Machine learning-based in-hospital mortality prediction of HIV/AIDS patients with Talaromyces marneffei infection in Guangxi, China

Characteristics and risk factors for death in HIV-positive talaromycosis marneffei patients with sepsis

Objectives

This case-control study aimed to analyze the characteristics and risk factors for death in HIV-positive Talaromycosis marneffei (TSM) patients with sepsis.

Methods

We retrospectively reviewed 173 AIDS patients diagnosed with TSM infection from January 1, 2013, to December 1, 2023, at Hangzhou Xixi Hospital. We collected and analyzed clinical characteristics, laboratory findings, bone marrow cytology results, treatment, and prognosis.

Results

Out of 173 AIDS-TSM patients, 92 had sepsis while 81 did not. AIDS-TSM patients with sepsis have a higher in-hospital mortality rate (19.6 %) than non-sepsis patients (0 %). The SOFA score showed a significant association with in-hospital mortality in AIDS-TSM patients with sepsis (OR = 1.583, 95 % CI: 1.183-2.118, P = 0.002), indicating an almost linear relationship. After adjusting for the SOFA score, only hemoglobin (Hb) (OR = 0.971, 95 % CI: 0.943-1.000, P = 0.046), international normalized ratio (INR) (OR = 22.33, 95 % CI: 1.84-270.90, P = 0.015), and C-reactive protein (CRP) (OR = 1.014, 95 % CI: 1.001-1.027, P = 0.039) remained significantly associated with in-hospital mortality. The Receiver Operating Characteristic (ROC) curve of the SOFA score, INR, and CRP showed moderately good predictive performance for in-hospital mortality, while Hb had a low predictive performance. The Area Under Curve (AUC) values were 0.834, 0.820, 0.776, and 0.669, respectively.

Conclusions

AIDS-TSM patients with sepsis have a higher mortality rate. Moreover, the SOFA score, along with Hb, INR, and CRP, are the risk factors for death in AIDS-TSM patients with sepsis.

Risk factors and prediction model for mortality in HIV/Talaromyces marneffei co-infection: A retrospective cohort study

Background

This study aimed to identify the risk factors associated with mortality among patients co-infected with human immunodeficiency virus (HIV) and Talaromyces marneffei (TM) in China, and develop a risk prediction model.

Methods

In this retrospective cohort analysis conducted from 2013 to 2024, comprehensive clinical data from 160 patients were analyzed using a logistic regression model to identify mortality predictors and construct a predictive model. An additional 36 patients constituted the validation cohort, which was specifically designed to evaluate the predictive value of the model. Model performance was assessed using the area under the curve (AUC).

Results

The overall mortality rate for hospitalized patients with HIV/TM co-infection was 17.35 %. The median age was 35.0 years, and 89.30 % were male. Additionally, 89.80 % of the patients reported fever and 87.76 % presented with lymphadenopathy. Key independent risk factors associated with mortality included age (odds ratio (OR): 1.103, 95 % confidence interval (CI) = 1.033-1.178, P = 0.003), procalcitonin (PCT) levels (OR: 1.270, 95 % CI = 1.052-1.534, P = 0.013), and urea to albumin ratio (UAR) (OR: 1.491, 95 % CI = 1.175-1.892, P < 0.001). Advanced age, elevated PCT levels, and increased UAR were identified as independent risk factors of mortality. Furthermore, the mortality prediction probability combining age, PCT, and UAR exhibited a high predictive value in patients with HIV/TM co-infection. Additionally, the AUC showed a good discrimination ability in the validation group (AUC, 0.898).

Conclusions

Advanced age, elevated PCT levels, and increased UAR significantly determine mortality in patients with HIV/TM co-infection. These findings underscore the potential of using laboratory parameters as predictive indicators of mortality, facilitating the early identification of HIV/TM co-infection cases in clinical practice.

The effects of meteorological factors and air pollutants on the incidence of tuberculosis in people living with HIV/AIDS in subtropical Guangxi, China

BACKGROUND

Previous studies have shown the association between tuberculosis (TB) and meteorological factors/air pollutants. However, little information is available for people living with HIV/AIDS (PLWHA), who are highly susceptible to TB.

METHOD

Data regarding TB cases in PLWHA from 2014 to2020 were collected from the HIV antiviral therapy cohort in Guangxi, China. Meteorological and air pollutants data for the same period were obtained from the China Meteorological Science Data Sharing Service Network and Department of Ecology and Environment of Guangxi. A distribution lag non-linear model (DLNM) was used to evaluate the effects of meteorological factors and air pollutant exposure on the risk of TB in PLWHA.

RESULTS

A total of 2087 new or re-active TB cases were collected, which had a significant seasonal and periodic distribution. Compared with the median values, the maximum cumulative relative risk (RR) for TB in PLWHA was 0.663 (95% confidence interval [CI]: 0.507-0.866, lag 4 weeks) for a 5-unit increase in temperature, and 1.478 (95% CI: 1.116-1.957, lag 4 weeks) for a 2-unit increase in precipitation. However, neither wind speed nor PM10 had a significant cumulative lag effect. Extreme analysis demonstrated that the hot effect (RR = 0.638, 95%CI: 0.425-0.958, lag 4 weeks), the rainy effect (RR = 0.285, 95%CI: 0.135-0.599, lag 4 weeks), and the rainless effect (RR = 0.552, 95%CI: 0.322-0.947, lag 4 weeks) reduced the risk of TB. Furthermore, in the CD4(+) T cells < 200 cells/µL subgroup, temperature, precipitation, and PM10 had a significant hysteretic effect on TB incidence, while temperature and precipitation had a significant cumulative lag effect. However, these effects were not observed in the CD4(+) T cells ≥ 200 cells/µL subgroup.

CONCLUSION

For PLWHA in subtropical Guangxi, temperature and precipitation had a significant cumulative effect on TB incidence among PLWHA, while air pollutants had little effect. Moreover, the influence of meteorological factors on the incidence of TB also depends on the immune status of PLWHA.

The predictive accuracy of machine learning for the risk of death in HIV patients: a systematic review and meta-analysis

BACKGROUND

Early prediction of mortality in individuals with HIV (PWH) has perpetually posed a formidable challenge. With the widespread integration of machine learning into clinical practice, some researchers endeavor to formulate models predicting the mortality risk for PWH. Nevertheless, the diverse timeframes of mortality among PWH and the potential multitude of modeling variables have cast doubt on the efficacy of the current predictive model for HIV-related deaths. To address this, we undertook a systematic review and meta-analysis, aiming to comprehensively assess the utilization of machine learning in the early prediction of HIV-related deaths and furnish evidence-based support for the advancement of artificial intelligence in this domain.

METHODS

We systematically combed through the PubMed, Cochrane, Embase, and Web of Science databases on November 25, 2023. To evaluate the bias risk in the original studies included, we employed the Predictive Model Bias Risk Assessment Tool (PROBAST). During the meta-analysis, we conducted subgroup analysis based on survival and non-survival models. Additionally, we utilized meta-regression to explore the influence of death time on the predictive value of the model for HIV-related deaths.

RESULTS

After our comprehensive review, we analyzed a total of 24 pieces of literature, encompassing data from 401,389 individuals diagnosed with HIV. Within this dataset, 23 articles specifically delved into deaths during long-term follow-ups outside hospital settings. The machine learning models applied for predicting these deaths comprised survival models (COX regression) and other non-survival models. The outcomes of the meta-analysis unveiled that within the training set, the c-index for predicting deaths among people with HIV (PWH) using predictive models stands at 0.83 (95% CI: 0.75-0.91). In the validation set, the c-index is slightly lower at 0.81 (95% CI: 0.78-0.85). Notably, the meta-regression analysis demonstrated that neither follow-up time nor the occurrence of death events significantly impacted the performance of the machine learning models.

CONCLUSIONS

The study suggests that machine learning is a viable approach for developing non-time-based predictions regarding HIV deaths. Nevertheless, the limited inclusion of original studies necessitates additional multicenter studies for thorough validation.

Aspartate Aminotransferase/Platelet Ratio Index Upon Admission Predicts 24-Week Mortality in Patients With HIV-Associated Talaromyces marneffei

Background

A high aspartate aminotransferase/platelet ratio index (APRI) predicts mortality in patients with severe infection. This study aims to assess the potential of APRI as a predictor for mortality in patients with HIV-associated Talaromyces marneffei (HTM).

Methods

Associations between APRI and CD4 count, white blood cell count, C-reactive protein (CRP) level, procalcitonin (PCT) level, and cytokines were assessed in 119 patients. Univariate and multivariate Cox regression models were used to predict APRI on 24-week mortality.

Results

APRI was positively associated with CRP (r = 0.190, P = .039), PCT (r = 0.220, P = .018), interleukin 6 (r = 0.723, P < .001), interleukin 10 (r = 0.416, P = .006), and tumor necrosis factor α (r = 0.575, P < .001) and negatively associated with CD4 count (r = -0.234, P = .011). In total, 20.2% (24/119) of patients died within the 24-week follow-up. The 24-week survival rate was 88.0% for patients with APRI <5.6% and 61.1% for those with APRI ≥5.6 (log-rank P < .001). After adjustment for sex, age, body mass index, and CD4 count, as well as serum levels of hemoglobin, APRI ≥5.6 (adjusted hazard ratio [95% CI]; 3.0 [1.2-7.1], P = .015), PCT ≥1.7 ng/mL (3.7 [1.5-9.6], P = .006), and non-amphotericin B deoxycholate treatment (2.8 [1.2-6.6], P = .018) were independent risk factors for 24-week mortality.

Conclusions

For patients with HTM, APRI is associated with severity and is an independent risk factor for 24-week mortality.

Clinical Characteristics Associated with Poor Prognosis of Acquired Immunodeficiency Syndrome Patients Complicated with Disseminated Talaromycosis marneffei

Purpose

To analyze the clinical characteristics of AIDS with dTSM, especially in patients with poor prognosis.

Patients and Methods

One hundred and seventy AIDS patients were enrolled in this single-center retrospective study. The epidemiological characteristics, clinical manifestations, laboratory tests, imaging examination, and treatment outcome were collected. Logistic regression analysis was used to estimate the risk of mortality in AIDS patients with dTSM. The predictive value was evaluated using the receiver operating characteristic (ROC) curve.

Results

From 2015 to 2022, the incidence of AIDS with dTSM in the Wenzhou region increased yearly, mainly in young adults. The mortality rate was 16.47%. The most common clinical manifestations were lymph-node enlargement (92.35%) and fever (78.24%). Multivariate logistic regression analysis showed that procalcitonin (PCT), blood urea nitrogen (BUN), shock, and antiretroviral therapy (ART) were the risk factors for poor outcomes. The model comprised four risk factors and showed an excellent prediction performance, with an AUC of 0.987 in the training cohort (95% CI: 0.946-0.999) and 0.976 in the validation cohort (95% CI: 0.887-0.999).

Conclusion

This study suggested that PCT, BUN, shock, and ART were associated with the prognosis and outcome of AIDS with dTSM and had a specific predictive value.

Severe anemia, severe leukopenia, and severe thrombocytopenia of amphotericin B deoxycholate-based induction therapy in patients with HIV-associated talaromycosis: a subgroup analysis of a prospective multicenter cohort study

BACKGROUND

This study's objective was to investigate the predictors for severe anemia, severe leukopenia, and severe thrombocytopenia when amphotericin B deoxycholate-based induction therapy is used in HIV-infected patients with talaromycosis.

METHODS

A total of 170 HIV-infected patients with talaromycosis were enrolled from January 1st, 2019, to September 30th, 2020.

RESULTS

Approximately 42.9%, 20.6%, and 10.6% of the enrolled patients developed severe anemia, severe leukopenia, and severe thrombocytopenia, respectively. Baseline hemoglobin level < 100 g/L (OR = 5.846, 95% CI: 2.765 ~ 12.363), serum creatinine level > 73.4 µmol/L (OR = 2.573, 95% CI: 1.157 ~ 5.723), AST/ALT ratio > 1.6 (OR = 2.479, 95% CI: 1.167 ~ 5.266), sodium level ≤ 136 mmol/liter (OR = 4.342, 95% CI: 1.747 ~ 10.789), and a dose of amphotericin B deoxycholate > 0.58 mg/kg/d (OR = 2.504, 95% CI:1.066 ~ 5.882) were observed to be independent risk factors associated with the development of severe anemia. Co-infection with tuberculosis (OR = 3.307, 95% CI: 1.050 ~ 10.420), and platelet level (per 10 × 109 /L) (OR = 0.952, 95% CI: 0.911 ~ 0.996) were shown to be independent risk factors associated with the development of severe leukopenia. Platelet level < 100 × 109 /L (OR = 2.935, 95% CI: 1.075 ~ 8.016) was identified as the independent risk factor associated with the development of severe thrombocytopenia. There was no difference in progression to severe anemia, severe leukopenia, and severe thrombocytopenia between the patients with or without fungal clearance at 2 weeks. 10 mg on the first day of amphotericin B deoxycholate was calculated to be independent risk factors associated with the development of severe anemia (OR = 2.621, 95% CI: 1.107 ~ 6.206). The group receiving a starting amphotericin B dose (10 mg, 20 mg, daily) exhibited the highest fungal clearance rate at 96.3%, which was significantly better than the group receiving a starting amphotericin B dose (5 mg, 10 mg, 20 mg, daily) (60.9%) and the group receiving a starting amphotericin B dose (5 mg, 15 mg, and 25 mg, daily) (62.9%).

CONCLUSION

The preceding findings reveal risk factors for severe anemia, severe leukopenia, and severe thrombocytopenia. After treatment with Amphotericin B, these severe adverse events are likely unrelated to fungal clearance at 2 weeks. Starting amphotericin B deoxycholate at a dose of 10 mg on the first day may increase the risk of severe anemia but can lead to earlier fungal clearance.

TRIAL REGISTRATION

ChiCTR1900021195. Registered 1 February 2019.

Characteristics and risk factors for readmission in HIV-infected patients with Talaromyces marneffei infection

OBJECTIVES

Talaromyces marneffei (T. marneffei) is an opportunistic fungal infection (talaromycosis), which is common in subtropical regions and is a leading cause of death in HIV-1-infected patients. This study aimed to determine the characteristics and risk factors associated with hospital readmissions in HIV patients with T. marneffei infection in order to reduce readmissions.

METHODS

We conducted a retrospective study of admitted HIV-infected individuals at the Fourth People's Hospital of Nanning, Guangxi, China, from 2012 to 2019. Kaplan-Meier analyses and Principal component analysis (PCA) were used to evaluate the effects of T. marneffei infection on patient readmissions. Additionally, univariate and multifactorial analyses, as well as Propensity score matching (PSM) were used to analyze the factors associated with patient readmissions.

RESULTS

HIV/AIDS patients with T. marneffei-infected had shorter intervals between admissions and longer lengths of stay than non-T. marneffei-infected patients, despite lower readmission rates. Compared with non-T. marneffei-infected patients, the mortality rate for talaromycosis patients was higher at the first admission. Among HIV/AIDS patients with opportunistic infections, the mortality rate was highest for T. marneffei at 16.2%, followed by cryptococcus at 12.5%. However, the readmission rate was highest for cryptococcus infection (37.5%) and lowest for T. marneffei (10.8%). PSM and Logistic regression analysis identified leukopenia and elevated low-density lipoprotein (LDL) as key factors in T.marneffei-infected patients hospital readmissions.

CONCLUSIONS

The first admission represents a critical window to intervene in the prognosis of patients with T. marneffei infection. Leukopenia and elevated LDL may be potential risk factors impacting readmissions. Our findings provide scientific evidence to improve the long-term outcomes of HIV patients with T. marneffei infection.

An Overlooked and Underrated Endemic Mycosis-Talaromycosis and the Pathogenic Fungus Talaromyces marneffei

Talaromycosis is an invasive mycosis endemic in tropical and subtropical Asia and is caused by the pathogenic fungus Talaromyces marneffei. Approximately 17,300 cases of T. marneffei infection are diagnosed annually, and the reported mortality rate is extremely high (~1/3). Despite the devastating impact of talaromycosis on immunocompromised individuals, particularly HIV-positive persons, and the increase in reported occurrences in HIV-uninfected persons, diagnostic and therapeutic approaches for talaromycosis have received far too little attention worldwide. In 2021, scientists living in countries where talaromycosis is endemic raised a global demand for it to be recognized as a neglected tropical disease. Therefore, T. marneffei and the infectious disease induced by this fungus must be treated with concern. T. marneffei is a thermally dimorphic saprophytic fungus with a complicated mycological growth process that may produce various cell types in its life cycle, including conidia, hyphae, and yeast, all of which are associated with its pathogenicity. However, understanding of the pathogenic mechanism of T. marneffei has been limited until recently. To achieve a holistic view of T. marneffei and talaromycosis, the current knowledge about talaromycosis and research breakthroughs regarding T. marneffei growth biology are discussed in this review, along with the interaction of the fungus with environmental stimuli and the host immune response to fungal infection. Importantly, the future research directions required for understanding this serious infection and its causative pathogenic fungus are also emphasized to identify solutions that will alleviate the suffering of susceptible individuals worldwide.

Artificial Intelligence and Machine Learning Based Prediction of Viral Load and CD4 Status of People Living with HIV (PLWH) on Anti-Retroviral Treatment in Gedeo Zone Public Hospitals

Background

Despite the success made in scaling up HIV treatment activities, there remains a tremendous unmet demand for the monitoring of the disease progression and treatment success, which threatens HIV/AIDS treatment and control. This research presented the assessments of viral load and CD4 classification of adults enrolled in ART care using machine learning algorithms.

Methods

We trained, validated, and tested eight machine learning (ML) classifier algorithms with historical data, including demographics, clinical, and laboratory data. Data were extracted from the ART registry database of Yirgacheffe Primary Hospital and Dilla University Referral Hospital. ML classifiers were trained to predict virological failure (viral load >1000 copies/mL) and poor CD4 (CD4 cell count <200 cells/mL). The model predictive performances were evaluated using accuracy, sensitivity, specificity, precision, f1-score, F-beta scores, and AUC.

Results

The mean age of the sample participants was 41.6 years (SD = 10.9). The experimental results showed that XGB classifier ranked as the best algorithm for viral load prediction in terms of sensitivity (97%), f1-score (96%), AUC (0.99), accuracy (96%), followed by RF. The GB classifier exhibited a better predictive capability in predicting participants with a CD4 cell count <200 cells/mL.

Conclusion

In this study, the XGB and RF models had the highest accuracy and outperformed on various evaluation metrics among the models examined for viral load classification. In the prediction of participants CD4, GB model had the highest accuracy.

Pathogenic Drug Resistant Fungi: A Review of Mitigation Strategies

Fungal pathogens cause significant human morbidity and mortality globally, where there is a propensity to infect vulnerable people such as the immunocompromised ones. There is increasing evidence of resistance to antifungal drugs, which has significant implications for cutaneous, invasive and bloodstream infections. The World Health Organization (WHO) published a priority list of fungal pathogens in October 2022, thus, highlighting that a crisis point has been reached where there is a pressing need to address the solutions. This review provides a timely insight into the challenges and implications on the topic of antifungal drug resistance along with discussing the effectiveness of established disease mitigation modalities and approaches. There is also a need to elucidate the cellular and molecular mechanisms of fungal resistance to inform effective solutions. The established fungal decontamination approaches are effective for medical device processing and sterilization, but the presence of pathogenic fungi in recalcitrant biofilms can lead to challenges, particularly during cleaning. Future design ideas for implantable and reusable medical devices should consider antifungal materials and appropriates for disinfection, and where it is relevant, sterilization. Preventing the growth of mycotoxin-producing fungi on foods through the use of appropriate end-to-end processes is advisable, as mycotoxins are recalcitrant and challenging to eliminate once they have formed.

Disseminated Talaromyces marneffei infection after renal transplantation: A case report and literature review

We reported a 31-year-old man who received renal transplantation for more than 2 years. He was admitted to our hospital on 9 March 2022 due to intermittent diarrhea accompanied by leukopenia for more than 1 month. The patient successively developed high fever, cough, anemia, weight loss, gastrointestinal bleeding, and liver function impairment. Computed tomography (CT) revealed a slight inflammation in the lower lobes of both lungs, enlargement of the lymph nodes in the retroperitoneal and the root of mesenteric areas, and hepatosplenomegaly. Talaromyces marneffei was detected by metagenomics next-generation sequencing (mNGS) in blood and bronchoalveolar lavage fluid, and the pathogen was subsequently verified by blood culture. After endoscopic hemostatic therapy and antifungal therapy with voriconazole and amphotericin B cholesteryl sulfate complex, the patient was successfully discharged. Oral voriconazole was given regularly after discharge. Diarrhea, fever, enlargement of the lymph nodes, and endoscopic evidence of erosion may indicate intestinal T. marneffei infection. Although the mortality of T. marneffei infection after renal transplantation is very high, timely and effective antifungal therapy with amphotericin B cholesteryl sulfate complex is still expected to improve its prognosis.

Population pharmacokinetics of voriconazole and initial dosage optimization in patients with talaromycosis

The high variability and unpredictability of the plasma concentration of voriconazole (VRC) pose a major challenge for clinical administration. The aim of this study was to develop a population pharmacokinetics (PPK) model of VRC and identify the factors influencing VRC PPK in patients with talaromycosis. Medical records and VRC medication history of patients with talaromycosis who were treated with VRC as initial therapy were collected. A total of 233 blood samples from 69 patients were included in the study. A PPK model was developed using the nonlinear mixed-effects models (NONMEM). Monte Carlo simulation was applied to optimize the initial dosage regimens with a therapeutic range of 1.0–5.5 mg/L as the target plasma trough concentration. A one-compartment model with first-order absorption and elimination adequately described the data. The typical voriconazole clearance was 4.34 L/h, the volume of distribution was 97.4 L, the absorption rate constant was set at 1.1 h^-1, and the bioavailability was 95.1%. Clearance was found to be significantly associated with C-reactive protein (CRP). CYP2C19 polymorphisms had no effect on voriconazole pharmacokinetic parameters. ‏Monte Carlo simulation based on CRP levels showed that a loading dose of 250 mg/12 h and a maintenance dose of 100 mg/12 h are recommended for patients with CRP ≤ 96 mg/L, whereas a loading dose of 200 mg/12 h and a maintenance dose of 75 mg/12 h are recommended for patients with CRP > 96 mg/L. The average probability of target attainment of the optimal dosage regimen in CRP ≤ 96 mg/L and CRP > 96 mg/L groups were 61.3% and 13.6% higher than with empirical medication, and the proportion of C_min > 5.5 mg/L decreased by 28.9%. In conclusion, the VRC PPK model for talaromycosis patients shows good robustness and predictive performance, which can provide a reference for the clinical individualization of VRC. Adjusting initial dosage regimens based on CRP may promote the rational use of VRC.