Unveiling the future of COVID-19 patient care: groundbreaking prediction models for severe outcomes or mortality in hospitalized cases.

Background: Previous studies have identified COVID-19 risk factors, such as age and chronic health conditions, linked to severe outcomes and mortality. However, accurately predicting severe illness in COVID-19 patients remains challenging, lacking precise methods. Objective: This study aimed to leverage clinical real-world data and multiple machine-learning algorithms to formulate innovative predictive models for assessing the risk of severe outcomes or mortality in hospitalized patients with COVID-19. Methods: Data were obtained from the Taipei Medical University Clinical Research Database (TMUCRD) including electronic health records from three Taiwanese hospitals in Taiwan. This study included patients admitted to the hospitals who received an initial diagnosis of COVID-19 between January 1, 2021, and May 31, 2022. The primary outcome was defined as the composite of severe infection, including ventilator use, intubation, ICU admission, and mortality. Secondary outcomes consisted of individual indicators. The dataset encompassed demographic data, health status, COVID-19 specifics, comorbidities, medications, and laboratory results. Two modes (full mode and simplified mode) are used; the former includes all features, and the latter only includes the 30 most important features selected based on the algorithm used by the best model in full mode. Seven machine learning was employed algorithms the performance of the models was evaluated using metrics such as the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, and specificity. Results: The study encompassed 22,192 eligible in-patients diagnosed with COVID-19. In the full mode, the model using the light gradient boosting machine algorithm achieved the highest AUROC value (0.939), with an accuracy of 85.5%, a sensitivity of 0.897, and a specificity of 0.853. Age, vaccination status, neutrophil count, sodium levels, and platelet count were significant features. In the simplified mode, the extreme gradient boosting algorithm yielded an AUROC of 0.935, an accuracy of 89.9%, a sensitivity of 0.843, and a specificity of 0.902. Conclusion: This study illustrates the feasibility of constructing precise predictive models for severe outcomes or mortality in COVID-19 patients by leveraging significant predictors and advanced machine learning. These findings can aid healthcare practitioners in proactively predicting and monitoring severe outcomes or mortality among hospitalized COVID-19 patients, improving treatment and resource allocation.

Global Threat of Carbapenem-Resistant Gram-Negative Bacteria.

Infections caused by multidrug-resistant (MDR) and extensively drug-resistant (XDR) Gram-negative bacteria (GNB), including carbapenem-resistant (CR) Enterobacterales (CRE; harboring mainly blaKPC, blaNDM, and blaOXA-48-like genes), CR- or MDR/XDR-Pseudomonas aeruginosa (production of VIM, IMP, or NDM carbapenemases combined with porin alteration), and Acinetobacter baumannii complex (producing mainly OXA-23, OXA-58-like carbapenemases), have gradually worsened and become a major challenge to public health because of limited antibiotic choice and high case-fatality rates. Diverse MDR/XDR-GNB isolates have been predominantly cultured from inpatients and hospital equipment/settings, but CRE has also been identified in community settings and long-term care facilities. Several CRE outbreaks cost hospitals and healthcare institutions huge economic burdens for disinfection and containment of their disseminations. Parenteral polymyxin B/E has been observed to have a poor pharmacokinetic profile for the treatment of CR- and XDR-GNB. It has been determined that tigecycline is suitable for the treatment of bloodstream infections owing to GNB, with a minimum inhibitory concentration of ≤ 0.5 mg/L. Ceftazidime-avibactam is a last-resort antibiotic against GNB of Ambler class A/C/D enzyme-producers and a majority of CR-P. aeruginosa isolates. Furthermore, ceftolozane-tazobactam is shown to exhibit excellent in vitro activity against CR- and XDR-P. aeruginosa isolates. Several pharmaceuticals have devoted to exploring novel antibiotics to combat these troublesome XDR-GNBs. Nevertheless, only few antibiotics are shown to be effective in vitro against CR/XDR-A. baumannii complex isolates. In this era of antibiotic pipelines, strict implementation of antibiotic stewardship is as important as in-time isolation cohorts in limiting the spread of CR/XDR-GNB and alleviating the worsening trends of resistance.

Increasing Risks of Suicide Attempt and Suicidal Drug Overdose After Head Trauma in Patients With Sleep-Disordered Breathing: A Population-Based Study.

Objective: To determine the risks of suicide attempt (SA) and suicidal drug overdose (SDO) after head trauma in patients with sleep-disordered breathing (SDB) by using the National Health Insurance Research Database of Taiwan. Methods: We analyzed the data of patients aged ≥20 years who were diagnosed with SDB between 2000 and 2012. We further divided them into two cohorts [with admission for head injury (SBI) and without (SBN)], and we compared them against sex-, age-, comorbidity-, and index-date-matched healthy individuals. The adjusted hazard ratios (aHRs) and 95% confidence intervals of SA and SDO were calculated with adjustment of age, sex, and comorbidities. Results: Approximately 0.61% of patients among the overall 142,063 patients with SDB had SA, with 535 and 335 patients included in the SBN and SBI cohorts, respectively. Compared with patients with SBN, a significantly higher risk of SA was observed in patients with SBI (aHR = 2.22), especially in those aged under 50 years (aHR = 2.48). Notably, a SDO incidence of 1.20% was noted in patients with SDB, and the SBI cohort had a 1.81-fold higher risk for SDO when compared with the SBN cohort. Conclusion: The risks of subsequent SA and SDO are proportionally increased by the effects of head trauma with a moderating role of SDB, especially in those aged <50 years. SDB and head trauma can increase suicide behaviors individually and synergistically.

Role of gender in the survival outcome of acute phase of major trauma: A nationwide, population-based study.

BACKGROUND: Animal models of trauma have shown that females have better posttraumatic survival; however, results of previous studies on the influence of gender on major trauma patients have been controversial. This study aimed to evaluate the association between gender and survival in major trauma patients. METHODS: We retrospectively analyzed patients registered in Taiwan's National Health Insurance Research Database between 2008 and 2012 with the diagnosis codes 800-939 and 950-957 (International Classification of Diseases, ninth revision, clinical modification). Data on gender, age, catastrophic illness, and new injury severity score (NISS) ≥16 were collected for comparing patients' mortality after trauma. Propensity score matching (PSM) was performed to eliminate dissimilarities in age, comorbidities, NISS, and primary traumatic regions between the genders. RESULTS: Among 10 012 major trauma patients included in the study cohort, 28.8% (n = 2880) were women. The PSM patient group consisted of 50% (2876 of 5752) women. Women had a higher 30-day (15.4% of women vs 13.8% of men; p < 0.05) and hospital (16.1% of women vs 14.5% of men; p < 0.05) mortality and lower incidence rates of acute respiratory dysfunction (62.5% of women vs 65.9% of men; p < 0.005) and acute hepatic dysfunction (0.8% of women vs 2.1% of men; p < 0.001). However, the analysis of PSM patient groups showed lower mortality rates in women with moderate trauma (NISS 16-24) in the acute phase within three days (1.4% of women vs 2.7% of men, p = 0.03). Analysis of patients with an NISS of 16-24 who died within three days showed a higher NISS in women than in men (19.7 ± 2.3 vs 18.0 ±1.9, respectively, p <0.05). CONCLUSION: There is no gender difference in 30-day or hospital mortality among major trauma patients. However, women admitted for moderate major trauma had higher survival within three days of major trauma.

Poststroke Parkinsonism associates with an increased mortality risk in patients.

BACKGROUND: To determine whether poststroke Parkinsonism (PSP) increases mortality risk in poststroke patients by using Taiwan National Health Insurance Research Database (NHIRD). METHODS: We analyzed NHIRD data of ≥40-year-old patients diagnosed as having stroke [International Classification of Disease, Ninth Revision, Clinical Modification (ICD-9-CM) codes 430-438] between 2000 and 2013. Poststroke patients were divided into those with subsequent PSP (ICD-9-CM codes 332, 332.0, and 332.1) and without PSP (non-Parkinsonism, PSN) cohorts, all compared with a sex-, age-, comorbidity-, and index date-matched comparison cohort. We calculated adjusted hazard ratios (aHRs) and 95% confidence intervals (CIs) of all-cause mortality risk in these cohorts after adjustments for age, sex, and comorbidities. RESULTS: PSP was noted in 11.87% (1,644/13,846) of poststroke patients. In the PSN, PSP, and comparison cohorts, mortality incidence rates were 69.1, 124.9, and 38.8 per 1,000 person-years, respectively. Compared with the comparison cohort, the mortality risks in patients aged 40 to 64, 65 to 74, and ≥75 years were respectively 2.21-, 1.91-, and 1.86-fold higher mortality risks in the PSN cohort and 4.57-, 2.84-, and 2.27-fold higher mortality risks in the PSP cohort. Male sex further increased mortality risk in poststroke patients with PSP. CONCLUSIONS: Long-term all-cause mortality risk is increased by 1.39 times in poststroke patients with PSP than in those without. Our findings depict vital information in incidence and risk of PSP. Those would aid clinicians and the government to improve future poststroke care.

Long-Term Mortality and Medical Burden of Patients with Chronic Obstructive Pulmonary Disease with and without Subsequent Stroke Episodes.

BACKGROUND: We used the Taiwan National Health Insurance Research Database (NHIRD) to determine the differences in mortality and medical burden between patients with chronic obstructive pulmonary disease (COPD) with and without stroke. METHODS: We enrolled participants aged ≥20 years and defined four subgroups in this study, namely patients with COPD (International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9 CM): 491, 492, 494, and 496), patients with COPD with stroke (ICD-9 CM: 430-438), with COPD without stroke, and comparison subgroups. We calculated the hazard ratios and 95% CIs for all-cause mortality risk, average duration of hospitalization, and frequency of medical visits in these subgroups after adjustments were made for age, sex, and comorbidities. All participants were followed until the date of death, the date they were censored, the date they withdrew from the NHIRD, or 31 December, 2013. RESULTS: In total, 9.70% (men vs. women, 11.19% vs. 8.28%) of patients with COPD developed subsequent stroke during the 14 year follow-up. After a stroke, the risk of mortality exhibited a 2.66- to 5.05-fold increase, especially in the younger ones. COPD with stroke was also a leading factor in the increase in the average number of hospitalization days and frequency of medical visits. CONCLUSION: The mortality risk of patients with COPD is considerably increased by stroke independent of the other effects of COPD. Moreover, the average number of hospitalization days and frequency of medical visits dramatically increased in patients with COPD after stroke.

Increased Risks of Suicide Attempt and Suicidal Drug Overdose Following Admission for Head Injury in Patients with Depression.

AIMS: To determine the risks of suicide attempt (SA) and suicidal drug overdose (SDO) following the admission for head injury of patients with depression. DESIGN: We analyzed the NHIRD data of patients aged ≥20 years who had received depression diagnoses between 2000 and 2010. They were divided into cohorts of those with admission for head injury (DHI) and those without it (DWI) during the follow-up period and compared against a sex-, age-, comorbidity-, and index-date-matched cohort from the general population. SETTING: The Taiwan National Health Insurance Research Database (NHIRD). Participants/Cases: We analyzed the NHIRD data of patients (≥20 years) who had received depression diagnoses between 2000 and 2010. INTERVENTION(S): Regular interventions. MEASUREMENTS: We calculated the adjusted hazard ratios (aHRs) and 95% confidence intervals (CIs) of SA and SDO in these cohorts after adjustment for age, sex, and comorbidities. FINDINGS: Up to the end of 2011, our results revealed extremely high incidences of SA and SDO with 63.3 and 88.6 per 10,000 person-years, respectively, in the DHI cohort. The DHI cohort had a 37.4-times higher risk for SA and a 17.1-times higher risk for SDO compared with the comparison group and had aHRs of 14.4 and 16.3, respectively, for poisoning by medicinal substances and poisoning by tranquilizers compared with patients in the DWI cohort. Patients with DHI aged <50 years, of female sex, with high incomes, living in more urbanized areas, and without other comorbidities had extraordinarily higher risks for SA. CONCLUSIONS: The risks of SA and SDO were proportionally increased by head injury in patients with depression in Taiwan. Our findings provide crucial information to implement efficient suicide prevention strategies in the future.

Analyzing Mortality Risk and Medical Burden among Patients with Traumatic Brain Injury and Subsequent Dementia.

We used the National Health Insurance Research Database of Taiwan to determine whether patients with posttraumatic dementia (PTD) exhibit increased mortality and medical burden than those without it. Patients ≥20 years of age having head injury admission (per the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes 850-854, 959.01) between 2000 and 2012 were enrolled as traumatic brain injury (TBI) cohort. A PTD cohort (with ICD-9-CM codes 290, 294.1, 331.0) and a posttraumatic nondementia (PTN) cohort were established and compared in terms of age, sex, and comorbidities. We calculated adjusted hazard ratios (aHRs) and 95% confidence intervals (CIs) of all-cause mortality risk, number of hospital days, and frequency of medical visits in these cohorts. Patients with PTD had a higher mortality rate than did patients with TBI alone (rate per 1000 person-years: 12.00 vs. 6.32), with an aHR of 1.54 (95% CI: 1.32-1.80). Patients with PTD who were aged ≥65 years (aHR = 1.54, 95% CI: 1.31-1.80) or male (aHR = 1.78, 95% CI: 1.45-2.18) exhibited greatly increased risks of mortality. Furthermore, patients with PTD had 19.9 more hospital days and required medical visits 4.49 times more frequently compared with the PTN cohort. Taiwanese patients with PTD had increased mortality risk and medical burden compared with patients who had TBI only. Our findings provide crucial information for clinicians and the government to improve TBI and PTD outcomes.

Posttraumatic parkinsonism would increase the mortality risk in elderly patients with traumatic brain injury.

BACKGROUND: We used data from the National Health Insurance Research Database (NHIRD) of Taiwan to determine whether patients who develop posttraumatic parkinsonism (PTP) after traumatic brain injury (TBI) have an increased mortality risk. METHODS: We analyzed data from the NHIRD of patients aged ≥20 years who had received a diagnosis of and admitted for head injury with TBI (ICD-9-CM 850-854, 959.01) from 2000 to 2012. The TBI cohort was further divided into PTP and posttraumatic non-parkinsonism (PTN) cohorts and compared against a sex-, age-, comorbidity-, and index-date-matched comparison cohort. We calculated the adjusted hazard ratios (aHRs) and 95% confidence intervals (CIs) of all-cause mortality risk in these cohorts after adjustment for age, sex, and comorbidities. RESULTS: There were 23,504 and 744 patients enrolled in the PTN cohort and the PTP cohort. Subsequent parkinsonism happened with an incidence of 3.07% in patients with TBI, and 11.59% in those aged over 65 years. The PTP cohort (aHR =1.67, 95% CI: 1.47-1.90) other than PTN (aHR =1.37, 95% CI: 1.29-1.45) cohort had a higher risk of mortality. In ones aged 65-74 years (aHR =2.08, 95% CI: 1.41-3.07), there was a more increased mortality risk in patients with PTP when compared to the PTN cohort. CONCLUSIONS: PTP would increase the long-term mortality risk of patients with TBI, especially in whom aged 65-74 years. Our findings provide vital information for clinicians and the government to improve the long-term prognosis of TBI.

The association of heart rate variability with parkinsonian motor symptom duration.

PURPOSE: Impaired cardiovascular autonomic regulation is a non-motor symptom of Parkinson's disease (PD) and may increase long-term morbidity. This study applied frequency-domain analysis of heart rate variability (HRV) to understand the progression of sympathetic and parasympathetic cardiac regulation in patients with PD. MATERIALS AND METHODS: In this cross-sectional study, 21 male and 11 female Taiwanese patients with advanced PD and 32 healthy gender- and age-matched subjects were enrolled. To minimize artifacts due to subject motion, daytime electrocardiograms for 5 minutes were recorded in awake patients during levodopa-on periods and controls. Using fast Fourier transformation, heart rate variables were quantified into a high-frequency power component [0.15-0.45 Hz, considered to reflect vagal (parasympathetic) regulation], low-frequency power component (0.04-0.15 Hz, reflecting mixed sympathetic and parasympathetic regulation), and low-frequency power in normalized units (reflecting sympathetic regulation). The significance of between-group differences was analyzed using the paired t-test. Pearson correlation analysis and stepwise regression analysis were applied to assess the correlation of patient age, PD duration, and disease severity (represented by the Unified Parkinson's Disease Rating Scale) with each heart rate variables. RESULTS: Impaired HRV is significantly correlated with the duration of PD, but not with disease severity and patient age. Meanwhile, parasympathetic heart rate variable is more likely than sympathetic heart rate variable to be affected by PD. CONCLUSION: PD is more likely to affect cardiac parasympathetic regulation than sympathetic regulation by time and the heart rate variables have the association with Parkinsonian motor symptom duration.