BACKGROUND: Pulmonary tuberculosis (PTB) is a prevalent chronic disease associated with a significant economic burden on patients. Using machine learning to predict hospitalization costs can allocate medical resources effectively and optimize the cost structure rationally, so as to control the hospitalization costs of patients better.
METHODS: This research analyzed data (2020-2022) from a Kashgar pulmonary hospital\'s information system, involving 9570 eligible PTB patients. SPSS 26.0 was used for multiple regression analysis, while Python 3.7 was used for random forest regression (RFR) and MLP. The training set included data from 2020 and 2021, while the test set included data from 2022. The models predicted seven various costs related to PTB patients, including diagnostic cost, medical service cost, material cost, treatment cost, drug cost, other cost, and total hospitalization cost. The model\'s predictive performance was evaluated using R-square (R2), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) metrics.
RESULTS: Among the 9570 PTB patients included in the study, the median and quartile of total hospitalization cost were 13,150.45 (9891.34, 19,648.48) yuan. Nine factors, including age, marital status, admission condition, length of hospital stay, initial treatment, presence of other diseases, transfer, drug resistance, and admission department, significantly influenced hospitalization costs for PTB patients. Overall, MLP demonstrated superior performance in most cost predictions, outperforming RFR and multiple regression; The performance of RFR is between MLP and multiple regression; The predictive performance of multiple regression is the lowest, but it shows the best results for Other costs.
CONCLUSIONS: The MLP can effectively leverage patient information and accurately predict various hospitalization costs, achieving a rationalized structure of hospitalization costs by adjusting higher-cost inpatient items and balancing different cost categories. The insights of this predictive model also hold relevance for research in other medical conditions.

Robotic surgery has been increasingly adopted in various surgical fields, but the cost-effectiveness of this technology remains controversial due to its high cost and limited improvements in clinical outcomes. This study aims to explore the health economic implications of robotic pancreatic surgery, to investigate its impact on hospitalization costs and consumption of various medical resources. Data of patients who underwent pancreatic surgery at our institution were collected and divided into robotic and traditional groups. Statistical analyses of hospitalization costs, length of stay, costs across different service categories, and subgroup cost analyses based on age, BMI class, and procedure received were performed using t tests and linear regression. Although the total hospitalization cost for the robotic group was significantly higher than that for the traditional group, there was a notable reduction in the cost of medical consumables. The reduction was more prominent among elderly patients, obese patients, and those undergoing pancreaticoduodenectomy, which could be attributed to the technological advantages of the robotic surgery platform that largely facilitate blood control, tissue protection, and suturing. The study concluded that despite higher overall costs, robotic pancreatic surgery offers significant savings in medical consumables, particularly benefiting certain patient subgroups. The findings provide valuable insights into the economic viability of robotic surgery, supporting its adoption from a health economics perspective.

Adverse events (AEs) are a significant concern for healthcare systems. However, it is difficult to evaluate their influence because of the complexity of various medical services. This study aimed to assess the influence of AEs on the outcomes of hospitalized patients using a diagnosis-related group (DRG) database. We conducted a case-control study of hospitalized patients at a multi-district tertiary hospital with 2200 beds in China, using data from a DRG database. An AE refers to an unintended physical injury caused or contributed to by medical care that requires additional hospitalization, monitoring, treatment, or even death. Relative weight (RW), a specific indicator of DRG, was used to measure the difficulty of diagnosis and treatment, disease severity, and medical resources utilized. The primary outcomes were hospital length of stay (LOS) and hospitalization costs. The secondary outcome was discharge to home. This study applied DRG-based matching, Hodges-Lehmann estimate, regression analysis, and subgroup analysis to evaluate the influence of AEs on outcomes. Two sensitivity analyses by excluding short LOS and changing adjustment factors were performed to assess the robustness of the results. We identified 2690 hospitalized patients who had been divided into 329 DRGs, including 1345 patients who experienced AEs (case group) and 1345 DRG-matched normal controls. The Hodges-Lehmann estimate and generalized linear regression analysis showed AEs led to prolonged LOS (unadjusted difference, 7 days, 95% confidence interval [CI] 6-8 days; adjusted difference, 8.31 days, 95% CI 7.16-9.52 days) and excess hospitalization costs (unadjusted difference, $2186.40, 95% CI: $1836.87-$2559.16; adjusted difference, $2822.67, 95% CI: $2351.25-$3334.88). Logistic regression analysis showed AEs were associated with lower odds of discharge to home (unadjusted odds ratio [OR] 0.66, 95% CI 0.54-0.82; adjusted OR 0.75, 95% CI 0.61-0.93). The subgroup analyses showed that the results for each subgroup were largely consistent. LOS and hospitalization costs increased significantly after AEs in complex diseases (RW ≥ 2) and in relation to high degrees of harm subgroups (moderate harm and above groups). Similar results were obtained in sensitivity analyses. The burden of AEs, especially those related to complex diseases and severe harm, is significant in China. The DRG database serves as a valuable source of information that can be utilized for the evaluation and management of AEs.

BACKGROUND: The Diagnosis-Intervention Packet (DIP) payment system, initiated by China\'s National Healthcare Security Administration, is designed to enhance healthcare efficiency and manage rising healthcare costs. This study aims to evaluate the impact of the DIP payment reform on inpatient care in a specialized obstetrics and gynecology hospital, with a focus on its implications for various patient groups.
METHODS: To assess the DIP policy\'s effects, we employed the Difference-in-Differences (DID) approach. This method was used to analyze changes in total hospital costs and Length of Stay (LOS) across different patient groups, particularly within select DIP categories. The study involved a comprehensive examination of the DIP policy\'s influence pre- and post-implementation.
RESULTS: Our findings indicate that the implementation of the DIP policy led to a significant increase in both total costs and LOS for the insured group relative to the self-paying group. The study further identified variations within DIP groups both before and after the reform. In-depth analysis of specific disease groups revealed that the insured group experienced notably higher total costs and LOS compared to the self-paying group.
CONCLUSIONS: The DIP reform has led to several challenges, including upcoding and diagnostic ambiguity, because of the pursuit of higher reimbursements. These findings underscore the necessity for continuous improvement of the DIP payment system to effectively tackle these challenges and optimize healthcare delivery and cost management.

UNASSIGNED: With the increasing demand for joint replacement surgery in China, the government has successively issued the policies of national centralized procurement (NCP) and national volume-based procurement (NVBP) of artificial joints. The purpose of this study is to evaluate the impact of NCP and NVBP policies on hospitalization cost, rehospitalization and reoperation rate of total hip arthroplasty (THA).
UNASSIGNED: In total, 347 patients who underwent THA from January 2019 to September 2022 were retrospectively analyzed. According to the implementation of NCP and NVBP, patients were divided into three groups: control group (n = 147), NCP group (n = 130), and NVBP group (n = 70). Patient-level data on the total hospitalization costs, rehospitalization rate, THA reoperation rate and inpatient component costs were collected before and after the implementation of the policies and Consumer Price Index was used to standardize the cost.
UNASSIGNED: After the implementation of NCP and NVBP, the total cost of hospitalization decreased by $817.41 and $3950.60 (p < 0.01), respectively. The implantation costs decreased from $5264.29 to $4185.53 and then rapidly to $1143.49 (p < 0.01), contributing to increased total cost savings. However, the cost of surgery and rehabilitation increased after NCP and NVBP implementation (p < 0.01). The proportion of implants decreased from 66.76 to 59.22% and then to 29.07%, whereas that of drugs increased from 7.98 to 10.11% and then to 12.06%. The proportion of operating expenses rose from 4.86 to 8.01% and then to 18.47%. Univariate linear regression analysis showed that hospital stay, NCP and NVBP were correlated with total hospitalization cost (p < 0.01). Multivariate analysis showed that hospital stay, NCP and NVBP were independent predictors of total hospitalization cost (p < 0.01).
UNASSIGNED: In this study, hospital stay, NCP, and NVBP were independent predictors of total inpatient costs. After the implementation of NVBP policy, the cost of implants and hospitalization has decreased significantly, and the technical labor value of medical staff has increased, but a multifaceted method is still needed to solve the problem of increasing costs of other consumables. Limitations of the study suggest the need for further and more comprehensive evaluation in the future.

BACKGROUND: Because the proportion of elderly individuals and the incidence of cancer worldwide are continually increasing, medical costs for elderly inpatients with cancer are being significantly increasing, which puts tremendous financial pressure on their families and society. The current study described the actual direct medical costs of elderly inpatients with cancer and analyzed the influencing factors for the costs to provide advice on the prevention and control of the high medical costs of elderly patients with cancer.
METHODS: A retrospective descriptive analysis was performed on the hospitalization expense data of 11,399 elderly inpatients with cancer at a tier-3 hospital in Dalian between June 2016 and June 2020. The differences between different groups were analyzed using univariate analysis, and the influencing factors of hospitalization expenses were explored by multiple linear regression analysis.
RESULTS: The hospitalization cost of elderly cancer patients showed a decreasing trend from 2016 to 2020. Specifically, the top 3 hospitalization costs were material costs, drug costs and surgery costs, which accounted for greater than 10% of all cancers according to the classification: colorectal (23.96%), lung (21.74%), breast (12.34%) and stomach cancer (12.07%). Multiple linear regression analysis indicated that cancer type, surgery, year and length of stay (LOS) had a common impact on the four types of hospitalization costs (P < 0.05).
CONCLUSIONS: There were significant differences in the four types of hospitalization costs for elderly cancer patients according to the LOS, surgery, year and type of cancer. The study results suggest that the health administration department should enhance the supervision of hospital costs and elderly cancer patient treatment. Measures should be taken by relying on the hospital information system to strengthen the cost management of cancer diseases and departments, optimize the internal management system, shorten elderly cancer patients LOS, and reasonably control the costs of disease diagnosis, treatment and department operation to effectively reduce the economic burden of elderly cancer patients.

OBJECTIVE: Upper urinary tract stones (UUTSs) are among the most common types of urinary stones, and their incidence rate has been increasing annually in recent years, seriously affecting the daily lives of patients. This study aimed to compare the treatment efficacy of one-stage and staged flexible ureteroscopic lithotripsy (FURL) for UUTSs.
METHODS: A total of 142 patients with UUTSs admitted to our hospital between December 2019 and March 2023 were selected for retrospective analysis, including 76 patients who received staged FURL (control group) and 66 patients who received one-stage FURL (observation group). The duration of surgery, length of stay, stone clearance rate, incidence of postoperative complications (from postsurgery to discharge), and total hospitalization cost were analyzed in both groups. The visual analog scale (VAS) score and activities of daily living (ADL) score were assessed before surgery (T0), 3 days after surgery (T1), and 7 days after surgery (T2). Patients were followed up for 1 month after surgery, and their quality of life was assessed using the MOS Item Short Form Health Survey (SF-36).
RESULTS: There was no difference in the stone clearance rate or incidence of postoperative complications between the two groups (p > 0.05). The operation time, hospitalization time and hospitalization cost in the observation group were 75.58 ± 15.91 min, 4.20 ± 1.24 days and 14312.62 ± 1078.89 yuan, respectively, which were lower than those in the control group (p < 0.05). In addition, the VAS score at T3 was decreased to 1.49 ± 0.70, while the ADL and SF-36 scores were higher in the observation group (p < 0.05).
CONCLUSIONS: One-stage FURL shortens the duration of surgery and length of stay, reduces hospitalization costs, and improves the quality of life of patients with UUTSs.

OBJECTIVE: To report the cost of hospitalization and the associated risk factors for rheumatic diseases in middle-aged and elderly patients in China.
METHODS: The study participants included inpatients from hospitals of various levels in the Jiangsu Province Health Account database in 2016. Participants were selected by using a multistage sampling method. Patients <45 years of age were excluded, and patients hospitalized for rheumatic diseases were identified according to the 10th edition of the International Classification of Diseases. Generalized linear models were used to analyze the sociodemographic characteristics related to the hospitalization costs of patients with rheumatic diseases.
RESULTS: The study included 3696 patients. The average cost of hospitalization for patients with rheumatic diseases was USD 4038.63. Female sex, a long length of stay, age between 65 and 74 years, free medical care, not being covered by the Urban-Rural Residents Basic Medical Insurance, and a high hospital level were associated with high hospitalization costs.
CONCLUSIONS: This study examined hospitalization costs and relevant influencing factors in middle-aged and elderly patients with rheumatic disease in China. Our findings are useful for further research on costs of disease and the economic evaluation of strategies to prevent rheumatic disease.

UNASSIGNED: Frailty, representing the physiological reserve and tolerance of the body, serves as a crucial evaluation index of the overall status of the older adults. This study aimed to investigate the prevalence of preoperative frailty and its impact on postoperative outcomes among older adults with lumbar degenerative disease in China.
UNASSIGNED: In this prospective study, a total of 280 patients aged 60 and above, diagnosed with lumbar degenerative disease and scheduled for surgical intervention were enrolled. The prevalence of frailty pre-surgery was evaluated using the Tilburg Frailty Indicator (TFI) and the modified Frailty Index 11 (mFI-11). The primary outcome was postoperative complication within 30 days post-surgery. The secondary outcomes were the length of hospital stay, hospital costs, reoperation within 30 days post-surgery and unplanned readmission within 30 days post-discharge. Both univariable and multivariable logistic regression were employed to screen and identify the risk factors predisposing patients to postoperative complications.
UNASSIGNED: A total of 272 older adults were included in the study ultimately. The frailty detection rates of TFI and mFI-11 were 15.8% (43/272) and 10.7% (29/272) respectively. Thirty-four patients (12.5%) encountered complications. Significantly elevated rates of complications, prolonged hospital stays, increased hospital costs, and heightened readmission rates were observed in the frail group compared to the non-frail group (P<0.05). Univariable analysis showed that the potential factors related to complications are TFI, mFI-11 and albumin. Multivariable logistic regression revealed that TFI was an independent risk factor for postoperative complications (OR=5.371, 95% CI: 2.338-12.341, P < 0.001).
UNASSIGNED: Frailty was an independent predictor of postoperative complications in older adults undergoing lumbar fusion surgery. Frailty assessment should be performed in such patients to improve preoperative risk stratification and optimize perioperative management strategies.

OBJECTIVE: Assess hospital healthcare resource utilization (HCRU) and associated hospital costs of patients with lupus nephritis (LN) in China and compare these outcomes with a systemic lupus erythematosus (SLE) cohort (SLE with/without LN) as well as exploring the effect of end-stage kidney disease (ESKD).
METHODS: This retrospective administrative claims-based analysis identified patients with SLE and SLE with LN from China using diagnosis codes and keywords. Patients with LN were subcategorized by presence of ESKD. Outcomes included all-cause and disease-specific HCRU (defined as healthcare visits including inpatient and outpatient visits) and medical costs (in 2022 US dollars).
RESULTS: In total, 3645 patients with SLE were included, of whom 404 (11%) had LN. Among those with LN, 142 (35%) had ESKD. Median (interquartile range) all-cause healthcare visits per patient per month (PPPM) was significantly greater for patients with LN (2.08 [4.01]) vs SLE (0.92 [1.64]; P < .0001). Patients with LN and ESKD (3.00 [4.18]) had numerically more all-cause healthcare visits PPPM compared with LN patients without ESKD (1.50 [3.45]). Median all-cause costs PPPM were significantly greater among patients with LN ($287.46 [477.15]) vs SLE ($113.09 [267.39]; P < .0001) and numerically higher for patients with LN and ESKD ($466.29 [958.90]) vs LN without ESKD ($223.50 [319.56]).
CONCLUSIONS: Chinese patients with LN had greater HCRU and hospital healthcare costs compared with the general SLE cohort. This burden was higher for those with ESKD. These data highlight the substantial HCRU among patients with LN in China, especially those with ESKD, suggesting the need for early diagnosis and timely management of LN to mitigate the economic burden.