Predicting and Early Detection of Delirium through Motion Patterns: A Narrative Review.

International Liver Cancer Association (ILCA) White Paper on Biomarker Development for Hepatocellular Carcinoma

Background: Recognition and early detection of delirium in the intensive care unit (ICU) is essential to improve ICU outcomes. To date, neutrophil-lymphocyte ratio (NLR), one of inflammatory markers, has been proposed as a potential biomarker for brain disorders related to neuroinflammation. This study aimed to investigate whether NLR could be utilized in early detection of delirium in the ICU. Methods: Of 10144 patients who admitted to the ICU, 1112 delirium patients (DE) were included in the current study. To compare among inflammatory markers, NLR, C-reactive protein (CRP), and white blood cell (WBC) counts were obtained: the mean NLR, CRP levels, and WBC counts between the initial day of ICU admission and the day of initial delirium onset within DE were examined. The inflammatory marker of 1272 non-delirium patients (ND) were also comparatively measured as a supplement. Further comparisons included a subgroup analysis based on delirium subtypes (non-hypoactive versus hypoactive) or admission types (elective versus emergent). Results: The NLR and CRP levels in DE increased on the day of delirium onset compared to the initial admission day. ND also showed increased CRP levels on the sixth day (the closest day to average delirium onset day among DE) of ICU admission compared to baseline, while NLR in ND did not show significant difference over time. In further analyses, the CRP level of the non-hypoactive group was more increased than that of the hypoactive group during the delirium onset. NLR, however, was more significantly increased in patients with elective admission than in those with emergent admission. Conclusion: Elevation of NLR was more closely linked to the onset of delirium compared to other inflammatory markers, indicating that NLR may play a role in early detection of delirium.

Background: Recognition and early detection of delirium in the intensive care unit (ICU) is essential to improve ICU outcomes. To date, neutrophil-lymphocyte ratio (NLR), one of inflammatory markers, has been proposed as a potential biomarker for brain disorders related to neuroinflammation. This study aimed to investigate whether NLR could be utilized in early detection of delirium in the ICU.Methods: Of 10,144 patients who admitted to the ICU, 1,112 delirium patients (DE) were included in the current study. To compare among inflammatory markers, NLR, C-reactive protein (CRP), and white blood cell (WBC) counts were obtained: the mean NLR, CRP levels, and WBC counts between the initial day of ICU admission and the day of initial delirium onset within DE were examined. The inflammatory marker of 1,272 non-delirium patients (ND) were also comparatively measured as a supplement. Further comparisons included a subgroup analysis based on delirium subtypes (non-hypoactive vs. hypoactive) or admission types (elective vs. emergent).Results: The NLR and CRP levels in DE increased on the day of delirium onset compared to the initial admission day. ND also showed increased CRP levels on the sixth day (the closest day to average delirium onset day among DE) of ICU admission compared to baseline, while NLR in ND did not show significant difference over time. In further analyses, the CRP level of the non-hypoactive group was more increased than that of the hypoactive group during the delirium onset. NLR, however, was more significantly increased in patients with elective admission than in those with emergent admission.Conclusion: Elevation of NLR was more closely linked to the onset of delirium compared to other inflammatory markers, indicating that NLR may play a role in early detection of delirium.

Polygenic Risk Scores for Follow Up After Colonoscopy and Polypectomy: Another Tool for Risk Stratification and Planning Surveillance?

DETECT: Development of Technologies for Early HCC Detection

A New Data-Based Motor Subtype Schema for Delirium

Is it time to implement clinical decision rules for upper GI bleeding? Barriers, facilitators, and the need for a collaborative approach

Hepatocellular carcinoma (HCC) mortality remains high primarily due to late diagnosis as a consequence of failed early detection. Professional societies recommend semi-annual HCC screening in at-risk patients with chronic liver disease to increase the likelihood of curative treatment receipt and improve survival. However, recent dynamic shift of HCC etiologies from viral to metabolic liver diseases has significantly increased the potential target population for the screening, whereas annual incidence rate has become substantially lower. Thus, with the contemporary HCC etiologies, the traditional screening approach might not be practical and cost-effective. HCC screening consists of (i) definition of rational at-risk population, and subsequent (ii) repeated application of early detection tests to the population at regular intervals. The suboptimal performance of the currently available HCC screening tests highlights an urgent need for new modalities and strategies to improve early HCC detection. In this review, we overview recent developments of clinical, molecular, and imaging-based tools to address the current challenge, and discuss conceptual framework and approaches of their clinical translation and implementation. These encouraging progresses are expected to transform the current "one-size-fits-all" HCC screening into individualized precision approaches to early HCC detection and ultimately improve the poor HCC prognosis in the foreseeable future.

Risk Stratification Tools and Prognostic Models in Non–muscle-invasive Bladder Cancer: A Critical Assessment from the European Association of Urology Non-muscle-invasive Bladder Cancer Guidelines Panel

Background: Sexual assault survivors who present to emergency departments are not consistently offerered prophylaxis for HIV prevention because there are currently no national evidence-based practice protocols. Purpose: The project aim was to improve the provision rate of (N) PEP to SA survivors by providing a decision guideline risk stratification tool and appropriate training to forensic nurses who treated SA survivors who presented within 72-hours following an assault on how to use the risk assessment and stratification tool. Methods: A risk stratification tool provided HIV (N) PEP clinical decision guidelines and framework for use with adult survivors. Forensic and emergency department nurses (n=20 total) were given a pre-training knowledge assessment. Forensic nurses (n = 6) were given specific training in HIV risk stratification and use of the (N) PEP decision guideline tool. Knowledge scores were assessed immediately following training and three months after implementation of the risk stratification tool. Results: The average knowledge score of forensic and emergency department nurses increased following training, and remained higher after three months of implementation. Conclusion: The implementation of a locally-specific risk stratification decision guideline tool improved both provider knowledge and patient care as measured by an increase in appropriate (N) PEP treatment rates. Recommendations: Further research is needed to determine if risk stratification decision tools and standardized protocols improve provider knowledge across settings such as communities with different rates of SA, HIV prevalence, and socio-economic levels.

Prostate cancer (PC) remains a leading cause of malignancy in men worldwide, with current diagnostic methods such as prostate-specific antigen (PSA) testing and tissue biopsies facing limitations in specificity, invasiveness, and ability to capture tumor heterogeneity. Liquid biopsy, especially analysis of circulating tumor DNA (ctDNA), has emerged as a transformative tool for non-invasive detection, real-time monitoring, and treatment selection for PC. This review examines the role of ctDNA in both localized and metastatic PCs, focusing on its utility in early detection, risk stratification, therapy selection, and post-treatment monitoring. In localized PC, ctDNA-based biomarkers, including ctDNA fraction, methylation patterns, fragmentation profiles, and mutations, demonstrate promise in improving diagnostic accuracy and predicting disease recurrence. For metastatic PC, ctDNA analysis provides insights into tumor burden, genomic alterations, and resistance mechanisms, enabling immediate assessment of treatment response and guiding therapeutic decisions. Despite challenges such as the low ctDNA abundance in early-stage disease and the need for standardized protocols, advances in sequencing technologies and multimodal approaches enhance the clinical applicability of ctDNA. Integrating ctDNA with imaging and traditional biomarkers offers a pathway to precision oncology, ultimately improving outcomes. This review underscores the potential of ctDNA to redefine PC management while addressing current limitations and future directions for research and clinical implementation.

Invasive pulmonary aspergillosis (IPA) is increasingly recognized in non-neutropenic patients, where coexisting bacterial infections, particularly with Gram-negative pathogens, may impair susceptibility. However, validated tools for early risk stratification in this population remain unavailable. We retrospectively analyzed 437 non-neutropenic adults with bacterial co-infection (derivation N.=331; validation N.=106) admitted between 2019 and 2024. Independent predictors of IPA were identified through multivariable logistic regression and incorporated into both a weighted clinical risk score and an ensemble machine learning (ML) model. Model performance was assessed using discrimination, calibration, and decision curve analysis, with subgroup validation in Gram-negative infection, intensive care unit (ICU) admission, and diabetes. Seven independent predictors of IPA were identified: nodular shadow, chronic respiratory disease, Gram-negative infection, corticosteroid exposure, ICU admission, smoking history, and diabetes. Gram-negative pathogens accounted for nearly half of infections, with Pseudomonas aeruginosa predominating. The ensemble score achieved a strong performance (area under the curve [AUC] 0.922 derivation; 0.862 validation) with superior calibration compared to traditional approaches. Risk stratification at a threshold score of ≥7.5 significantly enriched 28-day IPA incidence (log-rank P<0.001). Subgroup analyses confirmed score robustness in Gram-negative infection (AUC=0.898), ICU admission (AUC=0.888), and diabetes (AUC=0.914). However, the predictive contributions of respiratory disease and corticosteroid exposure were attenuated in diabetic patients. Gram-negative bacterial co-infection synergistically amplifies IPA risk in non-neutropenic patients. The ensemble ML model integrating seven pragmatic predictors provides accurate, interpretable, and clinically actionable stratification, enabling precision prophylaxis and early antifungal intervention. Prospective multicenter validation is warranted before clinical implementation.

IntroductionDelirium is a fluctuating cognitive disorder that occurs in admitted patients, especially in patients who are in intensive care units. Nurses due to persistent contact with patients and direct observation of their mental changes play an essential role in delirium evaluation. Early detection of delirium, identification of risk factors, and its prevention methods are critical to reducing complications, mortality, and treatment costs. This study aimed to determine the perception and the practices of nurses in intensive care units to assess delirium and its barriers.Study designA cross-sectional study.Materials and methodsAll nurses working in the intensive care unit (neurology, trauma, surgery, general, and heart) of educational hospitals in Kerman, Iran, were the study population. The data gathering tool was a questionnaire consisting of four sections: demographic information, nurses’ perception, practices, and perceived barriers in delirium assessment.ResultsThe total score of nurses’ perception in delirium assessment was 19.47 ± 3.36, which was higher than the medium score of the questionnaire (estimated score = 16). In all, 45.5% of nurses reported having delirium treatment protocol in their units, and 12.1% of the nurses considered delirium as a priority of evaluating the patient's condition. The most important barrier to delirium assessment was the difficulty of assessing delirium in intubated patients. There was no association between nurses’ perception and practices (p value > 0.05).ConclusionDesigning and implementing educational programs for improving nurses’ practices in this field is necessary.Clinical significanceHealthcare providers, especially nurses, should be aware of the delirium assessment of the ICU patients to provide better care.How to cite this articleBiyabanaki F, Arab M, Dehghan M. Iranian Nurses Perception and Practices for Delirium Assessment in Intensive Care Units. Indian J Crit Care Med 2020;24(10):955–959.

&lt;p dir="ltr"&gt;Early cancer detection is critical for improving survival rates, yet it requires a careful balance between minimising missed diagnoses and avoiding over- investigation. Primary care plays a central role in this process. This thesis aims to enhance understanding of the complexities involved in early cancer detection by analysing symptoms and signs, with the goal of contributing to the development of risk assessment and prediction tools to identify cancer at an early stage within primary care.&lt;/p&gt;&lt;p dir="ltr"&gt;This thesis is based on five quantitative studies conducted within the Swedish healthcare system. Study I examined symptoms reported by referred patients via questionnaires at the Department of Pulmonary Medicine at Karolinska University Hospital. It investigated whether machine learning could predict which patients subsequently received a lung cancer diagnosis, stratified by smoking status. Studies II and III focused on comprehensive diagnostic data and coded symptoms from primary care to facilitate early detection of non-metastatic colorectal cancer, with Study II conducted in Region Stockholm and Study III in Region Västra Götaland. Studies IV and V used comprehensive clinical and laboratory data from the entire adult population of Stockholm County. Study IV presents a cohort description, while Study V examines the association and discriminatory capacity of newly developed anaemia as an indicator for cancer.&lt;/p&gt;&lt;p dir="ltr"&gt;In Study I, the findings demonstrate that predictive models, using machine learning, exhibit good discriminatory ability for patients who either never smoked or were current smokers. In Study II, an existing Swedish risk assessment tool was validated by replicating it in a different region, with consistent results across regions. In Study III, a new predictive model was developed using machine learning to analyse all diagnostic data for identifying non-metastatic colorectal cancer. Study IV introduces the extensive STEADY-CAN (Stockholm early detection of cancer study) cohort, providing opportunities to analyse early cancer detection patterns. Study V investigates the association between newly developed anaemia and cancer risk within the STEADY-CAN cohort, revealing a significant impact on risk assessment.&lt;/p&gt;&lt;p dir="ltr"&gt;These findings collectively address the value of improved risk stratification in primary care by leveraging existing data to better identify patients at elevated risk of having cancer. The results highlight key themes in early detection- predictive accuracy, risk stratification, clinical utility, and applicability across populations-and identify areas where current evidence has been limited or inconclusive. Future research should prioritise the validation of novel diagnostic approaches and the development of systems that support clinical decision- making, while upholding the principles of accessible, patient-centred care. Keywords: Early cancer detection, Primary care, Machine learning, Colorectal cancer, Lung cancer, Risk assessment tools, Anaemia, STEADY-CAN.&lt;/p&gt;&lt;h3&gt;List of scientific papers&lt;/h3&gt;&lt;p dir="ltr"&gt;I. &lt;b&gt;Nemlander E&lt;/b&gt;, Rosenblad A, Abedi E, Ekman S, Hasselström J, Eriksson LE, Carlsson AC. Lung cancer prediction using machine learning on data from a symptom e-questionnaire for never smokers, formers smokers and current smokers. PLoS One. 2022 Oct 21;17(10):e0276703. PMID: 36269746; PMCID: PMC9586380.&lt;/p&gt;&lt;p dir="ltr"&gt;Erratum for: PLoS One. 2022 Oct 21;17(10):e0276703. PMID: 38060550; PMCID: PMC10703334. &lt;a href="https://doi.org/10.1371/journal.pone.0276703"&gt;https://doi.org/10.1371/journal.pone.0276703&lt;/a&gt;&lt;/p&gt;&lt;p dir="ltr"&gt;II. &lt;b&gt;Nemlander E&lt;/b&gt;, Rosenblad A, Abedi E, Hasselström J, Sjövall A, Carlsson AC, Ewing M. Validation of a diagnostic prediction tool for colorectal cancer: a case-control replication study. Fam Pract. 2023 Jan 5:cmac147. PMID: 36611019. &lt;a href="https://doi.org/10.1093/fampra/cmac147"&gt;https://doi.org/10.1093/fampra/cmac147&lt;/a&gt;&lt;br&gt;&lt;br&gt;III. &lt;b&gt;Nemlander E&lt;/b&gt;, Ewing M, Abedi E, Hasselström J, Sjövall A, Carlsson AC, Rosenblad A. A machine learning tool for identifying non- metastatic colorectal cancer in primary care. European Journal of Cancer. 2023 Jan 11. &lt;a href="https://doi.org/10.1016/j.ejca.2023.01.011"&gt;https://doi.org/10.1016/j.ejca.2023.01.011&lt;/a&gt;&lt;br&gt;&lt;br&gt;IV. &lt;b&gt;Nemlander E&lt;/b&gt;, Abedi E, Ljungman P, Hasselström J, Carlsson AC, Rosenblad A. The Stockholm Early Detection of Cancer Study (STEADY-CAN): rationale, design, data collection, and baseline characteristics for 2.7 million participants. &lt;a href="https://doi.org/10.1007/s10654-024-01192-8" rel="noreferrer" target="_blank"&gt;https://doi.org/10.1007/s10654-024-01192-8&lt;/a&gt;&lt;/p&gt;&lt;p dir="ltr"&gt;&lt;br&gt;V. &lt;b&gt;Nemlander E&lt;/b&gt;, Rosenblad A, Abedi E, Hasselström J, Ljungman P, Carlsson AC. Newly developed anaemia predicts incident cancer and death within 18 months: Findings from 1.1 million patients in the Stockholm Early Detection of Cancer Study (STEADY-CAN) cohort. [Manuscript]&lt;/p&gt;

&lt;p dir="ltr"&gt;Early cancer detection is critical for improving survival rates, yet it requires a careful balance between minimising missed diagnoses and avoiding over- investigation. Primary care plays a central role in this process. This thesis aims to enhance understanding of the complexities involved in early cancer detection by analysing symptoms and signs, with the goal of contributing to the development of risk assessment and prediction tools to identify cancer at an early stage within primary care.&lt;/p&gt;&lt;p dir="ltr"&gt;This thesis is based on five quantitative studies conducted within the Swedish healthcare system. Study I examined symptoms reported by referred patients via questionnaires at the Department of Pulmonary Medicine at Karolinska University Hospital. It investigated whether machine learning could predict which patients subsequently received a lung cancer diagnosis, stratified by smoking status. Studies II and III focused on comprehensive diagnostic data and coded symptoms from primary care to facilitate early detection of non-metastatic colorectal cancer, with Study II conducted in Region Stockholm and Study III in Region Västra Götaland. Studies IV and V used comprehensive clinical and laboratory data from the entire adult population of Stockholm County. Study IV presents a cohort description, while Study V examines the association and discriminatory capacity of newly developed anaemia as an indicator for cancer.&lt;/p&gt;&lt;p dir="ltr"&gt;In Study I, the findings demonstrate that predictive models, using machine learning, exhibit good discriminatory ability for patients who either never smoked or were current smokers. In Study II, an existing Swedish risk assessment tool was validated by replicating it in a different region, with consistent results across regions. In Study III, a new predictive model was developed using machine learning to analyse all diagnostic data for identifying non-metastatic colorectal cancer. Study IV introduces the extensive STEADY-CAN (Stockholm early detection of cancer study) cohort, providing opportunities to analyse early cancer detection patterns. Study V investigates the association between newly developed anaemia and cancer risk within the STEADY-CAN cohort, revealing a significant impact on risk assessment.&lt;/p&gt;&lt;p dir="ltr"&gt;These findings collectively address the value of improved risk stratification in primary care by leveraging existing data to better identify patients at elevated risk of having cancer. The results highlight key themes in early detection- predictive accuracy, risk stratification, clinical utility, and applicability across populations-and identify areas where current evidence has been limited or inconclusive. Future research should prioritise the validation of novel diagnostic approaches and the development of systems that support clinical decision- making, while upholding the principles of accessible, patient-centred care. Keywords: Early cancer detection, Primary care, Machine learning, Colorectal cancer, Lung cancer, Risk assessment tools, Anaemia, STEADY-CAN.&lt;/p&gt;&lt;h3&gt;List of scientific papers&lt;/h3&gt;&lt;p dir="ltr"&gt;I. &lt;b&gt;Nemlander E&lt;/b&gt;, Rosenblad A, Abedi E, Ekman S, Hasselström J, Eriksson LE, Carlsson AC. Lung cancer prediction using machine learning on data from a symptom e-questionnaire for never smokers, formers smokers and current smokers. PLoS One. 2022 Oct 21;17(10):e0276703. PMID: 36269746; PMCID: PMC9586380.&lt;/p&gt;&lt;p dir="ltr"&gt;Erratum for: PLoS One. 2022 Oct 21;17(10):e0276703. PMID: 38060550; PMCID: PMC10703334. &lt;a href="https://doi.org/10.1371/journal.pone.0276703"&gt;https://doi.org/10.1371/journal.pone.0276703&lt;/a&gt;&lt;/p&gt;&lt;p dir="ltr"&gt;II. &lt;b&gt;Nemlander E&lt;/b&gt;, Rosenblad A, Abedi E, Hasselström J, Sjövall A, Carlsson AC, Ewing M. Validation of a diagnostic prediction tool for colorectal cancer: a case-control replication study. Fam Pract. 2023 Jan 5:cmac147. PMID: 36611019. &lt;a href="https://doi.org/10.1093/fampra/cmac147"&gt;https://doi.org/10.1093/fampra/cmac147&lt;/a&gt;&lt;br&gt;&lt;br&gt;III. &lt;b&gt;Nemlander E&lt;/b&gt;, Ewing M, Abedi E, Hasselström J, Sjövall A, Carlsson AC, Rosenblad A. A machine learning tool for identifying non- metastatic colorectal cancer in primary care. European Journal of Cancer. 2023 Jan 11. &lt;a href="https://doi.org/10.1016/j.ejca.2023.01.011"&gt;https://doi.org/10.1016/j.ejca.2023.01.011&lt;/a&gt;&lt;br&gt;&lt;br&gt;IV. &lt;b&gt;Nemlander E&lt;/b&gt;, Abedi E, Ljungman P, Hasselström J, Carlsson AC, Rosenblad A. The Stockholm Early Detection of Cancer Study (STEADY-CAN): rationale, design, data collection, and baseline characteristics for 2.7 million participants. &lt;a href="https://doi.org/10.1007/s10654-024-01192-8" rel="noreferrer" target="_blank"&gt;https://doi.org/10.1007/s10654-024-01192-8&lt;/a&gt;&lt;/p&gt;&lt;p dir="ltr"&gt;&lt;br&gt;V. &lt;b&gt;Nemlander E&lt;/b&gt;, Rosenblad A, Abedi E, Hasselström J, Ljungman P, Carlsson AC. Newly developed anaemia predicts incident cancer and death within 18 months: Findings from 1.1 million patients in the Stockholm Early Detection of Cancer Study (STEADY-CAN) cohort. [Manuscript]&lt;/p&gt;