Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “chemical and drug‐induced liver injury”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

2,987 records · Page 11Linked to original sources
PubMed2026

Unconfined compressive strength prediction for the ordinary Portland cement-steel slag-silica fume ternary system based on response surface methodology.

This research was undertaken to address environmental concerns associated with industrial solid waste and to reduce cement consumption in geotechnical engineering. It specifically investigates the feasibility of using steel slag (SS) and silica fume (SF) as partial substitutes for ordinary Portland cement (OPC) in soil stabilization. The effects of SS, SF, OPC, and initial moisture content on the unconfined compressive strength (UCS) of stabilized soil were investigated through single-factor experiments and response surface methodology (RSM). The results show that SS and SF can synergistically enhance the strength of stabilized soil, although their interaction effect was not statistically significant within the investigated ranges. Compared with soil stabilized solely with OPC, the addition of 18 % SS and 10 % SF reduced OPC consumption by 3 % without compromising strength. Microstructural and compositional analyses further revealed that SS mainly supplied calcium- and silica-bearing components, while SF provided highly reactive silica and micro-filling effects, jointly promoting hydration reactions and improving the compactness of the stabilized soil matrix. As a result, more hydration products were formed in the OPC/SS/SF-stabilized soil than in the OPC-stabilized soil, which contributed to pore filling and strength enhancement. This study provides useful guidance for the sustainable utilization of industrial solid waste and the low-carbon development of soil stabilization materials.

Construction Materials↗
PubMed2026

Hyperbaric oxygen for the treatment of traumatic incomplete spinal cord injury: a systematic review and meta-analysis of randomized controlled trials.

The therapeutic efficacy of hyperbaric oxygen therapy for traumatic incomplete spinal cord injury remains a subject of debate. To comprehensively evaluate the impact of hyperbaric oxygen on motor function, sensory function, and activities of daily living in patients with traumatic incomplete spinal cord injury, we conducted a systematic review and meta-analysis. We performed a comprehensive search across PubMed, Embase, the Cochrane Library, Web of Science, and major Chinese databases for randomized controlled trials published through June 2025. A total of 15 randomized controlled trials were included. The pooled results indicated that hyperbaric oxygen therapy significantly improved the American Spinal Injury Association motor score (mean difference = 10.30, 95% confidence interval: 7.70-12.90), the total American Spinal Injury Association sensory score (mean difference = 29.29, 95% confidence interval: 18.82-39.75), the American Spinal Injury Association light touch score (mean difference = 9.84, 95% confidence interval: 6.15-13.53), and the American Spinal Injury Association pinprick score (mean difference = 8.75, 95% confidence interval: 4.40-13.11). Furthermore, hyperbaric oxygen therapy was associated with significant enhancements in the Barthel Index (mean difference = 16.60, 95% confidence interval: 10.51-22.68) and the Functional Independence Measure (mean difference = 17.41, 95% confidence interval: 10.83-23.98). In conclusion, adjunctive hyperbaric oxygen therapy appears to improve motor function, sensory function, and activities of daily living in patients with traumatic incomplete spinal cord injury compared to conventional treatments alone. However, due to methodological limitations and potential publication bias in the included studies, these findings should be interpreted with caution, and further high-quality, multi-center randomized controlled trials are warranted.

Humans↗
PubMed2026

Analysis of deep learning techniques in computer-aided diagnosis for meniscus injuries: a systematic literature review.

Meniscus informatics is a growing subject of study in the healthcare industry. One of the major hindrances to the healthcare system's transformation is obtaining knowledge and meaningful information from complicated, high-dimensional and diverse sources. Modern biomedical research, for instance, has seen an increase in the use of complex, dissimilar, poorly documented, and generally unstructured electronic health records, imaging, sensor data and text, even after many current techniques have been used to extract more robust and useful elements from the data for analysis. New efficient standards for building end-to-end learning models from complex data are therefore needed. Therefore, the current study aims to examine the most recent research on the use of deep learning techniques for diagnosing meniscus tears and recommend creating comprehensive and meaningful interpretable structures that might benefit the healthcare industry. We also draw attention to shortcomings and the need for better technique development, and we provide new perspectives about this exciting new development in the field.

Humans↗
PubMed2026

Targeting Gasdermins for Therapeutic Interventions in Central Nervous System Injury.

Central nervous system (CNS) injuries are the leading cause of permanent disability and premature death in adults worldwide, with their incidence continuing to rise amid social development. These injuries not only severely impair the quality of life but also impose a heavy burden on the global public health system. Current clinical interventions, such as decompression and thrombolysis, can alleviate primary injury but fail to effectively reverse the secondary neuroinflammatory damage. Traditional anti-inflammatory therapies, which cannot block the upstream source of the inflammatory cascade, have led to repeated failures in global clinical translation research over the past decades. Gasdermins were first characterized in studies of systemic inflammatory diseases. These proteins form transmembrane pores to drive the release of proinflammatory factors and inflammatory cell death, serving as key mediators of host innate immunity. Recent studies have revealed that gasdermins play critical roles in regulating the initiation and amplification of neuroinflammation following CNS injury. To clarify the therapeutic potential of gasdermins as targets for injury repair, this review systematically summarizes the structure and function of gasdermins, as well as their cell-specific activation and regulatory mechanisms. We further elaborate on their pathological roles in these injuries and the corresponding therapeutic strategies, aiming to provide a theoretical reference for basic research and clinical translation in this field.

Humans↗
PubMed2026

Sex-stratified analyses of femoral intercondylar notch morphology and ACL injury risk: a systematic review and meta-analysis.

BACKGROUND: Anterior cruciate ligament (ACL) injury is more common in females. Although ACL injury risk is multifactorial, involving neuromuscular, hormonal, and biomechanical factors, femoral intercondylar notch morphology is a proposed non-modifiable anatomical contributor that may help explain this disparity. This review synthesizes evidence on its association with ACL injury risk, analyses stratified by male and female sex. METHODS: A literature search of PubMed, Web of Science, and Scopus was conducted through January 2026. After duplicate removal, 527 unique records were screened and 134 full texts assessed for eligibility. Twenty-four studies met inclusion criteria, with 22 providing quantitative data. Data were extracted on ACL-injured (ACLi) and control (ACLc) knees, stratified by sex. RESULTS: ACLi knees had narrower notch widths than ACLc knees in both females (MD -1.74 mm, 95% CI -2.54 to -0.95) and males (MD -1.31 mm, 95% CI -1.94 to -0.68), with substantial heterogeneity (I2 81-95%). NWI differences were significant in males (MD -0.01, 95% CI -0.02 to 0.00) but not females. Limited notch shape data suggested higher ACL injury odds with A-shaped notches in females (OR 2.85, 95% CI 0.07-110.66) and males (OR 1.67, 95% CI 0.00-3.98 × 105). CONCLUSION: Narrower femoral intercondylar notch width was consistently associated with ACL injury in both sexes, whereas findings for NWI and notch shape were limited by heterogeneity and sparse data. These results provide a structured synthesis of sex-specific anatomical risk factors and support femoral notch narrowing as a shared contributor, while highlighting the need for prospective, standardized studies in the future.

Humans↗
PubMed2026

Nerve injury in revision total elbow arthroplasty: a systematic review and meta-analysis.

BACKGROUND: Revision total elbow arthroplasty (TEA) is technically demanding and carries a substantial risk of postoperative neurological complications because of scarring, altered anatomy, implant removal, and repeated humeral and ulnar exposure. The incidence, nerve distribution, and recovery profile of nerve injury after revision TEA remain incompletely defined. This study aimed to systematically review the literature to define the incidence, recovery profile, and risk factors for nerve injury after revision TEA. METHODS: A systematic review of the literature was performed in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidance. Thirteen retrospective case series were included, comprising 282 revision TEAs in 271 patients. Random-effects meta-analysis of proportions was undertaken where the data permitted. The primary outcome was postoperative nerve injury following revision TEA. Secondary outcomes included nerve type, recovery, secondary nerve-related procedures, infection, triceps insufficiency, metallosis, periprosthetic fracture, and re-revision. RESULTS: The pooled incidence of postoperative nerve injury was 22.3% (95% confidence interval [CI] 16.3 to 29.6; I2 = 34.6%). The crude incidence was 60 of 282 revisions (21.3%, 95% CI 16.6 to 26.5). The ulnar nerve was involved in 66.7% of all nerve injuries, the radial nerve in 31.7%, and the median nerve in 1.7%. No significant difference in pooled nerve-injury incidence was identified between studies published before 2010 and those published from 2010 onwards (22.9% vs. 21.4%, P = .837). Recovery reporting was heterogeneous; among injuries with numerically extractable outcomes, 85.4% improved partially or completely (95% CI 72.2 to 93.9). Secondary nerve-related procedures were reported in 7 studies. Pooled complication estimates were 10.2% for infection, 13.6% for triceps insufficiency, 25.5% for metallosis, 15.9% for periprosthetic fracture, and 14.0% for re-revision. CONCLUSIONS: Postoperative nerve injury is a common and clinically important complication of revision TEA, affecting approximately 1 in 5 cases. The ulnar nerve is most frequently involved, although radial nerve injury accounts for a substantial proportion of cases. Many neuropathies improve during follow-up, but persistent deficits and the need for secondary nerve-related procedures are not uncommon. Future studies should adopt standardized neurological definitions and reporting to improve comparability and guide preventive surgical strategies.

Humans↗
PubMed2026

Intervention components, training dose, and adherence in exercise-based prevention of hamstring strain injury in football: a systematic review and meta-analysis.

OBJECTIVE: To quantify associations between exercise-based prevention programmes and hamstring strain injury (HSI) risk in football participants, and whether training dose and adherence modify effects. METHODS: Six databases were searched to 1 October 2025. Randomised and cluster-randomised trials comparing HSI prevention programmes with usual practice or warm-up in football participants were included. Random-effects meta-analysis pooled risk ratios (RRs); subgroup analyses and meta-regression assessed effect modification. RESULTS: Fifteen trials (n = 7,465) were analysed. Programmes reduced HSI risk (RR = 0.51, 95% CI 0.36-0.71), with I&#xb2;=57% and a prediction interval crossing the null (0.18-1.40). Based on a control event rate of 7.8%, absolute risk reduction was 3.8% (38 fewer HSIs per 1000 participants; 95% CI 23-50 fewer). Effects were stronger for shorter interventions (1-6 months; RR = 0.43) than longer interventions (7-10 months; RR = 0.77; P for interaction=0.04), and for elite/semi-professional players (RR = 0.38) than amateur players (RR = 0.77; P for interaction = 0.02). Training frequency and weekly volume did not modify effects, whereas adherence did. High adherence (&#x2265;75%) was associated with lower HSI risk (RR = 0.36, 95% CI 0.28-0.48), whereas low adherence (<75%) showed no clear benefit (RR = 0.92, 95% CI 0.68-1.23; P for interaction <0.00001). Each 10% increase in adherence corresponded to an RR multiplier of 0.83 (approximately 17% lower RR). Certainty of evidence was low. CONCLUSION: Exercise-based programmes reduce HSI risk in football when implementation supports sustained adherence. Effects may be stronger in shorter interventions and elite populations, but evidence remains insufficient to differentiate programme types or components.

Humans↗
PubMed2026

Predicting ACL injury risk in athletes: A systematic review of machine learning-based models.

BACKGROUND: Early ACL injury risk identification in athletes is essential. This systematic review examines machine learning (ML) models for predicting ACL injuries, evaluating their methodological quality, performance, and reliability. METHOD: A comprehensive electronic search was conducted across PubMed, Scopus, Web of Science, and IEEE Xplore databases, supplemented by Google Scholar for grey literature, covering articles published between January 1, 2015, and August 30, 2025. Eligible studies were appraised using the Prediction Model Study Risk of Bias Assessment Tool (PROBAST) for methodological quality and risk of bias, and the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) guidelines for quality of evidence. RESULTS: Ten studies were included. PROBAST showed eight studies had moderate risk of bias and two low risk. TRIPOD found only two studies met quality criteria. ML models included logistic regression (n&#xa0;=&#xa0;5), support vector machines (n&#xa0;=&#xa0;4), k-nearest neighbor (n&#xa0;=&#xa0;3), decision trees (n&#xa0;=&#xa0;3), random forests (n&#xa0;=&#xa0;5), neural networks (n&#xa0;=&#xa0;2), linear discriminant analysis (n&#xa0;=&#xa0;1), and pre-trained CNNs (n&#xa0;=&#xa0;1). AUC ranged from 0.63 to 0.98. Accuracy (reported in six studies) ranged from 26% to 95%; however, these values should be interpreted with caution due to the absence of confidence intervals, lack of class imbalance handling, and limited external validation across studies. Tree-based ensemble methods such as random forest achieved competitive accuracy (74-86%), while SVM, a non-ensemble classifier, reported accuracy ranging from 71% to 95%; however, the highest values were obtained in studies with notably small sample sizes (n&#xa0;=&#xa0;12 to n&#xa0;=&#xa0;39), raising concerns about overfitting and generalizability. CONCLUSION: Current ML algorithms show promise for identifying athletes at high ACL injury risk and detecting relevant risk factors. Although study quality was generally satisfactory, future research should prioritize external validation and model interpretability to support clinical translation.

Humans↗
PubMed2026

Effect of urinary catheter securement band on meatal pressure injury in male intensive care patients: A randomized controlled trial.

OBJECTIVES: To investigate the effectiveness of a urinary catheter securement band in preventing meatal pressure injury (meatal-PI) in male ICU patients, and to identify associated risk factors and the timing of injury development. METHODS: A total of 248 adult male ICU patients were randomly allocated to an intervention group (n&#xa0;=&#xa0;124) or a control group (n&#xa0;=&#xa0;124) between December 2024 and April 2025. The intervention group received a catheter securement band in addition to standard care, while the control group received standard care alone. Meatal-PI was evaluated daily using a structured monitoring form and a validated staging system. RESULTS: The incidence of meatal-PI was significantly lower in the intervention group (6.5%) compared with the control group (16.1%) (p&#xa0;=&#xa0;0.016). Multivariate analysis identified catheter securement, use of silicone catheters, higher Braden Scale scores, and shorter ICU length of stay as independent protective factors, while advanced age was associated with increased risk. Additional factors significantly associated with meatal-PI included comorbidities, higher device burden, latex catheter use, dry skin, lower Glasgow Coma Scale and Braden scores, sedation, and perineal oedema (p&#xa0;<&#xa0;0.001). CONCLUSIONS: The use of a catheter securement band significantly reduces the incidence of meatal-PI in male ICU patients. Incorporating catheter securement devices into routine nursing care, prioritising silicone catheter use, and performing regular meatal assessments may enhance patient safety by reducing the risk of device-related pressure injuries. Further research comparing different catheter securement methods across diverse patient populations is warranted. IMPLICATIONS FOR CLINICAL PRACTICE: The use of catheter securement bands may reduce the incidence of meatal-PI in male ICU patients. Incorporating standardized catheter stabilization strategies into routine intensive care nursing practice may enhance patient safety and support pressure injury prevention efforts.

Humans↗
PubMed2026

Urban stormwater infrastructure as a microplastic superhighway: a critical review of transport dynamics, modelling, and mitigation across pavements and drainage networks.

This review examines the transport, fate, modelling, and mitigation of Microplastics (MPs) in urban stormwater infrastructure, with emphasis on pavements, runoff pathways, micro-drainage, and macro-drainage systems. Following a systematic review approach, more than 1000 records were screened and approximately 50 core studies were retained when they addressed urban stormwater or drainage-related MP transport with adequate methodological reporting; marine-only studies and biological-effect studies without direct relevance to transport processes were excluded. The evidence shows that stormwater systems function not merely as passive conduits but as dynamic reactive transport systems with temporary storage, where particle mobilisation, sedimentation, resuspension, and temporary retention regulate MP export. Road surfaces, especially high-traffic areas, are major reservoirs of tyre wear, road-marking, atmospheric, and litter-derived particles that are rapidly mobilised during rainfall. Conventional grab sampling may underestimate MP loads, which in some cases exceed treated wastewater effluent loads by up to six-fold. Drainage structures such as manholes can immobilise up to 17.3% of near-neutrally buoyant particles, while biofouling and aggregation may shift buoyant polymers from wash-load to bedload. Mitigation systems, including permeable pavements, bioretention, wetlands, and technical inserts, can achieve high removal of coarse MPs, but performance declines for fine particles below 100&#xa0;&#xb5;m. The review highlights the need for standardised flow-proportional sampling, physically informed modelling, and treatment-train strategies targeting both surface sources and in-network storage.

Microplastics↗
PubMed2026

A profile of suspected female homicide cases at the Johannesburg and Diepkloof Forensic Pathology Service Medico-legal Mortuaries for 2020-2022.

This study profiles suspected female homicide victims in Johannesburg, South Africa, during the COVID-19 period marked by socio-environmental changes from lockdown restrictions. Guided by the Socio-Ecological Model, a retrospective case series of 369 victims was reviewed using medico-legal mortuary records from Johannesburg and Diepkloof Forensic Pathology Service facilities. Descriptive analyses were conducted, supplemented by a chi-square test to assess whether distributions of causes of death among women differed between COVID-19 and non-COVID-19 periods. No statistically significant association was found, &#x3c7;2 (6, N&#x2009;=&#x2009;339) = 6.68, p&#x2009;=&#x2009;0.35. Key findings highlight that Black, unemployed, unmarried women aged 21-40 were at greatest risk. Cause of death was established in 97.0% (358/369) of cases, with firearm injuries predominating (43.9%), followed by sharp&#x2011;force (24.5%) and blunt&#x2011;force trauma (13.1%). Approximately 90% of victims were suspected to have been killed by males, with half of deaths attributed to intimate partner violence. Homicide frequency decreased during strict lockdowns but rose as restrictions eased, suggesting that movement and alcohol controls may reduce risk. Despite temporary disturbance caused by COVID&#x2011;19 restrictions, the underlying risk profile of female homicide victims remained unchanged. These findings inform multi-level prevention and intervention strategies in South Africa.

Humans↗
PubMed2026

Patient-reported outcome measures within European cohorts of severely injured patients: a systematic review and meta-analysis.

PURPOSE: Severe injury affects multiple health-related domains, yet comprehensive European data on patient-reported outcomes remain limited. This systematic review and meta-analysis evaluates patient-reported outcome measures (PROMs) use and outcomes in severely injured European cohorts. METHODS: A systematic search of four databases up to October 14, 2025, identified European studies from 2000 onward reporting PROMs in severely injured patients. Severe injury was defined as an Injury Severity Score&#x2009;&#x2265;&#x2009;16, Glasgow Coma Scale&#x2009;&#x2264;&#x2009;8, intensive care unit admission, spinal cord injury, traumatic amputations, or pelvic fractures. Two reviewers independently screened records, with disagreements resolved by a third reviewer. Meta-analysis was performed when &#x2265;&#x2009;3 studies reported comparable PROMs at similar follow-up timepoints. RESULTS: Of 2,479 studies, 119 were included. Most cohorts originated from the Netherlands (26%), Norway (18%), and Germany (16%). General severely injured cohorts were most frequently studied (61%), followed by traumatic brain injury (17%), and spinal cord injury (15%). In total, 94 PROMs were used across 277 follow-up timepoints. Health-related quality of life was assessed most frequently (63%), after that anxiety/depression (14%), post-traumatic stress (9%), and social functioning (6%). At one year follow-up, the pooled EuroQol-5D-3&#xa0;L index score was 0.70 (95% CI 0.62-0.77) and VAS score was 68 (95% CI 60-75), indicating persistent impairment compared to population norms. CONCLUSION: Severely injured patients show persistent impairments with incomplete restoration of pre-injury functioning. Despite increased PROMs use, heterogeneity in selection and outcome reporting limits comparability, underscoring the need for standardised PROM assessment to improve outcome evaluation after severe injury.

Humans↗
PubMed2026

Pre-transport dietary chitosan improves the physiological robustness of juvenile largemouth bass (Micropterus salmoides) by modulating antioxidant and inflammatory responses.

The acute stress caused by long-distance transport can lead to oxidative damage, immune dysfunction, and health deterioration in fish. This study evaluated dietary chitosan as a pre-transport nutritional strategy for juvenile largemouth bass (Micropterus salmoides). Five experimental diets contained chitosan at 0, 2.5, 5.0, 7.5, or 10.0&#x202f;g/kg, designated as p0, p25, p50, p75, and p100, respectively, for 56&#x202f;d. The effects of dietary chitosan were evaluated using growth performance, feed utilization, digestive function, antioxidant capacity, nonspecific immunity, and resistance to Aeromonas hydrophila infection. Then, fish from the p0 and p50 groups underwent a 12-h transport stress test, with samples collected before, during, and 7&#x202f;d after transport. Dietary chitosan improved most of these parameters. Among the treatment groups, p50 and p75 showed the best overall performance. The dose-response analysis further indicated that the appropriate dietary inclusion range was 5.0-7.5&#x202f;g/kg. Under transport stress, fish in the p50 group exhibited more stable antioxidant enzyme responses and lower lipid peroxidation, as indicated by reduced MDA levels. Consistent with these enzyme responses, antioxidant-related genes remained relatively stable. At the same time, expression patterns related to the Nrf2-Keap1 and NF-&#x3ba;B signaling pathways suggested that 5.0&#x202f;g/kg chitosan alleviated transport-induced oxidative damage and inflammation. Dietary chitosan also attenuated pro-inflammatory gene induction and altered the temporal expression patterns of anti-inflammatory genes. Overall, 5.0-7.5&#x202f;g/kg dietary chitosan is suitable for juvenile largemouth bass, and 5.0&#x202f;g/kg may serve as an effective pre-transport dietary inclusion level.

Animals↗
PubMed2026

An Assessment of Reliability Estimation Methods for Binomial Health Care Quality Measures.

We evaluated the performance of commonly used methods for estimating the reliability of binomial health care quality measures using simulated datasets spanning a range of performance score means and variances, numbers of entities, and patient sample sizes. For each simulation, reliability was estimated for all selected methods and compared with the known true reliability derived from the simulation parameters, with methods assessed on their accuracy and precision. Logistic regression with reliability estimated on the outcome scale demonstrated the highest accuracy and precision among all methods evaluated. The widely used Adams beta-binomial method performed poorly, although a modification recommended by Nieser and Harris substantially improved its performance. These approaches are applicable only to binomial measures. Among methods that can be applied to both binomial and continuous measures, permutation resampling of the Spearman rank correlation coefficient was the most accurate and precise, outperforming other commonly used approaches. Overall, for binomial quality measures, logistic regression on the outcome scale is the preferred method for reliability estimation, followed closely by the modified beta-binomial approach, while for non-binomial measures, permutation-based Spearman rank correlation appears to be the most suitable method.

Reproducibility of Results↗
PubMed2026

The global potential of freshwater microbes for plastic degradation.

Plastic pollution is becoming increasingly severe on a global scale, and the potential for biodegradation as a treatment method that is environmentally friendly merits greater attention. A significant number of genes that associated the degradation of plastic (PDAGs) have been identified, however, the distribution of these genes among microorganisms in global inland waters remains to be elucidated. A global-scale meta-analysis was conducted, incorporating approximately 1000 metagenome datasets of inland waters across seven continents. A total of 13,109 metagenome-assembled genomes (MAGs) were obtained by means of metagenomics binning, and 22,621 PDAGs were identified from these. Among these recognized PDAGs, phenylacetaldehyde dehydrogenase (PAD) was the most dominant (n = 16,664), followed by catalase (n = 5931). The predominant hosts for PAD and catalase were identified as Gamma-proteobacteria and Bacteroidia, respectively. The largest number of both PAD and catalase was found in MAGs from North America, while the average gene number in single MAG was highest in MAGs from Oceania. In accordance with the prediction of traits, PDAG-carrying MAGs from Europe demonstrated the fastest growth rate and the lowest optimal growth rate. Furthermore, 25 styrene monooxygenase (StyA) enzymes were identified, which were found to cluster into two distinct groups hosted by Alpha-proteobacteria and Gamma-proteobacteria, respectively. Moreover, 11 MAGs were observed to possess the complete pathway of polystyrene degradation. These results explored the potential of inland water microorganisms as a biological resource for plastic degradation and provided valuable microbial reference information that can be used to develop biological treatment technologies for mitigating plastics.

Plastics↗
PubMed2026

The role of artificial intelligence in the diagnosis and prognosis of traumatic brain injury based on brain CT scans: a systematic review.

Traumatic brain injury (TBI) is a leading cause of emergency department visits and a major contributor to injury-related mortality and long-term neurological disability. Non-contrast computed tomography (CT) is the gold-standard imaging modality for the rapid diagnosis of TBI. Clinical outcomes depend strongly on early detection and prompt acute management. Artificial intelligence (AI)-based models may support faster automated identification of traumatic findings and early prediction of patient prognosis.&#xa0;A systematic literature search was conducted in PubMed/MEDLINE, Scopus, IEEE Xplore, ACM Digital Library, and the Cochrane Library in accordance with PRISMA 2020 guidelines to evaluate AI-based models for automated detection of TBI-related findings on CT and for prediction of clinical outcomes. Risk of bias and applicability were assessed using QUADAS-2 for diagnostic accuracy studies and PROBAST&#x2009;+&#x2009;AI for prediction model studies.&#xa0;Twenty-two studies were included. Sixteen studies evaluated diagnostic tasks and 10 evaluated prognostic outcomes, with four studies contributing to both categories. Diagnostic performance was generally high, with many studies reporting AUC values approaching or exceeding 0.90, particularly for larger lesion volumes.Prognostic performance was more variable, with moderate to high discrimination and substantial heterogeneity. Only 9 studies incorporated independent external validation, and performance was frequently lower in external cohorts. All prognostic model studies were judged to be at high overall risk of bias using PROBAST&#x2009;+&#x2009;AI, and most diagnostic accuracy studies also demonstrated high or unclear risk of bias in at least one QUADAS-2 domain, most frequently in patient selection.&#xa0;AI-based models applied to brain CT demonstrate strong technical performance for both diagnostic and prognostic tasks in TBI. However, most studies relied on retrospective designs and lacked independent external validation which limits models generalizability and raises concern for potential overfitting. Prospective, multicenter studies with standardized methodologies and rigorous external validation are required before widespread clinical implementation.

Humans↗