def infer_or_drop_diagnosis(bids_df: pd.DataFrame) -> pd.DataFrame:
"""
Deduce the diagnosis when missing from previous and following sessions of the subject. If not identical, the session
is dropped. Sessions with no diagnosis are also dropped when there are the last sessions of the follow-up.
Args:
bids_df: DataFrame with columns including ['participant_id', 'session_id', 'diagnosis']
Returns:
cleaned DataFrame
"""
bids_copy_df = copy(bids_df)
found_diag_interpol = 0
for subject, subject_df in bids_df.groupby(level=0):
session_list = [
int(session[5::]) for _, session in subject_df.index.values
]
for _, session in subject_df.index.values:
diagnosis = subject_df.loc[(subject, session), "diagnosis"]
session_nb = int(session[5::])
if isinstance(diagnosis, float):
if session == last_session(session_list):
bids_copy_df.drop((subject, session), inplace=True)
else:
prev_session = neighbour_session(session_nb, session_list,
-1)
prev_diagnosis = bids_df.loc[(subject, prev_session),
"diagnosis"]
while isinstance(
prev_diagnosis, float
) and prev_session != first_session(subject_df):
prev_session = neighbour_session(
int(prev_session[5::]), session_list, -1)
prev_diagnosis = bids_df.loc[(subject, prev_session),
"diagnosis"]
post_session = neighbour_session(session_nb, session_list,
+1)
post_diagnosis = bids_df.loc[(subject, post_session),
"diagnosis"]
while isinstance(
post_diagnosis, float
) and post_session != last_session(session_list):
post_session = neighbour_session(
int(post_session[5::]), session_list, +1)
post_diagnosis = bids_df.loc[(subject, post_session),
"diagnosis"]
if prev_diagnosis == post_diagnosis:
found_diag_interpol += 1
bids_copy_df.loc[(subject, session),
"diagnosis"] = prev_diagnosis
else:
bids_copy_df.drop((subject, session), inplace=True)
logger.debug(f"Inferred diagnosis: {found_diag_interpol}")
return bids_copy_df
def diagnosis_removal(MCI_df: pd.DataFrame,
diagnosis_list: List[str]) -> pd.DataFrame:
"""
Removes subjects whom last diagnosis is in the list provided (avoid to keep rMCI and pMCI in sMCI lists).
Args:
MCI_df: DataFrame with columns including ['participant_id', 'session_id', 'diagnosis']
diagnosis_list: list of diagnoses that will be removed
Returns:
cleaned DataFrame
"""
output_df = copy(MCI_df)
# Remove subjects who regress to CN label, even late in the follow-up
for subject, subject_df in MCI_df.groupby(level=0):
session_list = [
int(session[5::]) for _, session in subject_df.index.values
]
last_session_id = last_session(session_list)
last_diagnosis = subject_df.loc[(subject, last_session_id),
"diagnosis"]
if last_diagnosis in diagnosis_list:
output_df.drop(subject, inplace=True)
return output_df
def mci_stability(bids_df: pd.DataFrame,
horizon_time: int = 36) -> pd.DataFrame:
"""
A method to label all MCI sessions depending on their stability on the time horizon
Args:
bids_df: DataFrame with columns including ['participant_id', 'session_id', 'diagnosis']
horizon_time: time horizon in months
Returns:
DataFrame with new labels
"""
diagnosis_list = ["MCI", "EMCI", "LMCI"]
bids_df = bids_df[(bids_df.baseline_diagnosis.isin(diagnosis_list))]
bids_df = cleaning_nan_diagnoses(bids_df)
bids_df = infer_or_drop_diagnosis(bids_df)
# Check possible double change in diagnosis in time
bids_copy_df = copy(bids_df)
nb_subjects = 0
for subject, subject_df in bids_df.groupby(level=0):
session_list = [
int(session[5::]) for _, session in subject_df.index.values
]
session_list.sort()
diagnosis_list = []
for session in session_list:
if session < 10:
diagnosis_list.append(bids_df.loc[(subject,
"ses-M0" + str(session)),
"diagnosis"])
else:
diagnosis_list.append(bids_df.loc[(subject,
"ses-M" + str(session)),
"diagnosis"])
new_diagnosis = diagnosis_list[0]
nb_change = 0
for diagnosis in diagnosis_list:
if new_diagnosis != diagnosis:
new_diagnosis = diagnosis
nb_change += 1
if nb_change > 1:
nb_subjects += 1
bids_copy_df.drop(subject, inplace=True)
logger.debug(f"Dropped subjects: {nb_subjects}")
bids_df = copy(bids_copy_df)
# Stability of sessions
stability_dict = {
"CN": "r",
"MCI": "s",
"AD": "p",
} # Do not take into account the case of missing diag = nan
bids_copy_df = copy(bids_df)
for subject, subject_df in bids_df.groupby(level=0):
session_list = [
int(session[5::]) for _, session in subject_df.index.values
]
for _, session in subject_df.index.values:
diagnosis = subject_df.loc[(subject, session), "diagnosis"]
# If the diagnosis is not MCI we remove the time point
if diagnosis != "MCI":
bids_copy_df.drop((subject, session), inplace=True)
else:
session_nb = int(session[5::])
horizon_session_nb = session_nb + horizon_time
horizon_session = "ses-M" + str(horizon_session_nb)
# print(session, '-->', horizon_session)
if horizon_session_nb in session_list:
horizon_diagnosis = subject_df.loc[(subject,
horizon_session),
"diagnosis"]
update_diagnosis = stability_dict[horizon_diagnosis] + "MCI"
# print(horizon_diagnosis, update_diagnosis)
bids_copy_df.loc[(subject, session),
"diagnosis"] = update_diagnosis
else:
if after_end_screening(horizon_session_nb, session_list):
# Two situations, change in last session AD or CN --> pMCI or rMCI
# Last session MCI --> uMCI
last_diagnosis = subject_df.loc[(
subject, last_session(session_list)), "diagnosis"]
# This section must be discussed --> removed in Jorge's paper
if last_diagnosis != "MCI":
update_diagnosis = stability_dict[
last_diagnosis] + "MCI"
else:
update_diagnosis = "uMCI"
# print(update_diagnosis)
bids_copy_df.loc[(subject, session),
"diagnosis"] = update_diagnosis
else:
prev_session = neighbour_session(
horizon_session_nb, session_list, -1)
post_session = neighbour_session(
horizon_session_nb, session_list, +1)
# print('prev_session', prev_session)
# print('post_session', post_session)
prev_diagnosis = subject_df.loc[(subject,
prev_session),
"diagnosis"]
if prev_diagnosis != "MCI":
update_diagnosis = stability_dict[
prev_diagnosis] + "MCI"
else:
post_diagnosis = subject_df.loc[(subject,
post_session),
"diagnosis"]
if post_diagnosis != "MCI":
update_diagnosis = "uMCI"
else:
update_diagnosis = "sMCI"
# print(update_diagnosis)
bids_copy_df.loc[(subject, session),
"diagnosis"] = update_diagnosis
return bids_copy_df