Diagnostic Pathway Research Articles

Extensive Review on Multiple Disease Detection using Machine Learning

Diagnosing diseases rapidly are critical for improving patient outcomes, yet the usual diagnostic pathway causes significant delays due to extended waiting periods between sessions and advanced diagnostic tools. This review paper presents a study on the application of machine learning algorithms for multi-disease identification utilizing crowdsourced symptoms and a web-based platform. In this study, we want to investigate how machine learning algorithms might enhance diagnosis speed and accuracy by predicting diseases based on symptom data. Integrating such a technology into practice workflows can assist healthcare providers in prioritizing testing procedures based on detected risk, allowing for quicker patient diagnosis and treatment. Existing literature on machine learning applications in disease detection Challenges prevailing today for multidisease prediction currently covered within the review. In the end, this application potentially stands to improve patient care access by eliminating complex cases and thereby freeing up clinical expert time for more difficult patients as well as data-driven insights that can lead to better healthcare outcomes.

Mainstreaming cancer genetics: feasibility of an advanced nurse practitioner-led service diagnosing Lynch syndrome from colorectal cancer in Ireland.

Colorectal cancer (CRC) is a common cancer in Ireland. Of all CRCs, 2-4% are attributable to Lynch Syndrome (LS), the most common CRC predisposition syndrome. LS is caused by constitutional pathogenic variants (PVs) affecting mismatch repair (MMR) genes with resultant MMR protein deficiency (dMMR). Screening of all CRCs with MMR immunohistochemistry (IHC) testing is advocated to increase the detection of LS. However, successful implementation requires appropriate downstream management. In Ireland the traditional pathway involves referral to cancer genetics services to assess eligibility for genetic testing. Cancer genetics services in Ireland face many challenges in providing uniform access to timely healthcare with current wait times for assessment in excess of 1 year. An increasingly adopted pathway is that of mainstreaming, whereby genetic testing is managed locally by a multidisciplinary team member. Our institution therefore implemented an Advanced Nurse Practitioner (ANP)-led service with responsibility for the LS Diagnostic Pathway and mainstream genetic testing. Data was extracted from a prospectively maintained database of all newly diagnosed CRC patients discussed at our institutions CRC multidisciplinary meeting (MDM) between January 1st, 2023, and May 31st, 2024. MMR IHC testing was performed in 97.9% of the 385 patients diagnosed with CRC. The median time from histological confirmation of CRC to the availability of the MMR IHC report was 6 days. All 51 patients (100%) who required sequential tumor testing underwent BRAF V600 ± MLH1 promoter methylation testing. Additionally, 100% of the 14 patients eligible for mainstream genetic testing were referred to the ANP-led genetics service. The median time from the initial MDM discussion to the initiation of genetic testing was 69 days, while the median time from testing to the availability of results was 19 days. Patients received their results within a median of 21 days. MMR IHC testing increases the detection of LS through identification of dMMR tumours. Successful downstream delivery of clinical services, however, requires appropriate subsequent management, in a resource-limited environment. Our institutional experience demonstrates the feasibility, efficiency, and effectiveness of an ANP-led mainstreaming model of care for hereditary colorectal cancer.

Clinical utility of administering the WISC-V as standard practice in paediatric attention-deficit/hyperactivity disorder (ADHD) assessments in a public hospital and health system: a rapid review to inform clinical practice

ABSTRACT Objective The purpose of this rapid review is to appraise the current evidence-base to inform the development of a new assessment and diagnostic pathway for ADHD presentations in a public health paediatric department in Brisbane. We posited that the standardised WISC-V administration in all ADHD presentations regardless of cognitive indication was low-value, inefficient and burdensome for clinicians, children and their families. We wanted to find out if the literature supports this position. Method This review used PRISMA systematic methods to search two relevant databases (PUBMED, and Elsevier (ClinicalKey)). Search terms were used: (attention deficit hyperactivity disorder OR ADHD) AND (children) AND (assessment OR diagnosis) AND (Australia) AND (cognitive proficiency) OR (WISC). Results Search returned 286 full text journal articles, published between 2018 and 2023. Two hundred and sixty-two were removed to irrelevance, adult population, duplications, or focus on other paediatric mental health disorders. Following the application of exclusion criteria, 10 were reviewed at full text and four were ultimately included for contribution to this rapid review. Conclusions Neuropsychological testing if no cognitive query is indicated may confound the findings. This review provided the opportunity to improve clinical efficiency without compromising diagnostic accuracy.

MS O02 - OGC An audit of waiting times of the oesophagogastric cancer diagnostic pathway at a high-volume, tertiary centre

Abstract Background The oesophagogastric cancer (OGC) staging pathway is extensive, contributing to prolonged waiting times from referral to treatment. NHS England guidance details the ideal timeframe from referral to finalisation of the patient’s treatment plan and stipulates a time of 21 days from OGD to communication of the treatment plan to the patient. This audit aims to compare pathway times at a tertiary cancer centre, which accepts referrals from seven different hospitals, to the current NHS target and further stratify pathway times according to patient characteristics and referring hospitals. Method Data was collected using a prospectively collected database of OGC patients who underwent staging investigations at the tertiary centre between October 2022 and October 2023. The primary outcome was OGD to communication of the treatment plan. Secondary outcomes included time from OGD to first staging investigation and the proportion of patients that had a next-day computed tomography (CT) scan. Outcomes were stratified to investigate inter-hospital variation and the effect of curative status and tumour location. Data was expressed as median and interquartile range (IQR) for continuous data or n (%) if categorical. Results 263 patients were included in this audit with a median age of 69.0 (IQR 61.5-77.0). 13.8% of patients satisfied the target time of 21 days from OGD to communication of treatment plan. Curative patients had a longer median pathway time than palliative patients (49.0 vs 35.0 days), whereas oesophageal and gastric cancer patients had similar pathway times (44.0 vs 44.5 days). Patients diagnosed at the tertiary centre had a faster time from OGD to first staging investigation than patients diagnosed at non-specialist centres. Only 13.3% of patients had a next-day CT scan following their OGD (median time 5.0 days). Conclusion The OGC staging pathway is considerably slower than the target. Faster pathway times in palliative patients can be attributed to many of these patients not requiring further staging post-CT. Potentially, targets should be re-evaluated to distinguish between palliative and curative patients. The faster staging process at the central hospital may be explained by more regular clinics run by specialist clinicians and the prompt requesting of staging investigations without awaiting MDT discussions. Alongside increasing the proportion of next-day CT scans, these factors must be addressed to streamline the entire pathway.

Diagnostic Window Prior to a Haematological Cancer Diagnosis and the Association With Patient Pathways: A Nationwide Register-Based Cohort Study on Healthcare Utilization in Denmark.

This study investigated healthcare utilisation in general practice and hospitals in the 2 years preceding a diagnosis of haematological cancer and the association with patient pathways. The nationwide register-based cohort study included 12 994 patients diagnosed with leukaemia, multiple myeloma and lymphoma in 2014-2018 and 10 matched references. Patient pathways were analysed in unplanned routes (acute admission up to 1 month's prior diagnosis) and elective routes (other routes, e.g., cancer patient pathways). Female patients in unplanned diagnostic pathways had more contacts to general practice from 19 months before the diagnosis compared to their matched references; with IRR increasing from 1.14 (95% confidence interval (CI) 1.05-1.24) to 2.27 (95% CI 2.13-2.41) at 30-60 days before the diagnosis. Female patients had more point-of-care tests, hospital contacts and radiological investigations at 17, 24 and 17 months, respectively, before diagnosis compared to their references. Similar patterns were seen for male patients, although with a later onset of increase. No healthcare use variations were seen between patients diagnosed in unplanned versus elective pathways. Increased healthcare utilisation was seen in general practice and hospitals up to 24 months preceding a diagnosis, which may indicate a diagnostic window for detecting haematological cancer earlier.

Validation of a urine- based proteomics test to predict clinically significant prostate cancer: complementing mpMRI pathway.

INTRODUCTIONː Prostate cancer (PCa) is the most frequently diagnosed cancer among men. A major clinical need is to accurately predict clinically significant PCa (csPCa). A proteomics-based 19-biomarker model (19-BM) was previously developed using capillary electrophoresis-mass spectrometry (CE-MS) and validated in 1000 patients at risk for PCa. This study aimed to validate 19-BM in a multicenter prospective cohort of 101 biopsy-naive patients using current diagnostic pathways. METHODSː Urine samples from 101 patients with PCa were analyzed using CE-MS. All patients underwent MRI using a 3-T system. The 19-BM score was estimated using support vector machine-based software (MosaCluster v1.7.0), employing a previously established cut-off criterion of -0.07. Previously developed diagnostic nomograms were calculated along with MRI. RESULTSː Independent validation of 19-BM yielded a sensitivity of 77% and a specificity of 85% (AUC:0.81). This performance surpassed those of PSA (AUC:0.56) and PSA density (AUC:0.69). For PI-RADS≤ 3 patients, 19-BM showed a sensitivity of 86% and a specificity of 88%. Integrating 19-BM with MRI resulted in significantly better accuracy (AUC:0.90) compared to individual investigations alone (AUC19BM=0.81; p=0.004 and AUCMRI:0.79; p=0.001). Examining the decision curve analysis, 19-BM with MRI surpassed other approaches for the prevailing risk interval from a 30% cut-off. CONCLUSIONSː 19-BM exhibited favorable reproducibility for the prediction of csPCa. In patients with PI-RADS≤3, 19-BM correctly classified 88% of the patients with insignificant PCa at the cost of one missed csPCa patient. Utilizing the 19-BM test could prove valuable in complementing MRI and reducing the need for unnecessary biopsies.

Developmental and Epileptic Encephalopathies: Need for Bridging the Gaps Between Clinical Syndromes and Underlying Genetic Etiologies.

Advancement in genetic testing has become increasingly important in diagnosing and managing developmental and epileptic encephalopathies (DEEs), a group of rare neurodevelopmental disorders characterized by early-onset seizures, developmental delay, and electroencephalographic (EEG) abnormalities. These early epileptic encephalopathies are often described as various syndromes as per their clearly defined, relatively uniform, and distinct clinical phenotypes with consistent EEG and/or neuroimaging findings. Finding the underlying molecular mechanisms can cause a definitive change in the management strategy. With the evolving overlapping phenotypes, advent of technologies, and discovery of new genes, it is exceedingly becoming challenging to correctly characterise these disorders and plan subsequent evidence-based management. Cytogenetic microarray (CMA) and next generation sequencing (NGS) with improved data analysis pipe-lines and algorithms have revamped the diagnostic yield dramatically. However, as of now, there is a big lacuna in step-wise evaluation guideline or consensus on integration of genetic testing results with management plan. Understanding the genetic etiologies of such syndromes timely has three major implications: (1) Knowing the outcome of such a syndrome, (2) Therapeutic implications including licensing of drugs for certain forms (e.g. genetic syndromes involving ion channels) and (3) Genetic counseling, prenatal testing and choosing reproductive options in future pregnancies in such families. The focus of this review is to provide an understanding of different types of causative variants and their step-wise genetic testing approach; the most pressing clinical need and to develop an optimal diagnostic pathway for this group of patients.

Pre and post diagnostic dementia care in four Scottish prisons

Background and purposeThe number of older people in prisons is increasing across the globe. Many have poor physical and mental health, higher prevalence of head injury, cognitive impairment and dementia than found in community populations. Meeting the complex needs of this vulnerable group has become an increasing concern for prison and prison healthcare services. The aim of this multi method qualitative study was to investigate how men with diagnosed or suspected dementia were identified, assessed, and cared for in Scottish prisons. It also explored the lived experience of individuals being assessed for or diagnosed with dementia within four prisons. The data from twenty nine interviews was thematically analysed and used to collaboratively propose principles for dementia care in prison and present the resultant co-designed care pathway.ResultsAt the time of data collection almost all the men known to have a dementia diagnosis or suspected dementia had complex health and social care needs, and some were living with advanced dementia. Prison healthcare staff reported taking a ‘case by case’ approach to their pre- and post-diagnostic care. Meeting these prisoner’s needs was complicated by the absence of organisational leads for care of older adults or people with dementia and there was no pathway or model in place to guide staff. Prison healthcare teams often had difficulty accessing specialist community services to support diagnosis. There was a lack of dementia education and knowledge about how to provide pre and post diagnostic dementia care in this setting amongst staff. The findings arising from this research have informed the co-production of two important evidence informed innovations namely a Model of Care and a pre- and post-diagnostic Care Pathway.ConclusionThis research adds insights critical to understanding the adequacy of current approaches to meeting dementia related needs within the prison setting. To our knowledge this paper offers the first co-produced evidence informed pre- and post- diagnostic dementia care pathway and model of care for use in prisons. These could serve as tools for change that could enable prison healthcare staff to deliver the right care, at the right time, by the right people, and provide an opportunity to assess risk and plan care for the future.

The Complementary Role of Cardiopulmonary Exercise Testing in Coronary Artery Disease: From Early Diagnosis to Tailored Management

Coronary artery disease (CAD) remains a leading cause of morbidity and mortality worldwide, accounting for over 9 million deaths annually. The prevalence of CAD continues to rise, driven by ageing and the increasing prevalence of risk factors such as hypertension, diabetes, and obesity. Current clinical guidelines emphasize the importance of functional tests in the diagnostic pathway, particularly for assessing the presence and severity of ischemia. While recommended tests are valuable, they may not fully capture the complex physiological responses to exercise or provide the necessary detail to tailor personalized treatment plans. Cardiopulmonary exercise testing (CPET) offers a comprehensive assessment of the cardiovascular, pulmonary, and muscular systems under stress, potentially addressing these gaps and providing a more precise understanding of CAD, particularly in settings where traditional diagnostics may be insufficient. By enabling more personalized and precise treatment strategies, CPET could play a central role in the future of CAD management. This narrative review examines the current evidence supporting the use of CPET in CAD diagnosis and management and explores the potential for integrating CPET into existing clinical guidelines, considering its diagnostic and prognostic capabilities, cost-effectiveness, and the challenges associated with its adoption.

Changes in diagnostics and treatment pathways for developmental dysplasia of the hip after the introduction of national guidelines: An updated questionnaire amongst paediatric orthopaedic surgeons in The Netherlands.

Diagnostics and treatment pathways for developmental dysplasia of the hip are highly variable in clinical practice. Recently, two national guidelines were developed in the Netherlands, providing a uniform protocol for the diagnosis and treatment of developmental dysplasia of the hip in children under the age of 1 year. The aim of this survey study was to assess whether diagnostic and treatment strategies have changed amongst paediatric orthopaedic surgeons in the Netherlands compared to a similar survey study in 2011, after the introduction of the guidelines. A web-based online questionnaire was developed and shared amongst the members of the Dutch Paediatric Orthopaedic Society. The questions concerned the diagnosis and treatment of developmental dysplasia of the hip, ranging from mildly dysplastic to dislocated hips, in children under the age of 1 year. We used a questionnaire similar to the previous study and evaluated the results. Thirty-four participants completed the survey. Regarding diagnosis and follow-up, ultrasonography was generally applied for children younger than 6 months, while radiography was more frequently used for children aged 6-12 months. In 2011, radiography was more widely applied in all age groups. Initial treatment for dysplastic, stable hips was mostly active monitoring, while this was generally a rigid splint in 2011. For dislocated unstable hips, the first step in treatment was generally the Pavlik harness, as in 2011. The diagnostic and treatment pathways of developmental dysplasia of the hip in children under the age of 1 year seem to have partially changed amongst Dutch paediatric orthopaedic surgeons compared to 2011, after the publication of new guidelines.

Non-invasive imaging modalities for diagnosing pulsatile tinnitus: a comprehensive review and recommended imaging algorithm.

Pulsatile tinnitus (PT) is a challenging diagnostic condition arising from various vascular, neoplastic, and systemic disorders. Non-invasive imaging is essential for identifying underlying causes while minimizing risks of invasive diagnostic angiography. Although no consensus exists on the primary imaging modality for PT and currently CT, ultrasound, and MRI are used in the diagnostic pathway, MRI is increasingly preferred as the first-line screening test for its diagnostic efficacy and safety. MRI protocols such as time-of-flight, magnetic resonance angiography, diffusion-weighted imaging, and arterial spin labeling can identify serious causes, including vascular shunting lesions, venous sinus stenosis, and tumors. In this narrative review of the current literature we discuss the benefits and limitations of various non-invasive imaging modalities in identifying the characteristic imaging findings of the most common causes of PT and also provide an algorithm that clinicians can use to guide the imaging evaluation.

Economic impact case study of a wearable medical device for the diagnosis of obstructive sleep apnoea

BackgroundAcuPebble SA100 (‘AcuPebble’) is a novel wearable medical device to diagnose obstructive sleep apnoea (OSA). This paper investigates the potential economic impact of the technology in the UK through cost savings analysis, and the redirection of savings into further diagnoses.MethodsA cost comparison study was conducted, comparing AcuPebble to the standard diagnostic approach of home respiratory polygraphy (HRP) and in-clinic polysomnography (PSG), estimating the net benefit value (NBV) and return on investment (ROI). Cohort size was varied to model the effects of volume discounted pricing and staff training costs. To demonstrate the potential for cost savings, data on the healthcare costs of undiagnosed OSA patients were used to quantify the benefit of increased OSA diagnosis rates, as facilitated by AcuPebble.ResultsFor 500 uses of AcuPebble, the NBV in the diagnostic pathway over one year would be in excess of £101,169, increasing to £341,665 for 1,500 uses, £1,263,993 for 5,000 uses, and to £2,628,198 for 10,000 uses, with ROIs of 2.02, 3.03, 5.05, and 6.56, respectively. Given an initial cohort of 1,500 patients, 4,555 extra AcuPebble studies could be completed by redirecting resources from HRP/PSG. Direct cost savings to the NHS from resultant lower undiagnosed rates could be between £24,147 and £4,707,810, based on the cost per use and the percentage of tests that result in a positive diagnosis (varied from 25 to 75% positives).ConclusionsAcuPebble presents an opportunity for substantial healthcare savings, enabling an increase in the number of people tested, diagnosed and treated for OSA.

General practitioners’ perspectives on targeted breast ultrasound as primary diagnostic test in women with focal breast complaints: An interview study

IntroductionThe high diagnostic accuracy of ultrasound opens possibilities to shift towards an initial ultrasound approach for the evaluation of focal breast complaints in women, with only additional DBT in case of unclear or suspicious ultrasound findings. As general practitioners (GPs) are important stakeholders in the diagnostic pathway, this study focuses on GPs perspective on ultrasound as primary diagnostic imaging test, as well as the GP referral process. MethodsSixteen Dutch GPs were interviewed on the referral process and their perceived barriers and facilitators of initial ultrasound diagnostics in women presenting with focal breast complaints. Interview data were transcribed verbatim and analyzed thematically. ResultsThematic analysis identified themes related to 1) the routine breast consult (consult characteristics, referral decision, referral rationale and diagnostic imaging decision) and 2) considerations of an ultrasound-only approach. Regarding the latter, the theme diagnostic workflow emphasizes GPs concerns regarding long waiting times for ultrasound. Professional communication describes communicational barriers on patient-radiologist and radiologist-GP level. In the theme doctor-patient relationship shared decision-making was highlighted, while concerns existed on the lack of patient return to the GP after result disclosure at the hospital. Effectiveness of imaging is associated with GPs’ acceptance of the diagnostic performance of ultrasound as stand-alone modality. Personal expertise and workload is related to consequences of an initial ultrasound approach on GPs workload and professional tasks. Regarding the patient benefit-harm trade-off, various patient (dis)advantages were highlighted. Decentralization of diagnostic evaluation was considered a potential practical implication of ultrasound as primary diagnostic test. ConclusionParticipants seemed to welcome ultrasound-only diagnostics for the evaluation of women's focal breast complaints, emphasizing multiple benefits for both the patients and GPs. They, however, also addressed various challenges that should be taken into consideration when actually practicing an initial ultrasound approach.

Epidemiology of myocarditis following COVID-19 or influenza and use of diagnostic assessments

BackgroundPrevious research has suggested a heightened risk of acute myocarditis after COVID-19 infection. However, it is not clear from existing work whether this risk is higher than would be expected...

Implementation of a kidney genetic service into the diagnostic pathway for patients with chronic kidney disease in Canada.

Implementation of a kidney genetic service into the diagnostic pathway for patients with chronic kidney disease in Canada.

Identifying the facilitators and barriers to implementation of renal tumour biopsy in the diagnostic pathway for small renal masses.

To understand the facilitators and barriers to the implementation of renal tumour biopsy (RTB) in the diagnostic pathway for renal tumours in England. Participants consisted of patients who had a renal tumour diagnosed and/or treated at one of five tertiary centres in England, healthcare professionals involved in the direct care of patients diagnosed with renal tumours, and clinical service managers and commissioners. The study employed a mixed-methods research methodology consisting of individual interviews and an on-line survey that explored the types of facilitators and barriers individuals perceived and experienced and the frequency in which these were reported. A public dissemination event took place following the completion of data collection; to facilitate discussion of potential solutions to implementing RTB. There were 50 participant interviews (23 patients, 22 clinicians, and five health service commissioners/operations managers). The patient on-line survey received 52 responses, and the clinician survey received 22 responses. Patients most frequently reported influences in choosing whether to undergo RTB pertained to wanting to know the diagnosis of their kidney mass (40%), the advice or information provided by healthcare professionals (40%), and not wishing to delay treatment (23%). Clinicians most frequently reported barriers to recommending RTB related to their uncertainty of diagnostic accuracy (56%), availability of appointments or hospital beds (52%), concerns of risk of bleeding (44%), risk of seeding (41%), and delays in meeting national cancer pathway targets (41%). The dissemination event was attended by 18 participants (seven patients and 11 clinicians). Suggestions to improve implementation included reducing variation and promotion of standardisation of practice by a consensus statement, increasing the evidence base (clinicians) and improved communication by developing better patient aids such as videos and diagrams (patients and clinicians). Implementation of RTB may be dependent on the quality of information provided, its format and perceived reliability of the information. Increased utilisation of RTB may be improved by development of a consensus statement on the role of biopsy, with patients expressing a preference for alternative information aids such as patient videos.

SCD programmatic diagnostic strategy and diagnostic pathway for vertigo disease

Vertigo （or dizziness） is one of the most common symptoms in clinical practice. The misdiagnosis rate of vertigo diseases is high due to the factors that vertigo disorders involve multiple systems and organs throughout the body with a wide range of pathogenesis, and different kind of vertigo diseases often present with overlapping clinical presentation. In recent years, scholars have conducted many explorations in the diagnosis model of vertigo disorders, the identification model of high-risk central vertigo, or the combination of diagnostic tests such as the TiTrATE diagnostic model for vertigo disorders （Newman-Toker and Edlow, 2015）, the ATTEST differential diagnosis model for acute vertigo （Gurley and Edlow, 2019）; the application of the ABCD2 score to assess the risk of high-risk vertigo （Navi et al, 2012）, and the "TriAGe+" score to assess the risk of stroke in vertigo patients （Kuroda et al, 2017）; HINTS battery （Kattah et al, 2009）, HINTS+ battery （Newman-Toker et al, 2013）, and STANDING battery （Vanni et al, 2014） for acute serious vestibular disorders. These diagnostic approaches are immensely beneficial in enhancing the accuracy of vertigo diagnosis, as well as for identifying high-risk central vertigo with reducing the misdiagnosis of vertigo. Based on clinical experience, with referring to the diagnostic approaches mentioned above, the author propose the SCD programmatic diagnostic strategy for vertigo disorders[Strategy 1: Classification of vertigo syndromes （syndromes, S）; Strategy 2: Identify/diagnose high-risk central vertigo （central, C）; Strategy 3: differential diagnosis of peripheral vertigo （disease, D） ] and the A·E³GAP·AT differentiation battery and A²B²C²D²E³ alarm battery for dangerous central vertigo as well as targeted identifying and examining of E³GAP battery for central vertigo in five steps.The SCD programmatic diagnostic strategy for vertigo disorders is beneficial for clinicians to grasp diagnostic approach and pay special attention to dangerous central vertigo, while mastering the differential diagnosis model of dangerous central vertigo as well as the rapid diagnostic approach of peripheral vertigo.

Heart failure with preserved ejection fraction: diagnostic value of HFA-PEFF score, H₂FPEF score, and the diastolic stress echocardiography.

The aim of our study was to compare 3 diagnostic pathways: diastolic stress echocardiography (DSE) based on the ASE/EACVI 2016 guidelines, the 2018 H₂FPEF score, and the 2019 HFA-PEFF algorithm, in patients suspected of heart failure with preserved ejection fraction (HFpEF). The study group included 80 consecutive patients with a clinical suspicion of HFpEF. The H₂FPEF and HFA-PEFF scores and serum NT-proBNP concentrations were assessed in all the patients before they were sent for DSE. The DSE-based pathway confirmed HFpEF in 17 (21%) patients, the HFA-PEFF algorithm in 43 (54%), and H₂FPEF scoring in 4 (5%) patients. The ROC analysis showed that HFA-PEFF score > 5 predicts a DSE-positive test with a sensitivity of 70.5% and a specificity of 65%, (AUC = 0.711, p = 0.002) with a negative predictive value of 89.1% and positive predictive value of 35.3%. The H₂FPEF score > 3 had a negative predictive value of 90%, a positive predictive value of 29.8%, and predicted positive DSE result with a sensitivity of 82.3% but rather poor specificity of 47.6% (AUC = 0.692, p = 0.004). Both H₂FPEF and HFA-PEFF showed similar predictive values (AUC) in the prediction of positive DSE test (p = ns). The HFA-PEFF score overestimated the rate of HFpEF in comparison to DSE and the H₂FPEF score. The H₂FPEF and HFA-PEFF scores showed only modest predictive values of the positive DSE and had a diagnostic power to rule out the HFpEF.

Recent Advances in Artificial Intelligence to Improve Immunotherapy and the Use of Digital Twins to Identify Prognosis of Patients with Solid Tumors.

To date, the public health system has been impacted by the increasing costs of many diagnostic and therapeutic pathways due to limited resources. At the same time, we are constantly seeking to improve these paths through approaches aimed at personalized medicine. To achieve the required levels of diagnostic and therapeutic precision, it is necessary to integrate data from different sources and simulation platforms. Today, artificial intelligence (AI), machine learning (ML), and predictive computer models are more efficient at guiding decisions regarding better therapies and medical procedures. The evolution of these multiparametric and multimodal systems has led to the creation of digital twins (DTs). The goal of our review is to summarize AI applications in discovering new immunotherapies and developing predictive models for more precise immunotherapeutic decision-making. The findings from this literature review highlight that DTs, particularly predictive mathematical models, will be pivotal in advancing healthcare outcomes. Over time, DTs will indeed bring the benefits of diagnostic precision and personalized treatment to a broader spectrum of patients.

What does routine healthcare data tell us about the diagnostic pathway for older people with heart failure in Wales: under-testing, problems with access, or poor coding?

Abstract Background United Kingdom guidelines (NICE, NG106) for suspected chronic heart failure (HF) recommend that NT pro-BNP is performed as a first-line test. The result is also used to triage individuals; when NT pro-BNP is <400ng/L, a diagnosis of HF is less likely, echocardiography (echo) and specialist assessment should be performed within 6 weeks when the result is 400-2000ng/L, and within 2 weeks if >2000ng/L. How accurately this guidance is followed in clinical practice in Wales is not known. Purpose To examine how the current diagnostic pathway is recorded in routinely-collected electronic health record (EHR) data for older people in Wales with a diagnosis of heart failure. Methods We conducted a retrospective, population-level, observational study using linked anonymised EHR data in Wales (2015-22). We included patients aged 65y+ with a HF diagnosis in their primary or secondary care records and with a minimum of 12m pre and post-diagnosis data (for assessment of diagnostic pathway). We looked back from the point of HF diagnosis for codes associated with prior cardiovascular conditions (any time prior), symptoms (within 3 years), and key diagnostic tests (within 90 days). Results The final cohort comprised 51,020 individuals 65y and over with a diagnosis of heart failure between 2015-2022. Incidence and prevalence of heart failure increased across the study period (1.4-1.5% and 8.5-9.1% respectively). HF diagnosis was first evident in secondary care records in 54.9%, in primary care 36.3%, and in both data sources on the same day in 8.8%. Preceding cardiovascular diagnoses included hypertension (69.5%), atrial fibrillation (36.7%), myocardial infarction (30.5%), coronary artery disease (25.7%), and valve disease (17.7%). The most common recorded symptoms preceding diagnosis were breathlessness (41.4%), ankle oedema (9.8%), and fatigue (8.8%). Searched for symptoms were not recorded in 43.8%. In the 90 days preceding the diagnosis, 7-30% had recorded NT pro-BNP with the number of tests increasing throughout the study period (Figure 1). In the 90 days prior to HF diagnosis, 28-31% had an echo recorded. NT pro-BNP was >2000ng/L in 51.8%, 400-2000ng/L in 38.6% and <400ng/L in 9.6%. Conclusions In Wales, a greater number of individuals with heart failure appear to be diagnosed during hospital admission, compared with primary care. Many individuals with a code for HF in their records, do not have recorded objective evidence of cardiac dysfunction. The proportion of first-line and definitive tests appears low. It is unclear whether this is because of under-referral, difficulty accessing tests in primary care, or inaccurate coding of test referrals and results. These results are important in evaluating health service delivery and workforce planning.