Clinical Field Research Articles

Analyzing research trends and developments in osseointegration in patients with extremity amputations: Systematic bibliometric analysis and research recommendations

Background: Bone-anchored protheses (BAPs) by means of osseointegrated implants are increasingly being used in amputees with socket-related issues. Clinical advancements are being published by more and more centers worldwide. Although the number of publications and interest in BAP is growing, a systematic evaluation of scholarly output is lacking. Objective: To identify scholarly output, understand research trends and make research recommendations in the clinical field of BAP. Methods: Systematic searches in Medline All, Embase, Web of Science Core Collection, Cochrane Library, and Google Scholar were completed in February 2023. The results were deduplicated, screened, and assessed for quality by independent reviewers. Inclusion criteria were as follows: clinical studies and BAP in the extremities. Articles were excluded if they were animal or fundamental studies, nonclinical reports, had a study population less than 10 patients, or BAP was performed in areas other than extremities. Results: One hundred twelve articles were included and published between 1993 and 2023. An annual growth rate of 10.3% was found and research was published in 62 different journals. Prosthetics and Orthotics International, Clinical Orthopaedics and Related Research and The Bone & Joint Journal were the most prolific journals. Hagberg K, Aschoff HH, and Branemark R were major contributors to BAP research. Collaborations are predominantly among high-income countries. Main research trends were on rehabilitation, questionnaires, complication managements, and implant treatment. Conclusions: Research on BAP shows an increasing global trend, highlighting key research areas and authors. A unified global research agenda, stakeholders' collaborations, and consensus are essential for addressing knowledge gaps and development future direction of BAP.

Characterizing T1 in the fetal brain and placenta over gestational age at 0.55T.

T1 mapping and T1-weighted contrasts have a complimentary but currently under utilized role in fetal MRI. Emerging clinical low field scanners are ideally suited for fetal T1 mapping. The advantages are lower T1 values which results in higher efficiency and reduced field inhomogeneities resulting in a decreased requirement for specialist tools. In addition the increased bore size associated with low field scanners provides improved patient comfort and accessibility. This study aims to demonstrate the feasibility of fetal brain T1 mapping at 0.55T. An efficient slice-shuffling inversion-recovery echo-planar imaging (EPI)-based T1-mapping and postprocessing was demonstrated for the fetal brain at 0.55T in a cohort of 38 fetal MRI scans. Robustness analysis was performed and placental measurements were taken for validation. High-quality T1 maps allowing the investigation of subregions in the brain were obtained and significant correlation with gestational age was demonstrated for fetal brain T1 maps ( ) as well as regions-of-interest in the deep gray matter and white matter. Efficient, quantitative T1 mapping in the fetal brain was demonstrated on a clinical 0.55T MRI scanner, providing foundations for both future research and clinical applications including low-field specific T1-weighted acquisitions.

Assessment of pencil beam scanning proton therapy beam delivery accuracy through machine learning and log file analysis

PurposeComprehensive Quality Assurance (QA) protocols are necessary for complex beam delivery systems like Pencil Beam Scanning (PBS) proton therapy. This study focuses on automating the evaluation of beam delivery accuracy using irradiation log files and machine learning (ML) models. MethodsIrradiation log files of 935 clinical treatment fields and routine QA beams were analysed to evaluate spot parameters and Monitor Unit (MU) accuracy. ML models predicted spot size along the X, Y, major, and minor axes. In-house scripts automated log file analysis and spot size predictions. Predicted spot sizes were compared with expected baselines, and the accuracy of spot position, symmetry, and MU for each spot in the beam was evaluated. ResultsMore than 99.5 % of spot positions were accurate within a 1 mm. The mean and Standard Deviation (SD) of X positional error were −0.021 mm (SD: 0.181 mm), and for Y positional error, they were −0.002 mm (SD: 0.132 mm). ML models accurately predicted spot sizes, with over 95 % of spots demonstrating size variations within 10 % of the baseline. The Root Mean Squared Error (RMSE) of X and Y spot size differences were 0.15 mm and 0.16 mm, respectively. Spot symmetry was within 10 %, and MU accuracy showed 95 % of spots with MU per spot variation less than 2 %. ConclusionThis method can validate the vendor’s beam delivery safety interlock system and serve as a quick alternative to patient-specific QA in adaptive treatment, where time is limited, as well as for routine QA spot parameter evaluations.

Selective Dry Cow Therapy: Clinical Field Trial on Prevention and Cure of Intramammary Infections

Selective Dry Cow Therapy: Clinical Field Trial on Prevention and Cure of Intramammary Infections

Research Trends in the Evaluation and Treatment of Speech Disorders Using Automatic Speech Recognition (ASR)

Purpose: The purpose of this study is to examine recent research trends regarding automatic speech recognition (ASR), which is used in the evaluation and intervention of speech disorders.Methods: Through a search engine, articles published in domestic journals were searched. A total of 27 papers were selected from the searched documents and analyzed according to the year, research subject, speech task, and ASR system.Results: The years with the most research was done in 2019~2021. The subjects who most frequently underwent speech evaluation and treatment using ASR system were those with dysarthria. The speech production tasks used to utilize ASR were at the word and sentence level, and commercialized and non-commercialized ASR systems were used similarly.Conclusion: These results might be used for the fundamental data to establish the most suitable evaluation methods and intervention plans for patients with speech disorders in clinical and research fields.

Process of Reliability of the Ventilatory Workload Kinetic Index and Prioritization in the Intrahospital Clinical Setting

Background and Objectives: The Ventilatory Workload Kinetic Index (VWKI) has been proposed as a clinical instrument to evaluate ventilatory balance–imbalance. However, the regulated application of scales that allow an integral evaluation of the object of study and their subsequent reliability evaluation should be continuous. The objective was to determine the reliability of the VWKI between two evaluators and its applicability in the clinical field of physiotherapy. Materials and Methods: The methodology was divided into three stages: (i) induction period, (ii) application of the VWKI, and (iii) assessment of reliability. Results: The VWKI total score obtained excellent inter-rater reliability (ICC = 0.913, p < 0.05). The airway resistance (AR) showed moderate inter-rater reliability (ICC = 0.528, p < 0.05), while the use of accessory musculature (UAM) showed poor inter-rater reliability (ICC = 0.483, p < 0.05). In the physiotherapy care prioritization system, for both evaluator A (EA) and evaluator B (EB), the total VWKI score was significantly higher in priority 1 (p = 0.001; p < 0.05, respectively). Regarding the total VWKI score by services, it was observed that both EA and EB rated the VWKI significantly higher in the intensive care unit (ICU) than in medicine and the other services (p = 0.001, p = 0.0001 and p < 0.05, p < 0.05, respectively). Conclusions: VWKI is highly reliable in the total score. It is also consistent with the system of prioritization of physiotherapy care and the ability to determine the severity of clinical respiratory symptoms.

Evaluation of in-house-built pipette-tip micro-solid-phase extraction devices for sample preparation in the analysis of amino compounds by liquid chromatography-tandem mass spectrometry

Amino compounds are of significant interest in dietary, clinical, and quality control fields. Efficient extraction is crucial for comprehensive metabolomics, especially for amino acids and biogenic amines, but traditional solid-phase extraction (SPE) methods are costly and require large solvent volumes. Miniaturized SPE techniques, like pipette-tip micro-solid-phase extraction (PT-µ-SPE), offer promising alternatives by improving throughput and reducing solvent and sorbent usage. This study presents PT-µ-SPE for the screening and quantification of amino compounds in bee products, particularly honey. The method involves derivatization with diethyl ethoxymethylenemalonate (DEEMM) and analysis using liquid chromatography-triple quadrupole mass spectrometry. Silica-based SCX sorbents were effective for a broad range of amino compounds, while WCX sorbents were better for aliphatic amines. The method's extraction efficiency was assessed across sample loading, washing, and elution solution, with recovery rates of 70 - 120% in oat bran, sea buckthorn leaves, and honey extracts. Matrix effects were observed for four amino compounds in honey. Limits of detection (LoD) and quantification (LoQ) ranged from 0.37 to 57 µg L⁻¹ and 1.13 to 174 µg L⁻¹, respectively. Covering 48 amino compounds under different PT-µ-SPE conditions, this method has been applied to several samples, demonstrating accuracy, environmental sustainability, cost-effectiveness, portability, and versatility in amino compound analysis.

Genetic and other omics-based information in the most-cited recent clinical trials

Abstract Introduction Since the genomic revolution, the utilization of genetic and omics technologies has undergone considerable expansion within clinical studies, employed in design, analysis, and interpretation. Methods A recent study of Siena et al. developed a database containing the 600 most cited clinical trials published from 2019 to 2022. Building on this database, the aim of our study is to assess how frequently genetic and other omics-based information has been used in the design, analysis, results or conclusion of these recent influential trials. Results 132 out 600 (22%) trials used genetic or other omics. These trials were more likely to be oncology trials (76%vs34%), having industry funding (59%vs47%), and having industry authors (75%vs54%) than others. Overall, genetics and genomics were present in 75% of the trials (100/132), and oncology was the predominant medical field (76%, n = 101). The prevailing use was detection of specific mutations (n = 99), often (n = 60) used as eligibility criterion. These mutations were mostly somatic (n = 85), while 14 were germline. Other applications included transcriptomics (20.4%), proteomics (10.6%), metabolomics (8.3%) and metagenomics (8.3%). 36 studies (27%) employed multiple applications. Genetics or other omics were used in 10% of the studies (14/132) for randomization stratification and in 63% (83/132) to conduct subgroup analysis. Among the latter, in 48% (40/83) the presence of a somatic mutation was significantly associated with the investigated health outcomes, while germline mutation or other omics only in the 12% (10/83). In the trials conclusions, authors addressed the relevance of the genetic or omics information in 62.1% (82/132) of the trials. Conclusions A sizeable proportion of the most-cited clinical trials use genetics or omics-based information, but the large majority pertains to cancer mutations in oncology trials. Use of genetics and omics needs to become more common in other clinical trial fields. Key messages • Genetic profiling and omics applications should be incorporated into trial design. • Genomic research is mostly oncology related and it needs to be expanded to other medical fields.

Three-Dimensional Reconstruction of the Right Ventricle from a Radial Basis Morphing of the Inner Surface

In the realm of cardiac health research, accurate fluid dynamics simulations are vital for comprehending the heart function and diagnosing conditions. Central to these simulations is the precision of ventricular wall meshes used to model heart geometry. However, segmenting the wetted surface, particularly in the right ventricle (RV) with its significantly thinner parietal thickness compared to the left ventricle, presents challenges. This study focuses on qualitatively evaluating an automated reconstruction model for the RV’s outer wall using Radial Basis function (RBF) morphing. Two procedural criteria were compared, a random selection of control points and a curvature-based approach, which differ in terms of the identification of the control points of the RBF function. From these considerations, it emerges that a controlled use of the RBF function on the basis of the curvatures guarantees the greater controllability of the shape evolutions of the parietal structure of the RV, but it is more sensitive to any anomalies in the distribution of the vertices, as can be seen from the number of outliers, and its controllability is a function of the percentage of points chosen, exerting a greater impact on the required computational capacity. The definition of a strategic criterion for the selection of control points could represent a crucial aspect in the definition of an automatic reconstruction procedure of anatomical elements, which guarantees a morphological variability in line with the need to expand the pathological sample to be used for statistical formulations in the clinical field.

A Multi-Hierarchical Complementary Feature Interaction Network for Accelerated Multi-Modal MR Imaging

Magnetic resonance (MR) imaging is widely used in the clinical field due to its non-invasiveness, but the long scanning time is still a bottleneck for its popularization. Using the complementary information between multi-modal imaging to accelerate imaging provides a novel and effective MR fast imaging solution. However, previous technologies mostly use simple fusion methods and fail to fully utilize their potential sharable knowledge. In this study, we introduced a novel multi-hierarchical complementary feature interaction network (MHCFIN) to realize joint reconstruction of multi-modal MR images with undersampled data and thus accelerate multi-modal imaging. Firstly, multiple attention mechanisms are integrated with a dual-branch encoder–decoder network to represent shared features and complementary features of different modalities. In the decoding stage, the multi-modal feature interaction module (MMFIM) acts as a bridge between the two branches, realizing complementary knowledge transfer between different modalities through cross-level fusion. The single-modal feature fusion module (SMFFM) carries out multi-scale feature representation and optimization of the single modality, preserving better anatomical details. Extensive experiments are conducted under different sampling patterns and acceleration factors. The results show that this proposed method achieves obvious improvement compared with existing state-of-the-art reconstruction methods in both visual quality and quantity.

Enhancing Cytoplasmic Expression of Exogenous mRNA Through Dynamic Mechanical Stimulation.

Ionizable lipid nanoparticles (LNPs) are pivotal in combating COVID-19, and numerous preclinical and clinical studies have highlighted their potential in nucleic acid-based therapies and vaccines. However, the effectiveness of endosomal escape for the nucleic acid cargos encapsulated in LNPs is still low, leading to suboptimal treatment outcomes and side effects. Hence, improving endosomal escape is crucial for enhancing the efficacy of nucleic acid delivery using LNPs. Here, a mechanical oscillation (frequency: 65Hz) is utilized to prompt the LNP-mediated endosomal escape. The results reveal this mechanical oscillation can induce the combination and fusion between LNPs with opposite surface charges, enhance endosomal escape of mRNA, and increase the transfection efficiency of mRNA. Additionally, cell viability remains high at 99.3% after treatment with oscillation, which is comparable to that of untreated cells. Furthermore, there is no obvious damage to mitochondrial membrane potential and Golgi apparatus integrity. Thus, this work presents a user-friendly and safe approach to enhancing endosomal escape of mRNA and boosting gene expression. As a result, this work can be potentially utilized in both research and clinical fields to facilitate LNP-based delivery by enabling more effective release of LNP-encapsulated cargos from endosomes.

Amino acids and the kidney; friends or foes?

Acute kidney injury (AKI) is common in hospitalized patients and is independently associated with morbidity and mortality. Moreover, AKI increases the risk of chronic kidney disease, which is a major healthcare problem. Currently, no single therapy has been proven to be effective in preventing AKI. The role of amino acids in the context of kidney function and AKI prevention has been controversial and most of the evidence is available from nutritional studies. However, knowledge of amino acids in recruiting renal functional reserve and their potential role to protect renal function under stress has recently expanded. The nephroprotective effects of amino acids were first postulated in 1973. Recently, this strategy gained renewed interest and has been more extensively studied, reintroducing their use in clinical situations characterized by a high incidence of AKI. Intravenous amino acids administration for kidney protection is now supported by a large multinational randomized double-blind controlled trial in cardiac surgery and by experimental and observational data. All such data support the rationale for a biologically and clinically important nephroprotective effect. The infusion of amino acids was recently found to reduce the incidence of AKI in cardiac surgery patients and surgical patients. This strategy for the protection of renal function is supported by a multicenter, international, double-blind randomized trial, with a huge potential for additional application in several clinical fields. Several mechanisms of action support the robustness of these findings and are summarized in this manuscript.

Risk factors of the antenatal depression in a sample of Italian pregnant women: a preliminary study.

Antenatal depression is characterized by low mood, insomnia, disorganised behaviour, irritability, and agitation during the pregnancy. If underestimated, antenatal depression is untreated during the pregnancy. It is associated to higher levels of suicide, higher risk of depression after childbirth, preeclampsia, preterm birth, low birth weight, poor interactions between child and mother and severe obstetric outcomes. New data underlined the importance to prevent the risk of depression during the pregnancy. This study examines the predictive validity of potential risk factors, such as socio-demographic and psychological factors, in developing the antenatal depression. The sample was composed by Italian pregnant women (N = 247, mean age of 33.77, SD = 4.78 years). This sample completed the Edinburg Postnatal Depression Scale (EPDS), the Teate Depression Inventory (TDI) and questionnaires about demographic variables. To study associations among variables examined bivariate correlations were computed. To analyse the role of socio-demographic factors and the psychological dimension to predict the severity of the antenatal depression a logistic regression was performed. Results showed significantly positive correlations between the EPDS and the TDI, and no associations among the EPDS and all socio-demographic factors. Therefore, only the psychological factors were significant predictive risk factors of antenatal period. Finally, higher score of the depression measured via TDI predicted higher score of the EPDS. Our results had implications in clinical field. Indeed, the early diagnosis of depression during the pregnancy can help operators in the gynaecological field to prevent the depression in the post-partum period.

Standardised Tool for the Assessment of Bruxism: Translation, Cultural Adaptation and Pilot Testing in Italy.

Recently, the Standardised Tool for the Assessment of Bruxism (STAB) has been developed for use in clinical and research settings. The aim of the present study is to describe the process of forward and back translation and pilot testing of the STAB into Italian. The English version of the STAB was adopted as a template for translation into other languages, according to a step-by-step procedure led by the expert STAB bruxism panel and mother tongue experts in the field. In detail, the translation team was made up of 12 subjects: three study coordinators, two forward translators, two back-translators and five expert panellists. Following the translation process, a pilot test in patients, dentists and dental students was performed using the 'probing' method (i.e., subjects were questioned by the examiners about the perceived content and interpretation of the items) with the aim to assess the comprehensibility of the questions and response options, and the feasibility of the tool. This paper describes the translation process of the STAB and provides the outcomes of the pilot testing phase and the face validity assessment. The preliminary results suggest that, from a global point of view, the STAB reflects the characteristics required in clinical and research settings. Thanks to the translation process, the Italian version of the STAB can be assessed on-field and introduced in the clinical and research field to get deeper into the study of bruxism epidemiology in Italy.

Siblings of Persons with Disabilities: A Systematic Integrative Review of the Empirical Literature.

The systematic review aimed to systematize the empirical literature on the psychological impact of disability on the siblings of persons with disabilities, to inform research and provide clinical recommendations. Two research questions addressed the review: (1) What are the main psychological constructs investigated in siblings of persons with disability? (2) What is the main role of each psychological construct in siblings of persons with disability experience? The electronic search was conducted in 7 databases and the PRISMA diagram was used. The inclusion criteria were: Papers published in English and in peer-reviewed journals; papers published between January 2014 and June 2024; qualitative, quantitative, and mixed studies; and papers on the psychological impact of disabilities and/or chronic illnesses on the experience of siblings of persons with disabilities. The standardized Mixed Method Appraisal Tool protocol was used to appraise the methodological quality of the studies. To summarize the findings, a narrative approach was adopted. A total of 60 studies have been reviewed. According to the methodological quality appraisal of studies, most of them reported a high (n = 45) and medium (n = 15) quality. They involved 10,146 participants. Findings revealed that sibling relationships, sibling-focused parentification, and emotional/behavioral adjustment are the main psychological constructs investigated by existing literature. Few studies focused on siblings' well-being. Studies exploring more than a psychological construct were included as a hybrid. Only one study examined the siblings' psychological experience during the COVID-19 pandemic. The quality of the sibling relationship ranged from good to poor; the caregiver is the main role played by siblings of persons with disabilities; anxiety, depression, and aggressive behaviors are the main emotional/behavioral symptoms revealed. Most studies (n = 39) recruited participants with brothers or sisters with mental disorders. The findings of this systematic review may play a role in the clinical field, as they might help to design gender- and age-specific intervention programs.

Characterizing tandem repeat complexities across long-read sequencing platforms with TREAT and otter.

Tandem repeats (TRs) play important roles in genomic variation and disease risk in humans. Long-read sequencing allows for the accurate characterization of TRs; however, the underlying bioinformatics perspectives remain challenging. We present otter and TREAT: otter is a fast targeted local assembler, cross-compatible across different sequencing platforms. It is integrated in TREAT, an end-to-end workflow for TR characterization, visualization, and analysis across multiple genomes. In a comparison with existing tools based on long-read sequencing data from both Oxford Nanopore Technology (ONT, Simplex and Duplex) and Pacific Bioscience (PacBio, Sequel II and Revio), otter and TREAT achieve state-of-the-art genotyping and motif characterization accuracy. Applied to clinically relevant TRs, TREAT/otter significantly identify individuals with pathogenic TR expansions. When applied to a case-control setting, we replicate previously reported associations of TRs with Alzheimer's disease, including those near or within APOC1 (P = 2.63 × 10-9), SPI1 (P = 6.5 × 10-3), and ABCA7 (P = 0.04) genes. Finally, we use TREAT/otter to systematically evaluate potential biases when genotyping TRs using diverse ONT and PacBio long-read sequencing data sets. We show that, in rare cases (0.06%), long-read sequencing from coverage drops in TRs, including the disease-associated TRs in ABCA7 and RFC1 genes. Such coverage drops can lead to TR misgenotyping, hampering the accurate characterization of TR alleles. Taken together, our tools can accurately genotype TRs across different sequencing technologies and with minimal requirements, allowing end-to-end analysis and comparisons of TRs in human genomes, with broad applications in research and clinical fields.

Acoustic Streaming Tunnel Enables Particle Velocity Stretching in Multiplex Flow Cytometry.

Multiplexed flow cytometry, known for its powerful high-throughput identification capability, is widely applied across various biomedical and clinical fields. However, classical flow cytometry relies on multichannel lasers and detectors, which are significant in cost and size, limiting their application in miniaturized assays. Herein, we developed an acoustic streaming-based flow cytometry technique that focuses on multisized microbeads flowing sheathlessly. This method enables the discrimination of particle types and the quantification of target protein concentrations using only a single detector. Microbeads of different sizes exhibit distinct behaviors in the continuous acoustic streaming tunnel, leading to an increased velocity difference during their transition under the laser spot. Consequently, a size detection method based on "velocity stretching" has been established. A multiplex assay of three proteins: cardiac troponin I, creatine kinase-MB and myoglobin, in acute myocardial infarction is performed to validate the feasibility and evaluate the performance of the system. This new multiplexed flow cytometry strategy is expected to enable low-cost and onsite detection of multiple biomarkers.

Enhancing Cytoplasmic Expression of Exogenous mRNA through Dynamic Mechanical Stimulation.

Ionizable lipid nanoparticles (LNPs) have been pivotal in combating COVID-19, and numerous preclinical and clinical studies have highlighted their potential in nucleic acid-based therapies and vaccines. However, the effectiveness of endosomal escape for the nucleic acid cargos encapsulated in LNPs is still low, leading to suboptimal treatment outcomes and side effects. Hence, improving endosomal escape is crucial for enhancing the efficacy of nucleic acid delivery using LNPs. Here, a mechanical oscillation (frequency: 65 Hz) is utilized to prompt the LNP-mediated endosomal escape. The results reveal this mechanical oscillation can induce the combination and fusion between LNPs with opposite surface charges, enhance endosomal escape of mRNA, and increase the transfection efficiency of mRNA. Additionally, cell viability remains high at 99.3% after treatment with oscillation, which is comparable to that of untreated cells. Furthermore, there is no obvious damage to mitochondrial membrane potential and Golgi apparatus integrity. Thus, this work presents a user-friendly and safe approach to enhancing endosomal escape of mRNA and boosting gene expression. As a result, our work can be potentially utilized in both research and clinical fields to facilitate LNP-based delivery by enabling more effective release of LNP-encapsulated cargos from endosomes.

Automated Transformation of Unstructured Cardiovascular Diagnostic Reports into Structured Datasets Using Sequentially Deployed Large Language Models.

Rich data in cardiovascular diagnostic testing are often sequestered in unstructured reports, with the necessity of manual abstraction limiting their use in real-time applications in patient care and research. We developed a two-step process that sequentially deploys generative and interpretative large language models (LLMs; Llama2 70b and Llama2 13b). Using a Llama2 70b model, we generated varying formats of transthoracic echocardiogram (TTE) reports from 3,000 real-world echo reports with paired structured elements, leveraging temporal changes in reporting formats to define the variations. Subsequently, we fine-tuned Llama2 13b using sequentially larger batches of generated echo reports as inputs, to extract data from free-text narratives across 18 clinically relevant echocardiographic fields. This was set up as a prompt-based supervised training task. We evaluated the fine-tuned Llama2 13b model, HeartDx-LM, on several distinct echocardiographic datasets: (i) reports across the different time periods and formats at Yale New Haven Health System (YNHHS), (ii) the Medical Information Mart for Intensive Care (MIMIC) III dataset, and (iii) the MIMIC IV dataset. We used the accuracy of extracted fields and Cohen's Kappa as the metrics and have publicly released the HeartDX-LM model. The HeartDX-LM model was trained on randomly selected 2,000 synthetic echo reports with varying formats and paired structured labels, with a wide range of clinical findings. We identified a lower threshold of 500 annotated reports required for fine-tuning Llama2 13b to achieve stable and consistent performance. At YNHHS, the HeartDx-LM model accurately extracted 69,144 out of 70,032 values (98.7%) across 18 clinical fields from unstructured reports in the test set from contemporary records where paired structured data were also available. In older echo reports where only unstructured reports were available, the model achieved 87.1% accuracy against expert annotations for the same 18 fields for a random sample of 100 reports. Similarly, in expert-annotated external validation sets from MIMIC-IV and MIMIC-III, HeartDx-LM correctly extracted 201 out of 220 available values (91.3%) and 615 out of 707 available values (87.9%), respectively, from 100 randomly chosen and expert annotated echo reports from each set. We developed a novel method using paired large and moderate-sized LLMs to automate the extraction of unstructured echocardiographic reports into tabular datasets. Our approach represents a scalable strategy that transforms unstructured reports into computable elements that can be leveraged to improve cardiovascular care quality and enable research.

Clinicians’ roles and necessary levels of understanding in the use of artificial intelligence: A qualitative interview study with German medical students

BackgroundArtificial intelligence-driven Clinical Decision Support Systems (AI-CDSS) are being increasingly introduced into various domains of health care for diagnostic, prognostic, therapeutic and other purposes. A significant part of the discourse on ethically appropriate conditions relate to the levels of understanding and explicability needed for ensuring responsible clinical decision-making when using AI-CDSS. Empirical evidence on stakeholders’ viewpoints on these issues is scarce so far. The present study complements the empirical-ethical body of research by, on the one hand, investigating the requirements for understanding and explicability in depth with regard to the rationale behind them. On the other hand, it surveys medical students at the end of their studies as stakeholders, of whom little data is available so far, but for whom AI-CDSS will be an important part of their medical practice.MethodsFifteen semi-structured qualitative interviews (each lasting an average of 56 min) were conducted with German medical students to investigate their perspectives and attitudes on the use of AI-CDSS. The problem-centred interviews draw on two hypothetical case vignettes of AI-CDSS employed in nephrology and surgery. Interviewees’ perceptions and convictions of their own clinical role and responsibilities in dealing with AI-CDSS were elicited as well as viewpoints on explicability as well as the necessary level of understanding and competencies needed on the clinicians’ side. The qualitative data were analysed according to key principles of qualitative content analysis (Kuckartz).ResultsIn response to the central question about the necessary understanding of AI-CDSS tools and the emergence of their outputs as well as the reasons for the requirements placed on them, two types of argumentation could be differentiated inductively from the interviewees’ statements: the first type, the clinician as a systemic trustee (or “the one relying”), highlights that there needs to be empirical evidence and adequate approval processes that guarantee minimised harm and a clinical benefit from the employment of an AI-CDSS. Based on proof of these requirements, the use of an AI-CDSS would be appropriate, as according to “the one relying”, clinicians should choose those measures that statistically cause the least harm. The second type, the clinician as an individual expert (or “the one controlling”), sets higher prerequisites that go beyond ensuring empirical evidence and adequate approval processes. These higher prerequisites relate to the clinician’s necessary level of competence and understanding of how a specific AI-CDSS works and how to use it properly in order to evaluate its outputs and to mitigate potential risks for the individual patient. Both types are unified in their high esteem of evidence-based clinical practice and the need to communicate with the patient on the use of medical AI. However, the interviewees’ different conceptions of the clinician’s role and responsibilities cause them to have different requirements regarding the clinician’s understanding and explicability of an AI-CDSS beyond the proof of benefit.ConclusionsThe study results highlight two different types among (future) clinicians regarding their view of the necessary levels of understanding and competence. These findings should inform the debate on appropriate training programmes and professional standards (e.g. clinical practice guidelines) that enable the safe and effective clinical employment of AI-CDSS in various clinical fields. While current approaches search for appropriate minimum requirements of the necessary understanding and competence, the differences between (future) clinicians in terms of their information and understanding needs described here can lead to more differentiated approaches to solutions.