Artificial intelligence (AI) offers new methods to improve diagnosis and treatment in mental health. However, its use raises legal and ethical concerns.

AI is increasingly being used for mental health care, but its clinical prominence and ethical implications are yet to be determined. This systematic review discusses the clinical efficacy and the ethical issues of AI in mental health treatment and is trying to focus on the main conclusions with regard to the diagnostic accuracy and the therapeutic efficacy.

The review encompasses an exhaustive analysis of 35 studies in the narrow time frame of 2013-2024. It allows for multidatabase exploration and follows the systematic and well-established practice of PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines. This review searched PubMed (biomedical emphasis), IEEE Xplore (engineering or AI), PsycINFO (psychological literature), Scopus (multidisciplinary focus), and Cochrane Library (evidence-based treatment) from January 1, 2013, to December 31, 2024. Studies include those that focused on AI applications for diagnosis, treatment, or patient engagement, excluding tangential uses (eg, administrative tasks). Only English-language publications were searched to mitigate language bias, though this introduces potential geographic bias.

AI-enabled interventions of natural language processing models showed up to 89% accuracy for depression detection. The wearables, as in the Empatica E4, showed an F1-score of 0.81 to predict anxiety episodes. AI-enabled therapies, such as chat-based interventions and online cognitive behavioral therapy, have been shown to improve the anxiety symptoms of about 30% in some studies; however, there was considerable variability in the impact based on study design, intervention duration, and comparator conditions, as well as the overall methodological quality of the studies. However, challenges remain, such as including biases in training data, evidenced by performance declines of up to 15% in non-English datasets, and concerns over data privacy.

In addressing mental health, AI has the potential to revolutionize mental health treatment, offering cost-saving, personalized, and culturally sensitive interventions while protecting privacy, equity, and human agency.

Family caregivers commonly report high levels of burden, which is associated with risk for depression and anxiety. However, less is understood about how symptoms respond to changes in caregiver burden. This clinical-trial study assessed the influence of caregiver burden on anxiety and depression among informal caregivers on persons with Alzheimer's disease and related dementias.

U.S. caregivers (N = 139) self-reported caregiver burden, depression, and anxiety symptoms, up to 6 times over a twenty-week period. Multilevel models assessed concurrent and longitudinal effects of changes in caregiver burden on changes in depression and anxiety symptoms.

Caregivers who experienced increases in burden during a given month also reported increases in depression (b = 0.25, CI [0.19, 0.30]) and anxiety symptoms (b = 0.22, CI [0.16, 0.29]) that month, and had sustained increases in depression and anxiety symptoms one-month later (b=0.12, CI [0.07, 0.18]; b = 0.15, CI [0.08, 0.22]).

While worsening depression and anxiety symptoms that followed an increase in burden were modest in the context of a single month, reporting higher than typical burden for two or more months was related to clinically relevant shifts in the risk for depression and anxiety. Results indicate that interventions designed to reduce burden would likely benefit caregivers' mental health.

Background/Objectives: Patients with breast cancer show substantial heterogeneity in terms of psychological adjustment following diagnosis. We aimed to characterize longitudinal trajectories of quality of life (QoL) and depressive symptoms during the first 18 months post-diagnosis and to identify robust clinical, psychosocial, and behavioral predictors associated with distinct adjustment pathways. Methods: Women (N = 538; mean age 55.4 years; range 40-70) with operable breast cancer (stages I-III) were drawn from the multicenter BOUNCE cohort. QoL (Global Health Status/QoL scale of the European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire Core 30) and depressive symptoms (depression subscale of the Hospital Anxiety and Depression Scale) were assessed at baseline and months 3, 6, 9, 12, 15 and 18. Latent class growth analysis and growth mixture modeling identified distinct trajectory classes. Associations between early predictors and trajectory membership were examined using logistic regression combined with elastic net regularization. Results: Depression trajectories demonstrated heterogeneity, with groups characterized by persistent resilience (59.7%), stable moderate/high (25.3%), delayed onset (5.0%), and recovery (10.0%). QoL trajectories ranged from stable excellent (13.2%) and stable high (40.7%) to moderate (31.4%) and persistent low/deteriorating (6.9%), as well as a distinct recovering trajectory (7.8%). Trajectory differentiation was primarily driven by psychological resources, symptom burden, functional status, and coping processes, alongside specific contributions from clinical factors. Conclusions: Distinct subgroups of women with breast cancer follow divergent adjustment pathways. These findings highlight the multidimensional nature of resilience and support the need for tailored interventions that promote long-term well-being beyond simple risk reduction.

Cognitive impairment is common in multiple sclerosis (MS), yet the application of diagnostic frameworks of Neurocognitive Disorders (NCDs) is limited. Additionally, the integration of multimodal data for predicting cognitive outcomes using artificial intelligence (AI) remains underexplored. This study aimed to characterize NCDs in MS and predict cognitive worsening using an explainable deep learning model trained on MRI and clinical data.

Two-hundred twenty-four MS patients and 115 healthy controls (HC) underwent 3.0 T MRI and clinical assessment at baseline. MS patients also completed neuropsychological testing, including estimation of z-cognitive reserve, at baseline and after a median follow-up of 3.4 (interquartile range = [2.0; 6.1]) years. MS patients were classified as Mild or Major NCD according to the Diagnostic and Statistical Manual of Mental Disorders criteria at baseline, and as "stable" or "worsened" based on cognitive changes at follow-up. A deep learning model was trained on baseline T1-weighted MRI, demographic, clinical, and brain volumetric data to predict cognitive decline, with explainability methods used to interpret the model's decisions.

At baseline, 4% of patients had Mild and 11% Major NCD. At follow-up, 12% showed cognitive decline. The deep learning model predicted follow-up cognitive status with 90% accuracy. Explainability models identified the most relevant predictors, in order of importance: cortical gray matter volume, age, thalamic and hippocampal volumes, T2 lesion volume, and z-cognitive reserve.

The proposed multimodal AI approach demonstrated robust performance and highlighted relevant brain regions associated with cognitive worsening, underscoring its potential for personalized cognitive assessment and monitoring in MS.

Perinatal depression is a significant public health concern that affects women during pregnancy and the postpartum period. Despite being acknowledged globally, the burden of perinatal depression is particularly profound in low and middle-income countries, such as Ethiopia. This umbrella review is therefore intended to systematically consolidate findings on perinatal depression among Ethiopian women to better understand its prevalence, thereby highlighting the gaps in current research and informing future interventions.

This umbrella review used the PRIOR checklist for the reviews of systematic review and meta-analytic studies. The review protocol has been registered on PROSPERO: CRD42023495174. PubMed, EMBASE, and PsycINFO databases were searched for the presence of systematic review and meta-analysis studies. The quality of included articles has been evaluated with a measurement tool to assess systematic review and meta-analysis studies (AMSTAR). A novel graphic approach with an estimated corrected covered area (CCA) has been used to determine the degree of overlap of primary studies in the systematic review and meta-analysis studies. The weighted random effect model was used during the meta-analysis.

A total of 28 unique primary studies and 8 systematic reviews, and meta-analysis studies with 15,592 participants were included in this umbrella review. The pooled prevalence of perinatal depressive symptoms in the included systematic review and meta-analysis studies ranges from 20.1% to 25.8%. The pooled umbrella prevalence of perinatal depressive symptoms among women in Ethiopia was 22.49% (95 CI%:21.38, 23.59). The pooled umbrella analysis revealed that the antenatal and postnatal depressive symptoms were 22.76% (95% CI: 19.9, 25.62) and 21.75% (95% CI: 21.03, 22.48), respectively. In addition, the pooled prevalence of perinatal depression in studies that included 10 or below primary studies is 22.86% (95%CI:20.39, 25.33), and in those that included below 10 primary studies, it was 22.10% (95%CI: 21.55, 22.65). The novel graphic presentation depicted a very high degree of overlap of primary studies in the included systematic reviews and meta-analysis studies; corrected covered area (CCA) of 25.5%. Four of the included studies (fifty percent) had high methodological quality, and the remaining four relied on a moderate quality range.

The pooled overall, antenatal, and postnatal prevalence of depression symptoms was high in Ethiopia, with no significant difference during the antenatal and postnatal period. An improved understanding of perinatal depression will therefore guide policymakers and health practitioners in developing targeted strategies to alleviate this mental health challenge.

When the proportional hazards assumption does not hold, the hazard ratio can misrepresent treatment effects in survival analysis. We evaluate the win ratio, originally proposed for prioritizing multiple outcomes, as an effect size measure for a single survival outcome under non-proportional hazards, and compare it with the difference in restricted mean survival time (RMST). We perform bootstrap-based inference for the win ratio under both right- and interval-censoring using plug-in estimators based on nonparametric maximum likelihood estimators or spline-based sieve maximum likelihood estimators of the survival functions. We also study stratified win ratio to mitigate confounding. Extensive simulations are conducted to assess and compare the performances of the win ratio and the difference in RMST under various types of alternatives encountered in practice. The simulation results show that the win ratio-based tests outperform RMST-based tests when treatment benefits arise early, whereas RMST is more sensitive to late-onset effects, and stratified win ratio maintains nominal type I error in the presence of confounding, unlike unstratified win ratio. As an illustration, we analyze right-censored and interval-censored progression-free survival in patients with multiple myeloma treated with two different regimens. The results of this article support reporting the win ratio, along with the difference in RMST, when the proportional hazards assumption is doubtful, offering complementary clinical interpretability and robustness across censoring mechanisms and treatment effect patterns.

Distinguishing Pneumocystis jirovecii pneumonia (PJP) from colonization (PJC) is crucial due to overlapping symptoms but different treatments. This study aims to evaluate whether peripheral blood parameters can serve as a non-invasive tool for distinguishing PJP from PJC. We retrospectively enrolled 174 patients with PJP and 61 with PJC from the First Affiliated Hospital of Sun Yat-sen University (April 2022-March 2024). Peripheral blood parameters were analyzed and compared between groups. Normally distributed variables were assessed using Student's t-test, while non-parametric data were analyzed with the Wilcoxon rank-sum test. A diagnostic model was subsequently developed based on significant hematological indicators. Utilizing a significance threshold of p < 0.05, red blood cell (RBC) and lymphocyte percentage (Lym%), while excluding neutrophil percentage (Neu%), procalcitonin (PCT), and lactic dehydrogenase (LDH) were used to build a random forest diagnostic model. The optimal XGBoost model achieved an AUC of 0.9991 internally and 0.787 in external validation. A web-based tool was developed to assist diagnosis. The findings of this study offer an effective tool for clinical practice, enabling physicians to accurately diagnose and differentiate between PJP and PJC, guiding appropriate treatment for patients.

Tropical Diabetic Hand Syndrome (TDHS) is an acute, rapidly progressive hand infection affecting patients with diabetes mellitus (DM), often following trivial trauma. Unlike those with diabetic foot disease, neuropathy and vasculopathy play a minor role, while poor glycaemic control, delayed presentation, and minor injuries are key risk factors. TDHS is often not recognised in Nigeria despite its potential for disability and mortality. This study reviews the management outcomes of patients presenting with TDHS at a tertiary hospital in Nigeria.

A retrospective review was conducted of all patients with DM managed for TDHS at the Jos University Teaching Hospital from 2015 to 2024. Data were extracted on socio-demographics, type and duration of diabetes, clinical presentation, treatment, and outcomes. Descriptive statistics were applied using SPSS version 25.

Thirteen patients were included: mean age 45.4 ± 11.2 years, with a female predominance (61.5%). Most (92.3%) had type 2 diabetes of a median duration of 6 years, and poor glycaemic control was observed in 86.6%. Abscesses (53.8%) and ulcers (30.8%) were the commonest presentations, predominantly affecting the digits (61.5%). Incision and drainage with dressings (that included the use of povidone iodine) was the main surgical treatment, while flap cover was rarely required. The mean hospital stay was 26.5 ± 23.9 days. Outcomes were favourable in 86.6% (discharged), with one death (7.7%) and one patient leaving against medical advice.

TDHS remains a preventable but serious complication of diabetes in Nigeria, predominantly affecting middle-aged women with poorly controlled type 2 diabetes. Prompt surgical and medical management yielded favourable outcomes, but prolonged hospitalisation and mortality highlight its burden. Strengthening diabetes care, patient education, and clinician awareness are vital to reducing incidence and improving outcomes.

One of the complications of Diabetes Mellitus (DM) - both type 1(T1DM) and type 2 (T2DM) is Tropical diabetic hand syndrome (TDHS). The initiating event ranges from trivial trauma to overt injury to the hand in the presence of hyperglycaemia, usually aggravated by poorly treated wounds, superimposed infection and peripheral neuropathy. This case series aims to highlight the different forms of presentation of TDHS and their outcomes.

This is a case series that reviewed four cases of TDHS managed at the Endocrine Unit of Ahmadu Bello University Teaching Hospital (ABUTH), Zaria, over an 11 months period from August 2023 to June 2024. Out of seven identified cases, four with complete treatment records were included.

Case 1: A 24-year-old female single lady with a 2-week history of a stick injury to the left hand presented with a random blood sugar (RBS) of 22.2 mmol/L, swelling, ulcers, and pus discharge. Staphylococcus spp. was cultured from the wound. She was treated with antibiotics and underwent debridement. Case 2: A 20-year-old female trader presented with a 2-weeks history of spontaneous blisters on the right hand with an RBS of 22.5mmol/L, she exhibited similar symptoms as case 1. Staphylococcus spp. was also cultured. She had antibiotics and debridement. Case 3: A 44-year-old male butcher presented with a 3-weeks history of a knife injury to the left hand, along with swelling, ulcers, pus, and gangrene with an RBS of 18.5mmol/L. He required debridement and subsequent amputation. Case 4: A 49 year-old widow, a known T2DM, and Hypertensive heart failure patient who presented with left hand swelling and ulceration from the cannula site. She eventually died from multiple organ failure.

TDHS remains a serious and preventable complication among diabetic patients in tropical regions. This case series underscores the importance of educating patients on hand care in addition to other forms of diabetic education to prevent severe outcomes such as gangrene and amputation.

The predicted skeletal muscle mass index (pSMI), derived from the serum creatinine-to-cystatin C ratio (CCR), has emerged as a novel biomarker for predicting the onset of type 2 diabetes mellitus. However, its application remains primarily limited to East Asian populations, and the relationship between pSMI and mortality in general populations remains unclear. Therefore, this study aimed to investigate the association between pSMI and all-cause mortality in a nationally representative US adult population.

We analyzed data from three cycles (1999-2004) of the National Health and Nutrition Examination Survey (NHANES). pSMI levels were analyzed both as a continuous variable and categorized into tertiles. To assess the association between pSMI and all-cause mortality, we performed multivariable Cox regression, restricted cubic spline (RCS) analysis, and Kaplan-Meier survival analysis.

During a median follow-up of 193.2 months (2217 deaths), multivariable-adjusted analyses revealed that higher pSMI levels were significantly associated with reduced all-cause mortality (HR 0.76, 95% CI 0.72-0.80; p < 0.001). Compared to the lowest tertile (T1:4.98-7.83), T2 (7.84-9.18) and T3 (9.19-19.24) showed progressively lower mortality risks (T2: HR 0.79, 95% CI 0.67-0.94, p = 0.009; T3: HR 0.66, 95% CI 0.50-0.88, p = 0.004). Restricted cubic spline analysis demonstrated an L-shaped association (p for non-linear = 0.003) with an inflection point at 10.0 (HR 0.632, 95% CI 0.543-0.721; p < 0.001). Sex-stratified analyses revealed inflection points at 10.5 (males) and 7.6 (females). Kaplan-Meier analysis confirmed significantly improved survival with higher pSMI levels (all p < 0.001 for total population, males and females).

This study identifies pSMI as an independent predictor of lower all-cause mortality, revealing a nonlinear L-shaped association with a distinct threshold effect. The protective relationship remains consistent across both sexes, though with differing inflection points. These findings highlight the clinical importance of assessing skeletal muscle mass for mortality risk stratification.