Fundamentals of Machine Learning for NHS using R
Length of Stay (LOS) is defined in number of days from the initial admit date to the date that the patient is discharged from any given hospital facility.
LOS prediction at the time of admission can greatly enhance the quality of care as well as operational workload efficiency and help with accurate planning for discharges resulting in lowering of various other quality measures such as readmissions.
| Field | Type | Description |
|---|---|---|
| gender | String | Gender of the patient - M or F |
| dialysisrenalendstage | String | Flag for renal disease during encounter |
| asthma | String | Flag for asthma during encounter |
| irondef | String | Flag for iron deficiency during encounter |
| pneum | String | Flag for pneumonia during encounter |
| substancedependence | String | Flag for substance dependence during encounter |
| psychologicaldisordermajor | String | Flag for major psychological disorder during encounter |
| depress | String | Flag for depression during encounter |
| psychother | String | Flag for other psychological disorder during encounter |
| fibrosisandother | String | Flag for fibrosis during encounter |
| malnutrition | String | Flag for malnutrition during encounter |
| hemo | String | Flag for blood disorder during encounter |
| secondarydiagnosisnonicd9 | Integer | Flag for whether a non ICD 9 formatted diagnosis was coded as a secondary diagnosis |
| facid | Integer | Facility ID at which the encounter occurred |
| Field | Type | Description |
|---|---|---|
| rcount | Integer | Number of readmissions within last 180 days |
| hematocrit | Float | Average haematocrit value during encounter (g/dL) |
| neutrophils | Float | Average neutrophils value during encounter (cells/microL) |
| sodium | Float | Average sodium value during encounter (mmol/L) |
| glucose | Float | Average glucose value during encounter (mmol/L) |
| bloodureanitro | Float | Average blood urea nitrogen value during encounter (mg/dL) |
| creatinine | Float | Average creatinine value during encounter (mg/dL) |
| bmi | Float | Average BMI during encounter (kg/m2) |
| pulse | Float | Average pulse during encounter (beats/m) |
| respiration | Float | Average respiration during encounter (breaths/m) |
| Field | Type | Description |
|---|---|---|
| eid | Integer | Unique Id of the hospital admission |
| vdate | String | Visit date |
| discharged | String | Date of discharge |
We will try to fit a multiple regression model. Recall that this means that our hypothesis function is of the form:
\[h(x) = \beta_0 + \beta_1 x_1 + \dots + \beta_m x_m \qquad \beta_0, \beta_1, \dots, \beta_m \in \mathbb{R}\]
What are the challenges?