1
|
van Seventer EE, Fish MG, Fosbenner K, Kanter K, Mojtahed A, Allen JN, Blaszkowsky L, Clark JW, Dubois J, Franses JW, Giantonio BJ, Goyal L, Klempner SJ, Roeland EJ, Ryan DP, Weekes CD, Mulvey T, El-Jawahri A, Horick N, Corcoran RB, Parikh AR, Nipp RD. Associations of baseline patient-reported outcomes with treatment outcomes in advanced gastrointestinal cancer. Cancer 2020; 127:619-627. [PMID: 33170962 DOI: 10.1002/cncr.33315] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2020] [Revised: 10/14/2020] [Accepted: 10/15/2020] [Indexed: 12/23/2022]
Abstract
BACKGROUND Patient-reported outcomes (PROs) assessing quality of life (QOL) and symptom burden correlate with clinical outcomes in patients with cancer. However, to the authors' knowledge, data regarding associations between PROs and treatment response are lacking. METHODS The authors prospectively approached consecutive patients with advanced gastrointestinal cancer who were initiating a new treatment. Prior to treatment, patients reported their QOL (Functional Assessment of Cancer Therapy-General [FACT-G], 4 subscales: Functional, Physical, Emotional, Social; higher scores indicate better QOL) and symptom burden (Edmonton Symptom Assessment System [ESAS], Patient Health Questionnaire-4 [PHQ-4]; higher scores represent greater symptoms). Regression models were used to examine associations of baseline PROs with treatment response (clinical benefit or progressive disease [PD] at time of first scan), healthcare utilization, and survival. RESULTS From May 2019 to April 2020, a total of 112 patients with advanced gastrointestinal cancer were enrolled. For treatment response, 64.3% had CB and 35.7% had PD. Higher baseline ESAS-Physical (odds ratio, 1.04; P = .027) and lower FACT-G Functional (odds ratio, 0.92; P = .038) scores were associated with PD. Higher ESAS-Physical (hazard ratio [HR], 1.03; P = .044) and lower FACT-G Total (HR, 0.96; P = .005), FACT-G Physical (HR, 0.89; P < .001), and FACT-G Functional (HR, 0.87; P < .001) scores were associated with a greater hospitalization risk. Lower FACT-G Total (HR, 0.96; P = .009) and FACT-G Emotional (HR, 0.86; P = .012) scores as well as higher ESAS-Total (HR, 1.03; P = .014) and ESAS-Physical (HR, 1.04; P = .032) scores were associated with worse survival. CONCLUSIONS Baseline PROs are associated with treatment response in patients with advanced gastrointestinal cancer, namely physical symptoms and functional QOL, in addition to health care use and survival. The findings of the current study support the association between PROs and important clinical outcomes, including the novel finding of treatment response.
Collapse
Affiliation(s)
- Emily E van Seventer
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Madeleine G Fish
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Kathryn Fosbenner
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Katie Kanter
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Amirkasra Mojtahed
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| | - Jill N Allen
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Lawrence Blaszkowsky
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Jeffrey W Clark
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Jon Dubois
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Joseph W Franses
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Bruce J Giantonio
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Lipika Goyal
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Samuel J Klempner
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Eric J Roeland
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - David P Ryan
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Colin D Weekes
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Therese Mulvey
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Areej El-Jawahri
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Nora Horick
- Department of Statistics, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
| | - Ryan B Corcoran
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Aparna R Parikh
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| | - Ryan D Nipp
- Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital Cancer Center, Harvard Medical School, Boston, Massachusetts
| |
Collapse
|
2
|
Extracellular Vesicles-Based Drug Delivery Systems: A New Challenge and the Exemplum of Malignant Pleural Mesothelioma. Int J Mol Sci 2020; 21:ijms21155432. [PMID: 32751556 PMCID: PMC7432055 DOI: 10.3390/ijms21155432] [Citation(s) in RCA: 26] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2020] [Revised: 07/24/2020] [Accepted: 07/27/2020] [Indexed: 02/07/2023] Open
Abstract
Research for the most selective drug delivery to tumors represents a fascinating key target in science. Alongside the artificial delivery systems identified in the last decades (e.g., liposomes), a family of natural extracellular vesicles (EVs) has gained increasing focus for their potential use in delivering anticancer compounds. EVs are released by all cell types to mediate cell-to-cell communication both at the paracrine and the systemic levels, suggesting a role for them as an ideal nano-delivery system. Malignant pleural mesothelioma (MPM) stands out among currently untreatable tumors, also due to the difficulties in achieving an early diagnosis. Thus, early diagnosis and treatment of MPM are both unmet clinical needs. This review looks at indirect and direct evidence that EVs may represent both a new tool for allowing an early diagnosis of MPM and a potential new delivery system for more efficient therapeutic strategies. Since MPM is a relatively rare malignant tumor and preclinical MPM models developed to date are very few and not reliable, this review will report data obtained in other tumor types, suggesting the potential use of EVs in mesothelioma patients as well.
Collapse
|
3
|
Abstract
BACKGROUND Non small cell lung cancer (NSCLC) diagnosis and treatment is a highly complex process, requiring managerial skills merged with clinical knowledge and experience. Integrated care pathways (ICPs) might be a good strategy to overview and improve patient's management. The aim of this study was to review the ICPs of NSCLC patients in a University Hospital and to identify areas of quality improvement. MATERIALS AND METHODS The electronic medical records of 169 NSCLC patients visited at the University Hospital were retrospectively reviewed. Quality of care (QoC) has been measured trough fifteen indicators, selected according main international Guidelines and approved by the multi-disciplinary team for thoracic malignancies. Results have been compared with those of a similar retrospective study conducted at the same hospital in 2008. RESULTS A total of 146 patients were considered eligible. Eight of fifteen indicators were not in line with the benchmarks. We compared the results obtained in the two separate periods. Moreover, we process some proposal to be discussed with the general management of the hospital, aimed to redesign NSCLC care pathways. CONCLUSIONS ICPs confirm to be feasible and to be an effective tool in real life. The periodic measurement of QoC indicators is necessary to ensure clinical governance of patients pathways.
Collapse
|
4
|
Trufelli DC, Moraes TV, Lima AAPR, Giglio AD. Epidemiological profile and prognostic factors in patients with lung cancer. Rev Assoc Med Bras (1992) 2017; 62:428-33. [PMID: 27656852 DOI: 10.1590/1806-9282.62.05.428] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2015] [Accepted: 05/16/2015] [Indexed: 11/22/2022] Open
Abstract
OBJECTIVE To describe the epidemiological profile of patients with lung cancer treated at a public tertiary referral hospital specializing in oncology, and to explore variables that may be related to the overall survival (OS) of these patients. METHOD Data from the medical records of all patients with invasive lung cancer consecutively seen at the Oncology Department of Hospital Estadual Mário Covas between August 2008 and December 2013 were extracted. The information obtained was submitted to statistical analysis. RESULTS Of the total 210 patients, 39 were excluded from analysis due to lack of information in the medical record. The most common histological type was adenocarcinoma, representing 39.41% of the sample, followed by squamous cell carcinoma with 25.29% and small-cell carcinoma with 13.53%. Other histological types were responsible for the remaining 21.76%. There was a statistically significant association between Karnofsky performance status (KPS) ≤ 70%, palliative chemotherapy lines performed and stage at diagnosis, and OS. Additionally, administration of target therapy to patients with EGFR mutation was associated with significantly better overall survival. However, analysis of laboratory variables (hemoglobin, albumin and LDH) as possible prognostic factors for survival showed no statistically significant relationship. Among patients with stage III and IV, the median OS was 10.1 months. CONCLUSION The risk factors for shorter OS were KPS score ≤ 70%, less than two lines of palliative chemotherapy, and stage III and IV at diagnosis. The implementation of CT screening for risk patients may allow earlier diagnosis of cases and improve these results.
Collapse
Affiliation(s)
- Damila Cristina Trufelli
- MD, Oncologist/MSc Student - Medical Oncologist. Assistant Physician of the Department of Hematology and Oncology, Faculdade de Medicina do ABC, Santo André, SP, Brazil
| | - Thayles Vinicius Moraes
- MSc Student - Resident Physician of the Department of Hematology and Oncology, Faculdade de Medicina do ABC, Santo André, SP, Brazil
| | - Aline Angélica Porto Rocha Lima
- MSc in Oncology - Medical Oncologist. Assistant Physician of the Department of Hematology and Oncology, Faculdade de Medicina do ABC, Santo André, SP, Brazil
| | - Auro Del Giglio
- Habilitation (BR: Livre-docência) - Full Professor of the Department of Hematology and Oncology, Faculdade de Medicina do ABC, Santo André, SP, Brazil
| |
Collapse
|
5
|
Minami S, Ogata Y, Ihara S, Yamamoto S, Komuta K. Trajectory of chemotherapy for patients with EGFR wild-type advanced pulmonary adenocarcinoma: a single-institution retrospective study. LUNG CANCER-TARGETS AND THERAPY 2017; 8:21-30. [PMID: 28293125 PMCID: PMC5342614 DOI: 10.2147/lctt.s124301] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
Abstract
Background Pulmonary adenocarcinoma, recently benefited by new cytotoxic and molecularly targeted drugs, has been classified by driver mutations, such as EGFR mutations. The aim of this study was to research the proportions of patients treated with first- to third-line chemotherapy and to find influential factors for the introduction of chemotherapy and survival benefit from chemotherapy. Materials and methods Data were collected retrospectively on patients who met the following criteria: adenocarcinoma, diagnosed between June 2007 and March 2015 at our hospital, stage IIIB or IV, and EGFR wild type. A nonchemotherapy group of patients who did not receive chemotherapy was compared with a chemotherapy group of patients who received it. The patients who had received first- to third-line chemotherapy between June 2007 and November 2015 at our hospital were also analyzed. Results During the study period, 46 patients did not receive chemotherapy, while 148, 89, and 48 received first-, second- and third-line chemotherapy, respectively. As predictive factors for unlikely chemotherapy, multivariate logistic analysis detected Eastern Cooperative Oncology Group (ECOG) performance status (PS) ≥2, hemoglobin <13.2 g/dL, creatinine clearance (Ccr) <50.4 mL/min, and CRP ≥0.53 mg/dL. As factors predicting shorter survival after chemotherapy, multivariate Cox proportional-hazard analyses detected age ≥75 years, ECOG PS ≥2, lower lymphocyte counts, and higher CRP for the first line; female, higher neutrophil counts, lower lymphocyte counts, reduced Ccr, hyponatremia, and shorter interval between first- and second-line chemotherapy for the second line; and age ≥75 years, body mass index <18.5 kg/m2, higher neutrophil counts, lower lymphocyte counts, hyponatremia, higher lactate dehydrogenase, and higher CRP for the third line. Conclusion Approximately 76% of patients were treated with first-line chemotherapy. Of those patients, 61% and 34% proceeded to second- and third-line chemotherapy, respectively. For patients with poor PS, anemia, reduced Ccr, and higher CRP, it is difficult to introduce chemotherapy.
Collapse
Affiliation(s)
- Seigo Minami
- Department of Respiratory Medicine, Osaka Police Hospital, Osaka, Japan
| | - Yoshitaka Ogata
- Department of Respiratory Medicine, Osaka Police Hospital, Osaka, Japan
| | - Shouichi Ihara
- Department of Respiratory Medicine, Osaka Police Hospital, Osaka, Japan
| | - Suguru Yamamoto
- Department of Respiratory Medicine, Osaka Police Hospital, Osaka, Japan
| | - Kiyoshi Komuta
- Department of Respiratory Medicine, Osaka Police Hospital, Osaka, Japan
| |
Collapse
|
6
|
Halfter K, Mayer B. Bringing 3D tumor models to the clinic - predictive value for personalized medicine. Biotechnol J 2017; 12. [PMID: 28098436 DOI: 10.1002/biot.201600295] [Citation(s) in RCA: 29] [Impact Index Per Article: 4.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2016] [Revised: 12/02/2016] [Accepted: 12/09/2016] [Indexed: 12/17/2022]
Abstract
Current decision-guiding algorithms in cancer drug treatment are based on decades of research and numerous clinical trials. For the majority of patients, this data is successfully applied for a systemic disease management. For a number of patients however, treatment stratification according to clinically based risk criteria will not be sufficient. The most effective treatment options are ideally identified prior to the start of clinical drug therapy. This review will discuss the implementation of three-dimensional (3D) cell culture models as a preclinical testing paradigm for the efficacy of clinical cancer treatment. Patient tumor-derived cells in 3D cultures duplicate the individual tumor microenvironment with a minimum of confounding factors. Clinical implementation of such personalized tumor models requires a high quality of methodological and clinical validation comparable to other biomarkers. A non-systematic literature search demonstrated the small number of prospective studies that have been conducted in this area of research. This may explain the current reluctance of many physicians and insurance providers in implementing this type of assay into the clinical diagnostic routine despite potential benefit for patients. Achieving valid and reproducible results with a high level of evidence is central in improving the acceptance of preclinical 3D tumor models.
Collapse
Affiliation(s)
| | - Barbara Mayer
- SpheroTec GmbH, Martinsried, Germany.,Department of General, Visceral, and Transplantation Surgery, Hospital of the LMU Munich, Munich, Germany
| |
Collapse
|
7
|
Kim J, Cho CK, Yoo HS. Survival Analysis of Advanced Non-Small Cell Lung Cancer Patients Treated by Using Wheel Balance Cancer Therapy. Integr Cancer Ther 2016; 15:467-477. [PMID: 27151594 PMCID: PMC5739164 DOI: 10.1177/1534735416639714] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2015] [Revised: 12/18/2015] [Accepted: 02/25/2016] [Indexed: 12/15/2022] Open
Abstract
Objective To investigate the clinical effect and the overall survival (OS) rate of patients with advanced non-small cell lung cancer (NSCLC) who have undergone Wheel Balance Cancer Therapy (WBCT). Methods The cases of 33 patients with advanced NSCLC who were treated with WBCT at the East West Cancer Center (EWCC) between October 4, 2004, and October 3, 2013, without undergoing concurrent conventional treatment were analyzed. The Kaplan-Meier method was used to estimate the OS of the cases, and the median OS was calculated according to age, Eastern Cooperative Oncology Group Performance Status (ECOG PS), conventional-treatment history, WBCT treatment duration, and histological tumor type. Results The median OS of all patients was 31.1 (95% confidence interval [CI] = 3.5-58.7) months; the OS rates were 63.6% and 24.2% at years 1 and 2, respectively. The median OS rates of patients under and over 65 years were 45.2 (95% CI = 13.5-76.9) and 19.5 (95% CI = 7.1-31.8) months, respectively (P = .189). The median OS rates of patients who received WBCT for >14 days but <28 days and those who received WBCT for ≥28 days were 16.2 (95% CI = 13.3-19.2) and 45.2 (95% CI = 14.4-76.0) months, respectively (P = .437). The median OS rates of patients who had undergone prior conventional treatment and those who had not were 45.2 (95% CI = 9.1-81.3) and 3.9 (95% CI = unable to calculate) months, respectively (P = .000). The median OS rates of patients with squamous cell carcinoma (SCC) and non-SCC lung cancer were 5.6 (95% CI = unable to calculate) and 45.2 (95% CI = 9.1-81.3) months, respectively (P = .262). The median OS rate of patients with ECOG PS ≥3 was 14.3 (95% CI = 8.8-19.8) months; that of patients ECOG PS <3 could not be calculated. However, the mean OS rates of patients with ECOG PS <3 and with ECOG PS ≥3 were 85.7 (95% CI = 58.4-113.0) and 12.7 (95% CI = 8.5-16.9) months, respectively (P = .000). No severe adverse events were encountered. Conclusions Our study indicates that WBCT might be effective to prolong the length of survival for patients with advanced NSCLC who have previously undergone conventional treatment and have an ECOG PS <3.
Collapse
Affiliation(s)
- Jongmin Kim
- Dunsan Korean Medicine Hospital of Daejeon University, Daejeon, Republic of Korea
| | - Chong-Kwan Cho
- Dunsan Korean Medicine Hospital of Daejeon University, Daejeon, Republic of Korea
| | - Hwa-Seung Yoo
- Dunsan Korean Medicine Hospital of Daejeon University, Daejeon, Republic of Korea
| |
Collapse
|
8
|
Minami S, Ogata Y, Ihara S, Yamamoto S, Komuta K. Outcomes and prognostic factors of chemotherapy for patients with locally advanced or metastatic pulmonary squamous cell carcinoma. LUNG CANCER (AUCKLAND, N.Z.) 2016; 7:99-110. [PMID: 28210166 PMCID: PMC5310705 DOI: 10.2147/lctt.s107560] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
BACKGROUND Pulmonary squamous cell carcinoma has not benefited from improvements in chemotherapy over the past decade, compared with non-squamous non-small-cell lung cancer. Nowadays, treatment strategies differ between squamous and non-squamous non-small-cell lung cancers. This study aimed to investigate the percentage of patients treated with first-, second-, or third-line chemotherapy and the characteristics of patients for whom chemotherapy has been beneficial. METHOD Data on patients with stage IIIB or IV squamous cell carcinoma diagnosed between June 2007 and March 2015, and on patients who had received first-, second-, or third-line chemotherapy between June 2007 and November 2015 at our hospital, were retrospectively extracted from our institutional medical charts. We also compared patients who were treated with chemotherapy (chemotherapy group) and patients who were not (non-chemotherapy group) using multivariate logistic regression and multivariate Cox hazard analyses, respectively. RESULTS During the study period, 103, 63, and 32 patients received first-, second-, and third-line chemotherapy, respectively. Fifty-one patients did not receive chemotherapy. Factors predicting unlikely chemotherapy included age ≥75 years, Eastern Cooperative Oncology Group (ECOG)-performance status (PS) ≥2, Charlson comorbidity index ≥2, hemoglobin <12.2 g/dL, red cell distribution width ≥13.9%, and serum sodium <140 mEq/L. Factors predicting survival for each line of chemotherapy included the following: ECOG-PS ≥2 for first-line; ECOG-PS ≥2 and lymphocyte count for second-line; and ECOG-PS ≥2, body mass index <18.5 kg/m2, and hemoglobin and lactate dehydrogenase levels for third-line. CONCLUSION Approximately 66% of patients received first-line chemotherapy. Of those, 66% and 33% received second- and third-line chemotherapy, respectively. ECOG-PS was always an essential prognostic factor when considering introducing chemotherapy and proceeding with additional chemotherapy. Other markers, such as lymphocyte count, body mass index, anemia, and lactate dehydrogenase level, may be useful depending on the patient and line of chemotherapy.
Collapse
Affiliation(s)
- Seigo Minami
- Department of Respiratory Medicine, Osaka Police Hospital, Osaka, Japan
| | - Yoshitaka Ogata
- Department of Respiratory Medicine, Osaka Police Hospital, Osaka, Japan
| | - Shouichi Ihara
- Department of Respiratory Medicine, Osaka Police Hospital, Osaka, Japan
| | - Suguru Yamamoto
- Department of Respiratory Medicine, Osaka Police Hospital, Osaka, Japan
| | - Kiyoshi Komuta
- Department of Respiratory Medicine, Osaka Police Hospital, Osaka, Japan
| |
Collapse
|
9
|
Yu T, He Z, Zhou Q, Ma J, Wei L. Analysis of the factors influencing lung cancer hospitalization expenses using data mining. Thorac Cancer 2015; 6:338-45. [PMID: 26273381 PMCID: PMC4448379 DOI: 10.1111/1759-7714.12147] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2014] [Accepted: 06/10/2014] [Indexed: 12/11/2022] Open
Abstract
Background Hospitalization expenses for the therapy of lung cancer are not only a direct economic burden on patients, but also the focus of medical insurance departments. Therefore, the method for classifying and analyzing lung cancer hospitalization expenses so as to predict reasonable medical cost has become an issue of common interest for both hospitals and insurance institutions. Methods A C5.0 algorithm is adopted to analyze factors influencing hospitalization expenses of 731 lung cancer patients. A C5.0 algorithm is a data mining method used to classify calculation. Results Increasing the number of input variables leads to variation in the importance of different variables, but length of stay (LOS), major therapy, and medicine cost are the three variables of greater importance. They are important factors that affect the hospitalization cost of lung cancer patients. In all three calculations, the classification accuracy rate of training and testing partition sets reached 84% and above. The classification accuracy rate reached over 95% after addition of the cost variables. Conclusion The classification rules are proven to be in accordance with actual clinical practice. The model established by the research can also be applied to other diseases in the screening and analysis of disease hospitalization costs according to selected feature variables.
Collapse
Affiliation(s)
- Tianzhi Yu
- College of Management & Economics, Tianjin University Tianjin, China ; Tianjin Medical University General Hospital Tianjin, China
| | - Zhen He
- College of Management & Economics, Tianjin University Tianjin, China
| | - Qinghua Zhou
- Tianjin Medical University General Hospital Tianjin, China
| | - Jun Ma
- Tianjin Medical University General Hospital Tianjin, China
| | - Lihui Wei
- Tianjin Medical University General Hospital Tianjin, China
| |
Collapse
|
10
|
Eldeeb H, Camileri P, Mak C. Palliative chemotherapy followed by consolidation radiotherapy in patients with advanced and metastatic non-small cell lung cancer not suitable for radical treatment. ACTA ACUST UNITED AC 2012. [DOI: 10.1007/s10330-012-0970-4] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|