Using artificial intelligence to predict mortality in AKI patients: a systematic review/meta-analysis.

Background: Acute kidney injury (AKI) is associated with increased morbidity/mortality. With artificial intelligence (AI), more dynamic models for mortality prediction in AKI patients have been developed using machine learning (ML) algorithms. The performance of various ML models was reviewed in terms of their ability to predict in-hospital mortality for AKI patients. Methods: A literature search was conducted through PubMed, Embase and Web of Science databases. Included studies contained variables regarding the efficacy of the AI model [the AUC, accuracy, sensitivity, specificity, negative predictive value and positive predictive value]. Only original studies that consisted of cross-sectional studies, prospective and retrospective studies were included, while reviews and self-reported outcomes were excluded. There was no restriction on time and geographic location. Results: Eight studies with 37 032 AKI patients were included, with a mean age of 65.3 years. The in-hospital mortality was 18.0% in the derivation and 15.8% in the validation cohorts. The pooled [95% confidence interval (CI)] AUC was observed to be highest for the broad learning system (BLS) model [0.852 (0.820-0.883)] and elastic net final (ENF) model [0.852 (0.813-0.891)], and lowest for proposed clinical model (PCM) [0.765 (0.716-0.814)]. The pooled (95% CI) AUC of BLS and ENF did not differ significantly from other models except PCM [Delong's test P = .022]. PCM exhibited the highest negative predictive value, which supports this model's use as a possible rule-out tool. Conclusion: Our results show that BLS and ENF models are equally effective as other ML models in predicting in-hospital mortality, with variability across all models. Additional studies are needed.

Advancements in diabetic kidney disease management: integrating innovative therapies and targeted drug development.

Diabetic kidney disease (DKD) is a leading cause of chronic kidney disease and affects approximately 40% of individuals with diabetes . Cases of DKD continue to rise globally as the prevalence of diabetes mellitus increases, with an estimated 415 million people living with diabetes in 2015 and a projected 642 million by 2040. DKD is associated with significant morbidity and mortality, representing 34% and 36% of all chronic kidney disease deaths in men and women, respectively. Common comorbidities including hypertension and ageing-related nephron loss further complicate disease diagnosis and progression. The progression of DKD involves several mechanisms including glomerular endothelial cell dysfunction, inflammation, and fibrosis. Targeting these mechanisms has formed the basis of several therapeutic agents. Renin-angiotensin-aldosterone system (RAAS) blockers, specifically angiotensin receptor blockers (ARBs), demonstrate significant reductions in macroalbuminuria. Sodium-glucose transporter type 2 (SGLT-2) inhibitors demonstrate kidney protection independent of diabetes control while also decreasing the incidence of cardiovascular events. Emerging agents including glucagon-like peptide 1 (GLP-1) agonists, anti-inflammatory agents like bardoxolone, and mineralocorticoid receptor antagonists show promise in mitigating DKD progression. Many novel therapies including monoclonal antibodies CSL346, lixudebart, and tozorakimab; mesenchymal stem/stromal cell infusion; and cannabinoid-1 receptor inverse agonism via INV-202 are currently in clinical trials and present opportunities for further drug development.

Artificial intelligence in early detection and prediction of pediatric/neonatal acute kidney injury: current status and future directions.

Acute kidney injury (AKI) has a significant impact on the short-term and long-term clinical outcomes of pediatric and neonatal patients, and it is imperative in these populations to mitigate the pathways leading to AKI and be prepared for early diagnosis and treatment intervention of established AKI. Recently, artificial intelligence (AI) has provided more advent predictive models for early detection/prediction of AKI utilizing machine learning (ML). By providing strong detail and evidence from risk scores and electronic alerts, this review outlines a comprehensive and holistic insight into the current state of AI in AKI in pediatric/neonatal patients. In the pediatric population, AI models including XGBoost, logistic regression, support vector machines, decision trees, naïve Bayes, and risk stratification scores (Renal Angina Index (RAI), Nephrotoxic Injury Negated by Just-in-time Action (NINJA)) have shown success in predicting AKI using variables like serum creatinine, urine output, and electronic health record (EHR) alerts. Similarly, in the neonatal population, using the "Baby NINJA" model showed a decrease in nephrotoxic medication exposure by 42%, the rate of AKI by 78%, and the number of days with AKI by 68%. Furthermore, the "STARZ" risk stratification AI model showed a predictive ability of AKI within 7 days of NICU admission of AUC 0.93 and AUC of 0.96 in the validation and derivation cohorts, respectively. Many studies have reported the superiority of using biomarkers to predict AKI in pediatric patients and neonates as well. Future directions include the application of AI along with biomarkers (NGAL, CysC, OPN, IL-18, B2M, etc.) in a Labelbox configuration to create a more robust and accurate model for predicting and detecting pediatric/neonatal AKI.

Archetypal sustained low-efficiency daily diafiltration (SLEDD-f) for critically ill patients requiring kidney replacement therapy: towards an adequate therapy.

Sustained low-efficiency dialysis is a hybrid form of kidney replacement therapy that has gained increasing popularity as an alternative to continuous forms of kidney replacement therapy in intensive care unit settings. During the COVID-19 pandemic, the shortage of continuous kidney replacement therapy equipment led to increasing usage of sustained low-efficiency dialysis as an alternative treatment for acute kidney injury. Sustained low-efficiency dialysis is an efficient method for treating hemodynamically unstable patients and is quite widely available, making it especially useful in resource-limited settings. In this review, we aim to discuss the various attributes of sustained low-efficiency dialysis and how it is comparable to continuous kidney replacement therapy in efficacy, in terms of solute kinetics and urea clearance, and the various formulae used to compare intermittent and continuous forms of kidney replacement therapy, along with hemodynamic stability. During the COVID-19 pandemic, there was increased clotting of continuous kidney replacement therapy circuits, which led to increased use of sustained low-efficiency dialysis alone or together with extra corporeal membrane oxygenation circuits. Although sustained low-efficiency dialysis can be delivered with continuous kidney replacement therapy machines, most centers use standard hemodialysis machines or batch dialysis systems. Even though antibiotic dosing differs between continuous kidney replacement therapy and sustained low-efficiency dialysis, reports of patient survival and renal recovery are similar for continuous kidney replacement therapy and sustained low-efficiency dialysis. Health care studies indicate that sustained low-efficiency dialysis has emerged as a cost-effective alternative to continuous kidney replacement therapy. Although there is considerable data to support sustained low-efficiency dialysis treatments for critically ill adult patients with acute kidney injury, there are fewer pediatric data, even so, currently available studies support the use of sustained low-efficiency dialysis for pediatric patients, particularly in resource-limited settings.

The effects of COVID-19 on pediatric and adult solid organ transplant recipients and the emergence of telehealth.

BACKGROUND: The SARS-CoV-2 pandemic and corresponding acute respiratory syndrome have affected all populations and led to millions of deaths worldwide. The pandemic disproportionately affected immunocompromised and immunosuppressed adult patients who had received solid organ transplants (SOTs). With the onset of the pandemic, transplant societies across the world recommended reducing SOT activities to avoid exposing immunosuppressed recipients. Due to the risk of COVID-19-related outcomes, SOT providers adapted the way they deliver care to their patients, leading to a reliance on telehealth. Telehealth has helped organ transplant programs continue treatment regimens while protecting patients and physicians from COVID-19 transmission. This review highlights the adverse effects of COVID-19 on transplant activities and summarizes the increased role of telehealth in the management of solid organ transplant recipients (SOTRs) in both pediatric and adult populations. METHODS: A comprehensive systematic review and meta-analysis were conducted to accentuate the outcomes of COVID-19 and analyze the efficacy of telehealth on transplant activities. This in-depth examination summarizes extensive data on the clinical detriments of COVID-19 in transplant recipients, advantages, disadvantages, patient/physician perspectives, and effectiveness in transplant treatment plans via telehealth. RESULTS: COVID-19 has caused an increase in mortality, morbidity, hospitalization, and ICU admission in SOTRs. Telehealth efficacy and benefits to both patients and physicians have increasingly been reported. CONCLUSIONS: Developing effective systems of telehealth delivery has become a top priority for healthcare providers during the COVID-19 pandemic. Further research is necessary to validate the effectiveness of telehealth in other settings.

Cardiovascular implications of hypertensive autosomal dominant polycystic kidney disease: a systematic review and meta-analysis.

BACKGROUND: Autosomal dominant polycystic kidney disease (ADPKD) is among the most common inherited kidney diseases. Hypertension is a frequent cardiovascular manifestation, especially in adults, but elevated blood pressure is also found in children and adolescents. Acknowledgment of pediatric hypertension early is critical, as it can result in serious complications long-term if left undiagnosed. OBJECTIVE: We aim to identify the influence of hypertension on cardiovascular outcomes, mainly left ventricular hypertrophy, carotid intima media thickness, and pulse wave velocity. METHODS: We performed an extensive search on Medline, Embase, CINAHL, and Web of Science databases through March 2021. Original studies with a mix of retrospective, prospective, case-control studies, cross sectional studies, and observational studies were included in the review. There was no restriction on age group. RESULTS: The preliminary search yielded 545 articles with 15 articles included after inclusion and exclusion criteria. In this meta-analysis, LVMI (SMD: 3.47 (95% CI: 0.53-6.41)) and PWV (SMD: 1.72 (95% CI: 0.08-3.36)) were found to be significantly higher in adults with ADPKD compared to non-ADPKD; however, CIMT was not found to be significantly different. Also, LVMI was observed to be significantly higher among hypertensive adults with ADPKD (n = 56) as compared to adults without ADPKD (SMD: 1.43 (95% CI: 1.08-1.79)). Fewer pediatric studies were available with heterogeneity among patient populations and results. CONCLUSIONS: Adult patients with ADPKD were found to have worse indicators of cardiovascular outcomes, including LVMI and PWV, as compared to non-ADPKD. This study demonstrates the importance of identifying and managing hypertension, especially early, in this population. Further research, particularly in younger patients, is necessary to further elucidate the relationship between hypertension in patients with ADPKD and cardiovascular disease. REGISTRATION NUMBER: PROSPERO REGISTRATION: 343,013.

Surface-based brain morphometry in schizophrenia vs. cannabis-induced psychosis: A controlled comparison.

BACKGROUND & AIM: We examined group differences in cortical thickness and surface-parameters among age and handedness--matched persons with cannabis-induced psychosis (CIP), schizophrenia with heavy cannabis use (SZC), and healthy controls (HC). METHODS: We recruited 31 men with SZC, 28 with CIP, and 30 with HC. We used the Psychiatric Research Interview for Substance and Mental Disorders to differentiate between CIP and SZC. We processed and analyzed T1 MR images using the Surface-based Brain Morphometry (SBM) pipeline of the CAT-12 toolbox within the statistical parametric mapping. After pre-processing, volumes were segmented using surface and thickness estimation for the analysis of the region of interest. We used the projection-based thickness method to assess the cortical thickness and Desikan-Killiany atlas for cortical parcellation. RESULTS: We observed the lowest cortical thickness, depth, and gyrification in the SZC, followed by CIP and the control groups. The differences were predominantly seen in frontal cortices, with limited parietal and temporal regions involvement. After False Discovery Rate (FDR) corrections and post-hoc analysis, SZC had reduced cortical thickness than HC in the middle and inferior frontal, right entorhinal, and left postcentral regions. Cortical thickness of SZC was also significantly lower than CIP in bilateral postcentral and right middle frontal regions. We found negative correlations (after FDR corrections) between the duration of cannabis use and cortical thickness in loci of parietal and occipital cortices. CONCLUSION: Our study suggested cortical structural abnormalities in schizophrenia, in reference to healthy controls and cannabis-induced psychosis, indicating different pathophysiology of SZC and CIP.

Anti-factor H antibody and its role in atypical hemolytic uremic syndrome.

Atypical hemolytic uremic syndrome (aHUS) an important form of a thrombotic microangiopathy (TMA) that can frequently lead to acute kidney injury (AKI). An important subset of aHUS is the anti-factor H associated aHUS. This variant of aHUS can occur due to deletion of the complement factor H genes, CFHR1 and CFHR3, along with the presence of anti-factor H antibodies. However, it is a point of interest to note that not all patients with anti-factor H associated aHUS have a CFHR1/R3 deletion. Factor-H has a vital role in the regulation of the complement system, specifically the alternate pathway. Therefore, dysregulation of the complement system can lead to inflammatory or autoimmune diseases. Patients with this disease respond well to treatment with plasma exchange therapy along with Eculizumab and immunosuppressant therapy. Anti-factor H antibody associated aHUS has a certain genetic predilection therefore there is focus on further advancements in the diagnosis and management of this disease. In this article we discuss the baseline characteristics of patients with anti-factor H associated aHUS, their triggers, various treatment modalities and future perspectives.

White Matter Microstructure and Gray Matter Volume in Cannabis-Induced Psychosis and Schizophrenia With Cannabis Use.

OBJECTIVE: This study explored the differences in white matter (WM) microstructural integrity and gray matter (GM) volume between cannabis-induced psychosis (CIP) and schizophrenia with cannabis use (SZC). METHODS: This cross-sectional study with convenience sampling involved three groups of 20 participants each (CIP, SZC, and a control group without substance use), matched on age, handedness, and education. CIP and SZC were diagnosed with the Psychiatric Research Interview for Substance and Mental Disorders. Diffusion tensor and kurtosis imaging were done, and fractional anisotropy (FA), mean diffusivity, and mean kurtosis were estimated. GM volume was measured with voxel-based morphometry. RESULTS: Group comparisons revealed comparable age at initiation and duration and frequency of cannabis use between participants in the SZC and CIP groups. Participants with SZC had lower FA than controls in the anterior and retrolenticular internal capsule limbs, cingulate gyrus hippocampal formation, fornix, and superior fronto-occipital fasciculus (all p<0.05). Participants with CIP had lower FA than controls in the left fornix and right superior fronto-occipital fasciculus but higher FA than those with SZC in the left corticospinal tract (all p<0.05). On morphometry, participants with CIP had greater cerebellar GM volume than those with SZC and greater inferior frontal gyrus volumes than controls (all p<0.05). CONCLUSIONS: Widespread WM microstructural abnormalities were observed in participants with SZC, and fewer but significant WM disruptions were observed in those with CIP. Better WM integrity in some WM fiber tracts and greater GM volumes in crucial brain areas among those with CIP may have prevented the transition to schizophrenia.

Role of age at onset in the clinical presentation of bipolar disorder in Indian population.

OBJECTIVE: The objective of this study was to determine any association of age at onset (AAO) with clinical presentation of bipolar disorder (BD) and family history of illness. MATERIALS AND METHODS: A hospital-based cross-sectional observational study was conducted including 162 patients having a diagnosis of BD current episode manic. Individuals were divided into three subgroups according to AAO, i.e., early-onset BD (EOBD) (AAO ≤21 years), intermediate-onset BD (AAO - 22-34 years), and late-onset BD (AAO ≥35 years). The subgroups were compared on clinical variables; items of the Young Mania Rating Scale (YMRS), Hamilton Depression Rating Scale (HAM-D), and Scale for the Assessment of Positive Symptoms (SAPS); and family history of illness. RESULTS: The early-onset group had significantly more episodes per year than the other groups (P < 0.001). The prevalence of family history of mood disorder was also significantly higher in the early-onset group than the other subgroups. AAO was found to be significantly associated with different items of YMRS, HAM-D, and SAPS. The early-onset group had higher rating on irritability, motor activity-energy, sexual interest, depressed mood, delusions, and thought disorders, whereas the late-onset group had higher rating on elevated mood. CONCLUSION: EOBD can be considered as a specific phenotype of BD, which is more homogenous, severe, and inheritable form of illness.

Do neurocognitive functions in cannabis induced psychosis groups differ from schizophrenia with cannabis use? A controlled cross-sectional study.

OBJECTIVE: Cannabis-induced psychosis (CIP) has received little research attention. We compared neurocognitive functions in CIP, Schizophrenia with cannabis use (SZC) and healthy control group (CG). METHODS: Twenty age, education, and handedness-matched participants were recruited in each of the three groups. CIP and SZC were diagnosed with Psychiatric research interviews for substance use and mental disorders. Level of cannabis exposure, global intelligence, executive function, attention, vigilance, working, and verbal memory, and motor speed were compared by analysis of variance with post-hoc Scheffe's test. We did a post-hoc power calculation. RESULTS: Age at initiation, frequency, duration, and preparation of cannabis use did not differ significantly between CIP and SZC. CIP performed significantly better (than SZC) in tests of general cognitive ability or intelligence and attention, perceptual tracking and sequencing. SZC showed significant dysfunctions (than CG) in all parameters of the tests for executive dysfunction, sustained attention, short-term verbal memory and psychomotor functioning. CIP and CG did not differ in any cognitive domains except for non-perseverative errors in the test for executive functioning. CONCLUSIONS: CIP and SZC had different degrees of impairment compared to controls, but on direct comparisons CIP had better general intelligence and attention.KEY POINTSCannabis-induced psychosis (CIP) may have different neurocognitive impairment than Schizophrenia with cannabis use (SZC)CIP performed better in tests for general intelligence and visual attention than SZCSZC had significant impairment in executive function, attention, verbal memory, and psychomotor speed than controlsCompared to controls, CIP performed significantly worse in some domains of executive functionCIP and SZC had different degrees of cognitive impairments as compared to the controls.

Psychosocial interventions in patients with dual diagnosis.

Management of patients with dual diagnosis (Mental illness and substance use disorders) is a challenge. A lack of improvement in either disorder can lead to a relapse in both. The current consensus opinion favours an integrated approach to management of both the disorders wherein the same team of professionals manages both the disorders in the same setting. The role of pharmacotherapy for such dual diagnosis patients is well established but the non-pharmacological approaches for their management are still evolving. After stabilization of the acute phase of illnesses, non-pharmacological management takes centre stage. Evidence points to the beneficial effect of psychosocial approaches in maintaining abstinence, adherence to medication, maintenance of a healthy life style, better integration in to community, occupational rehabilitation and an overall improvement in functioning. Psychosocial approaches although beneficial, are difficult to implement. They require teamwork, involving professionals other than psychiatrists and psychologists alone. These approaches need to be comprehensive, individualized and require training to various levels that is difficult to achieve in most Indian settings. In this article we provide a brief review of these approaches.

Revisiting profile of deliberate self-harm at a tertiary care hospital after an interval of 10 years.

CONTEXT: Sociocultural factors complement psychopathological factors that result in deliberate self-harm (DSH). A study of change in these factors over time is essential for preventive action. AIMS: To identify factors influencing DSH, which have shown significant variation over a period of 10 years. SETTINGS AND DESIGN: Two hospital-based cross-sectional analytic types of observational studies were performed at two different times at an interval of 10 years. MATERIALS AND METHODS: Sociodemographic profile, factors related to DSH, stressful life events, and psychiatric disorders were assessed in two groups of patients drawn from the same tertiary care hospital, 100 consecutive patients in 2002 and 117 in 2012. The observations were compared to identify factors that have undergone significant change. STATISTICAL ANALYSIS: Descriptive statistics along with Chi-square test was used in this study. RESULTS: A significant decrease in the overall number of married subjects (60% vs. 43%) and an increase in the number of unmarried females (34% vs. 61%) were seen. A significant increase in the overall number of rural subjects (17% vs. 34%) and especially in a number of rural females (7% vs. 23%) was also seen. An increase in subjects from middle socioeconomic class (15% vs. 29%) and education up to secondary school (9% vs. 25%) was also seen. A significantly higher number of subjects had a psychiatric disorder (50% vs. 81%) with a significant increase in diagnoses of depression (36% vs. 67%). Family and social issues remain the most common antecedent stressful events. Chemical methods are still the most preferred means, but a higher number (8% vs. 18%) report a history of self-harm. CONCLUSION: Variations in factors responsible for DSH identified in this comparative study have preventive implications.