results showed that only 3 out of 12 sensors (25%) responded reliably to actual CO₂ concentrations and could be calibrated with acceptable accuracy, whereas 67% failed to detect CO₂ but falsely responded to alcohol vapors, frequently present in health care environments. These findings highlight the need for staff development educators to promote accurate sensor selection and propose a practical 3-step screening method that clinical engineers can use without specialized equipment.

Reconstruction of craniomaxillofacial (CMF) bony defects requires individualized strategies based on defect characteristics and graft bed biology, with traditional approaches relying on autogenous non-vascularized bone grafts or vascularized free flaps that, while reliable, are associated with donor-site morbidity and operative complexity. Biologically driven reconstructive strategies, including tissue engineering, cellular bone matrix allografts (CBMs), and growth factor adjuncts, have emerged as alternatives or complements to autograft-based reconstruction. This review introduces and details these new innovations with emphasis on the current literature, thus empowering surgeons to enhance their clinical armamentarium.

Background: Hospitals increasingly operate as technologyintensive environments in which medical devices, digital platforms, and diagnostic systems constitute essential infrastructure for safe and effective care delivery. The traditional scope of clinical engineering, historically associated with equipment maintenance and technical support, has progressively expanded toward broader responsibilities involving technology governance, regulatory compliance, risk management, and strategic institutional planning. This study investigates how clinical engineering has been incorporated into hospital governance structures and examines the organizational implications associated with this integration. Methods: A systematic literature review was conducted according to PRISMA 2020 guidelines. Searches were performed in Scopus, Web of Science, PubMed/MEDLINE, Embase, SciELO, and the Virtual Health Library. The search period covered January 2000 to December 2025. Eligible studies included peerreviewed publications addressing governance, management, or institutional roles of clinical engineering and medical technology management. A twostage screening process was applied (title/abstract and fulltext review). Methodological quality was assessed using CASP and Joanna Briggs Institute appraisal tools. Results: A total of 742 records were identified. After duplicate removal and eligibility screening, 25 studies were included in the qualitative synthesis. Three analytical domains emerged from the literature: integration of clinical engineering into executive governance structures; interaction with patient safety systems; and institutional accountability associated with medical technology management. Evidence suggests increasing recognition of clinical engineering as a governancerelevant function, although organizational models remain heterogeneous. Conclusions: Formal integration of clinical engineering into hospital governance contributes to improved technological traceability, enhanced patient safety practices, and stronger institutional accountability. However, standardized governance indicators and multicenter empirical validation remain limited. Future research should focus on developing comparative frameworks capable of evaluating technological governance maturity across healthcare systems.

BackgroundHigh-intensity interval training (HIIT) is a time-efficient approach that improves cardiovascular and metabolic health, but it can acutely increase oxidative stress and delay recovery. With the growing availability of wearable sensors and point-of-care biochemical testing, recovery interventions can be evaluated with objective physiological monitoring.ObjectiveTo investigate whether a single session of manual lymphatic drainage (MLD) modulates post-HIIT oxidative stress and lactate responses measured using wearable and point-of-care monitoring tools in healthy adults.MethodsThirty healthy adults were randomized to an MLD group (n = 15) or a passive-rest control group (n = 15). Exercise intensity was controlled using a wearable heart-rate monitor during a standardized HIIT protocol. Capillary blood lactate, reactive oxygen species (ROS), and antioxidant capacity were assessed at baseline, immediately after HIIT, after 35 min of MLD or rest, and at 24 h using portable analyzers and photometric assays. Two-way repeated-measures ANOVA and within-group one-way repeated-measures ANOVA were applied.ResultsTime effects were observed in oxidative stress and lactate markers. Within the MLD group, ROS and antioxidant capacity changed significantly over time (p < .05). Antioxidant capacity increased immediately after exercise and declined at 24 h. Lactate increased after HIIT and decreased after MLD and at 24 h (p < .05). Between-group differences were not significant.ConclusionMLD appears to support post-HIIT physiological recovery, and its effects can be quantified using wearable heart-rate monitoring and point-of-care oxidative stress and lactate testing. This monitoring-based framework strengthens the clinical engineering relevance of MLD as an adjunct recovery strategy in rehabilitation and health-management settings.

The COVID-19 pandemic has brought attention to the necessity of an adequate disinfection system to fight dangerous and contagious diseases. Current cleaning procedures are frequently laborious and time-consuming. Researchers are investigating the use of cutting-edge technologies to safeguard the worldwide populace against the spread of viruses and other illnesses to address this issue. A UV-222 nm light-based disinfection system has been suggested as a possible remedy in this regard to counteract the impacts of viruses and maintain a clean and secure environment. The implementation of UV-222 nm light-based disinfection systems and their prospective influence on healthcare technology are the main topics of this article. The technology can address issues with the spread of viruses and bacteria in a variety of contexts, including car headlights, public lighting, interior lights in homes, and other sterilising techniques. Additionally, the high-way geometry of UVC sterilisation has been theoretically formulated and investigated. Healthcare professionals, medical physicists, biomedical and clinical engineers, and other associated groups are the target audience for this article. In order to enhance patient safety, disease surveillance, and management, the study discusses the potential advantages of UV-222 nm light-based disinfection systems. We also talk about the ethical, moral, and legal ramifications of using such technology. In conclusion, this research offers a fresh viewpoint on UV-222 nm light-based disinfection systems and their prospective influence on medical technology. In order to improve patient care and safety, we hope that this conversation will promote additional research and development in the area of healthcare technology.

Parameter optimization and finite element simulation analysis of skin graft harvesting using an electric dermatome