Machine Learning Algorithm-Aided Determination of Predictors of Mortality from Diabetic Foot Sepsis at a Regional Hospital in South Africa During the COVID-19 Pandemic
<i>Background and Objectives</i>: Diabetic foot sepsis (DFS) accounts for approximately 60% of hospital admissions in patients with diabetes mellitus (DM). Individuals with DM are at risk of severe COVID-19. This study investigated factors associated with major amputation and mortality i...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Medicina |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1648-9144/60/10/1718 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850206099902300160 |
|---|---|
| author | Carlos Matsinhe Shingirai Brenda Kagodora Tshifhiwa Mukheli Tshepo Polly Mokoena William Khabe Malebati Maeyane Stephens Moeng Thifhelimbilu Emmanuel Luvhengo |
| author_facet | Carlos Matsinhe Shingirai Brenda Kagodora Tshifhiwa Mukheli Tshepo Polly Mokoena William Khabe Malebati Maeyane Stephens Moeng Thifhelimbilu Emmanuel Luvhengo |
| author_sort | Carlos Matsinhe |
| collection | DOAJ |
| description | <i>Background and Objectives</i>: Diabetic foot sepsis (DFS) accounts for approximately 60% of hospital admissions in patients with diabetes mellitus (DM). Individuals with DM are at risk of severe COVID-19. This study investigated factors associated with major amputation and mortality in patients admitted with DFS during the COVID-19 pandemic. <i>Materials and Methods</i>: Demographic information, COVID-19 and HIV status, clinical findings, laboratory results, treatment and outcome from records of patients with diabetic foot sepsis, were collected and analysed. Supervised machine learning algorithms were used to compare their ability to predict mortality due to diabetic foot sepsis. <i>Results</i>: Overall, 114 records were found and 57.9% (66/114) were of male patients. The mean age of the patients was 55.7 (14) years and 47.4% (54/114) and 36% (41/114) tested positive for COVID-19 and HIV, respectively. The median c-reactive protein was 168 mg/dl, urea 7.8 mmol/L and creatinine 92 µmol/L. The mean potassium level was 4.8 ± 0.9 mmol, and glycosylated haemoglobin 11.2 ± 3%. The main outcomes included major amputation in 69.3% (79/114) and mortality of 37.7% (43/114) died. AI. The levels of potassium, urea, creatinine and HbA1c were significantly higher in the deceased. <i>Conclusions</i>: The COVID-19 pandemic led to an increase in the rate of major amputation and mortality in patients with DFS. The in-hospital mortality was higher in patients above 60 years of age who tested positive for COVID-19. The Random Forest algorithm of ML can be highly effective in predicting major amputation and death in patients with DFS. |
| format | Article |
| id | doaj-art-6423d5a70aa549debbb416ce07515941 |
| institution | OA Journals |
| issn | 1010-660X 1648-9144 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Medicina |
| spelling | doaj-art-6423d5a70aa549debbb416ce075159412025-08-20T02:10:56ZengMDPI AGMedicina1010-660X1648-91442024-10-016010171810.3390/medicina60101718Machine Learning Algorithm-Aided Determination of Predictors of Mortality from Diabetic Foot Sepsis at a Regional Hospital in South Africa During the COVID-19 PandemicCarlos Matsinhe0Shingirai Brenda Kagodora1Tshifhiwa Mukheli2Tshepo Polly Mokoena3William Khabe Malebati4Maeyane Stephens Moeng5Thifhelimbilu Emmanuel Luvhengo6Department of Surgery, Thelle Mogoerane Hospital, University of the Witwatersrand, Johannesburg 2017, South AfricaDepartment of Nuclear Medicine, University of the Witwatersrand, Johannesburg 2017, South AfricaDirectorate of Oral Health and Therapeutic Services, Gauteng Province Department of Health, Johannesburg 2001, South AfricaDepartment of Podiatry, Charlotte Maxeke Johannesburg Academic Hospital, Johannesburg 2193, South AfricaNursing Department, Charlotte Maxeke Johannesburg Academic Hospital, Johannesburg 2193, South AfricaDepartment of Surgery, Charlotte Maxeke Johannesburg Academic Hospital, Johannesburg 2193, South AfricaDepartment of Surgery, Charlotte Maxeke Johannesburg Academic Hospital, Johannesburg 2193, South Africa<i>Background and Objectives</i>: Diabetic foot sepsis (DFS) accounts for approximately 60% of hospital admissions in patients with diabetes mellitus (DM). Individuals with DM are at risk of severe COVID-19. This study investigated factors associated with major amputation and mortality in patients admitted with DFS during the COVID-19 pandemic. <i>Materials and Methods</i>: Demographic information, COVID-19 and HIV status, clinical findings, laboratory results, treatment and outcome from records of patients with diabetic foot sepsis, were collected and analysed. Supervised machine learning algorithms were used to compare their ability to predict mortality due to diabetic foot sepsis. <i>Results</i>: Overall, 114 records were found and 57.9% (66/114) were of male patients. The mean age of the patients was 55.7 (14) years and 47.4% (54/114) and 36% (41/114) tested positive for COVID-19 and HIV, respectively. The median c-reactive protein was 168 mg/dl, urea 7.8 mmol/L and creatinine 92 µmol/L. The mean potassium level was 4.8 ± 0.9 mmol, and glycosylated haemoglobin 11.2 ± 3%. The main outcomes included major amputation in 69.3% (79/114) and mortality of 37.7% (43/114) died. AI. The levels of potassium, urea, creatinine and HbA1c were significantly higher in the deceased. <i>Conclusions</i>: The COVID-19 pandemic led to an increase in the rate of major amputation and mortality in patients with DFS. The in-hospital mortality was higher in patients above 60 years of age who tested positive for COVID-19. The Random Forest algorithm of ML can be highly effective in predicting major amputation and death in patients with DFS.https://www.mdpi.com/1648-9144/60/10/1718diabetic foot sepsisCOVID-19HIVmachine learningmortality |
| spellingShingle | Carlos Matsinhe Shingirai Brenda Kagodora Tshifhiwa Mukheli Tshepo Polly Mokoena William Khabe Malebati Maeyane Stephens Moeng Thifhelimbilu Emmanuel Luvhengo Machine Learning Algorithm-Aided Determination of Predictors of Mortality from Diabetic Foot Sepsis at a Regional Hospital in South Africa During the COVID-19 Pandemic Medicina diabetic foot sepsis COVID-19 HIV machine learning mortality |
| title | Machine Learning Algorithm-Aided Determination of Predictors of Mortality from Diabetic Foot Sepsis at a Regional Hospital in South Africa During the COVID-19 Pandemic |
| title_full | Machine Learning Algorithm-Aided Determination of Predictors of Mortality from Diabetic Foot Sepsis at a Regional Hospital in South Africa During the COVID-19 Pandemic |
| title_fullStr | Machine Learning Algorithm-Aided Determination of Predictors of Mortality from Diabetic Foot Sepsis at a Regional Hospital in South Africa During the COVID-19 Pandemic |
| title_full_unstemmed | Machine Learning Algorithm-Aided Determination of Predictors of Mortality from Diabetic Foot Sepsis at a Regional Hospital in South Africa During the COVID-19 Pandemic |
| title_short | Machine Learning Algorithm-Aided Determination of Predictors of Mortality from Diabetic Foot Sepsis at a Regional Hospital in South Africa During the COVID-19 Pandemic |
| title_sort | machine learning algorithm aided determination of predictors of mortality from diabetic foot sepsis at a regional hospital in south africa during the covid 19 pandemic |
| topic | diabetic foot sepsis COVID-19 HIV machine learning mortality |
| url | https://www.mdpi.com/1648-9144/60/10/1718 |
| work_keys_str_mv | AT carlosmatsinhe machinelearningalgorithmaideddeterminationofpredictorsofmortalityfromdiabeticfootsepsisataregionalhospitalinsouthafricaduringthecovid19pandemic AT shingiraibrendakagodora machinelearningalgorithmaideddeterminationofpredictorsofmortalityfromdiabeticfootsepsisataregionalhospitalinsouthafricaduringthecovid19pandemic AT tshifhiwamukheli machinelearningalgorithmaideddeterminationofpredictorsofmortalityfromdiabeticfootsepsisataregionalhospitalinsouthafricaduringthecovid19pandemic AT tshepopollymokoena machinelearningalgorithmaideddeterminationofpredictorsofmortalityfromdiabeticfootsepsisataregionalhospitalinsouthafricaduringthecovid19pandemic AT williamkhabemalebati machinelearningalgorithmaideddeterminationofpredictorsofmortalityfromdiabeticfootsepsisataregionalhospitalinsouthafricaduringthecovid19pandemic AT maeyanestephensmoeng machinelearningalgorithmaideddeterminationofpredictorsofmortalityfromdiabeticfootsepsisataregionalhospitalinsouthafricaduringthecovid19pandemic AT thifhelimbiluemmanuelluvhengo machinelearningalgorithmaideddeterminationofpredictorsofmortalityfromdiabeticfootsepsisataregionalhospitalinsouthafricaduringthecovid19pandemic |